diff --git a/Documentation/devicetree/bindings/net/asix,ax88796c.yaml b/Documentation/devicetree/bindings/net/asix,ax88796c.yaml new file mode 100644 index 000000000000..699ebf452479 --- /dev/null +++ b/Documentation/devicetree/bindings/net/asix,ax88796c.yaml @@ -0,0 +1,73 @@ +# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/asix,ax88796c.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: ASIX AX88796C SPI Ethernet Adapter + +maintainers: + - Łukasz Stelmach + +description: | + ASIX AX88796C is an Ethernet controller with a built in PHY. This + describes SPI mode of the chip. + + The node for this driver must be a child node of an SPI controller, + hence all mandatory properties described in + ../spi/spi-controller.yaml must be specified. + +allOf: + - $ref: ethernet-controller.yaml# + +properties: + compatible: + const: asix,ax88796c + + reg: + maxItems: 1 + + spi-max-frequency: + maximum: 40000000 + + interrupts: + maxItems: 1 + + reset-gpios: + description: + A GPIO line handling reset of the chip. As the line is active low, + it should be marked GPIO_ACTIVE_LOW. + maxItems: 1 + + local-mac-address: true + + mac-address: true + +required: + - compatible + - reg + - spi-max-frequency + - interrupts + - reset-gpios + +additionalProperties: false + +examples: + # Artik5 eval board + - | + #include + #include + spi0 { + #address-cells = <1>; + #size-cells = <0>; + + ethernet@0 { + compatible = "asix,ax88796c"; + reg = <0x0>; + local-mac-address = [00 00 00 00 00 00]; /* Filled in by a bootloader */ + interrupt-parent = <&gpx2>; + interrupts = <0 IRQ_TYPE_LEVEL_LOW>; + spi-max-frequency = <40000000>; + reset-gpios = <&gpe0 2 GPIO_ACTIVE_LOW>; + }; + }; diff --git a/Documentation/devicetree/bindings/net/dsa/dsa.yaml b/Documentation/devicetree/bindings/net/dsa/dsa.yaml index 16aa192c118e..2ad7f79ad371 100644 --- a/Documentation/devicetree/bindings/net/dsa/dsa.yaml +++ b/Documentation/devicetree/bindings/net/dsa/dsa.yaml @@ -46,6 +46,9 @@ patternProperties: type: object description: Ethernet switch ports + allOf: + - $ref: "http://devicetree.org/schemas/net/ethernet-controller.yaml#" + properties: reg: description: Port number @@ -73,11 +76,14 @@ patternProperties: dsa-tag-protocol: description: Instead of the default, the switch will use this tag protocol if - possible. Useful when a device supports multiple protcols and + possible. Useful when a device supports multiple protocols and the default is incompatible with the Ethernet device. enum: - dsa - edsa + - ocelot + - ocelot-8021q + - seville phy-handle: true @@ -91,6 +97,10 @@ patternProperties: managed: true + rx-internal-delay-ps: true + + tx-internal-delay-ps: true + required: - reg diff --git a/Documentation/devicetree/bindings/net/dsa/nxp,sja1105.yaml b/Documentation/devicetree/bindings/net/dsa/nxp,sja1105.yaml index f978f8719d8e..24cd733c11d1 100644 --- a/Documentation/devicetree/bindings/net/dsa/nxp,sja1105.yaml +++ b/Documentation/devicetree/bindings/net/dsa/nxp,sja1105.yaml @@ -74,10 +74,42 @@ properties: - compatible - reg +patternProperties: + "^(ethernet-)?ports$": + patternProperties: + "^(ethernet-)?port@[0-9]+$": + allOf: + - if: + properties: + phy-mode: + contains: + enum: + - rgmii + - rgmii-rxid + - rgmii-txid + - rgmii-id + then: + properties: + rx-internal-delay-ps: + $ref: "#/$defs/internal-delay-ps" + tx-internal-delay-ps: + $ref: "#/$defs/internal-delay-ps" + required: - compatible - reg +$defs: + internal-delay-ps: + description: + Disable tunable delay lines using 0 ps, or enable them and select + the phase between 1640 ps (73.8 degree shift at 1Gbps) and 2260 ps + (101.7 degree shift) in increments of 0.9 degrees (20 ps). + enum: + [0, 1640, 1660, 1680, 1700, 1720, 1740, 1760, 1780, 1800, 1820, 1840, + 1860, 1880, 1900, 1920, 1940, 1960, 1980, 2000, 2020, 2040, 2060, 2080, + 2100, 2120, 2140, 2160, 2180, 2200, 2220, 2240, 2260] + unevaluatedProperties: false examples: @@ -97,29 +129,40 @@ examples: port@0 { phy-handle = <&rgmii_phy6>; phy-mode = "rgmii-id"; + rx-internal-delay-ps = <0>; + tx-internal-delay-ps = <0>; reg = <0>; }; port@1 { phy-handle = <&rgmii_phy3>; phy-mode = "rgmii-id"; + rx-internal-delay-ps = <0>; + tx-internal-delay-ps = <0>; reg = <1>; }; port@2 { phy-handle = <&rgmii_phy4>; phy-mode = "rgmii-id"; + rx-internal-delay-ps = <0>; + tx-internal-delay-ps = <0>; reg = <2>; }; port@3 { + phy-handle = <&rgmii_phy4>; phy-mode = "rgmii-id"; + rx-internal-delay-ps = <0>; + tx-internal-delay-ps = <0>; reg = <3>; }; port@4 { ethernet = <&enet2>; phy-mode = "rgmii"; + rx-internal-delay-ps = <0>; + tx-internal-delay-ps = <0>; reg = <4>; fixed-link { diff --git a/Documentation/devicetree/bindings/net/dsa/qca8k.txt b/Documentation/devicetree/bindings/net/dsa/qca8k.txt deleted file mode 100644 index 8c73f67c43ca..000000000000 --- a/Documentation/devicetree/bindings/net/dsa/qca8k.txt +++ /dev/null @@ -1,215 +0,0 @@ -* Qualcomm Atheros QCA8xxx switch family - -Required properties: - -- compatible: should be one of: - "qca,qca8327" - "qca,qca8334" - "qca,qca8337" - -- #size-cells: must be 0 -- #address-cells: must be 1 - -Optional properties: - -- reset-gpios: GPIO to be used to reset the whole device - -Subnodes: - -The integrated switch subnode should be specified according to the binding -described in dsa/dsa.txt. If the QCA8K switch is connect to a SoC's external -mdio-bus each subnode describing a port needs to have a valid phandle -referencing the internal PHY it is connected to. This is because there's no -N:N mapping of port and PHY id. -To declare the internal mdio-bus configuration, declare a mdio node in the -switch node and declare the phandle for the port referencing the internal -PHY is connected to. In this config a internal mdio-bus is registered and -the mdio MASTER is used as communication. - -Don't use mixed external and internal mdio-bus configurations, as this is -not supported by the hardware. - -The CPU port of this switch is always port 0. - -A CPU port node has the following optional node: - -- fixed-link : Fixed-link subnode describing a link to a non-MDIO - managed entity. See - Documentation/devicetree/bindings/net/fixed-link.txt - for details. - -For QCA8K the 'fixed-link' sub-node supports only the following properties: - -- 'speed' (integer, mandatory), to indicate the link speed. Accepted - values are 10, 100 and 1000 -- 'full-duplex' (boolean, optional), to indicate that full duplex is - used. When absent, half duplex is assumed. - -Examples: - -for the external mdio-bus configuration: - - &mdio0 { - phy_port1: phy@0 { - reg = <0>; - }; - - phy_port2: phy@1 { - reg = <1>; - }; - - phy_port3: phy@2 { - reg = <2>; - }; - - phy_port4: phy@3 { - reg = <3>; - }; - - phy_port5: phy@4 { - reg = <4>; - }; - - switch@10 { - compatible = "qca,qca8337"; - #address-cells = <1>; - #size-cells = <0>; - - reset-gpios = <&gpio 42 GPIO_ACTIVE_LOW>; - reg = <0x10>; - - ports { - #address-cells = <1>; - #size-cells = <0>; - port@0 { - reg = <0>; - label = "cpu"; - ethernet = <&gmac1>; - phy-mode = "rgmii"; - fixed-link { - speed = 1000; - full-duplex; - }; - }; - - port@1 { - reg = <1>; - label = "lan1"; - phy-handle = <&phy_port1>; - }; - - port@2 { - reg = <2>; - label = "lan2"; - phy-handle = <&phy_port2>; - }; - - port@3 { - reg = <3>; - label = "lan3"; - phy-handle = <&phy_port3>; - }; - - port@4 { - reg = <4>; - label = "lan4"; - phy-handle = <&phy_port4>; - }; - - port@5 { - reg = <5>; - label = "wan"; - phy-handle = <&phy_port5>; - }; - }; - }; - }; - -for the internal master mdio-bus configuration: - - &mdio0 { - switch@10 { - compatible = "qca,qca8337"; - #address-cells = <1>; - #size-cells = <0>; - - reset-gpios = <&gpio 42 GPIO_ACTIVE_LOW>; - reg = <0x10>; - - ports { - #address-cells = <1>; - #size-cells = <0>; - - port@0 { - reg = <0>; - label = "cpu"; - ethernet = <&gmac1>; - phy-mode = "rgmii"; - fixed-link { - speed = 1000; - full-duplex; - }; - }; - - port@1 { - reg = <1>; - label = "lan1"; - phy-mode = "internal"; - phy-handle = <&phy_port1>; - }; - - port@2 { - reg = <2>; - label = "lan2"; - phy-mode = "internal"; - phy-handle = <&phy_port2>; - }; - - port@3 { - reg = <3>; - label = "lan3"; - phy-mode = "internal"; - phy-handle = <&phy_port3>; - }; - - port@4 { - reg = <4>; - label = "lan4"; - phy-mode = "internal"; - phy-handle = <&phy_port4>; - }; - - port@5 { - reg = <5>; - label = "wan"; - phy-mode = "internal"; - phy-handle = <&phy_port5>; - }; - }; - - mdio { - #address-cells = <1>; - #size-cells = <0>; - - phy_port1: phy@0 { - reg = <0>; - }; - - phy_port2: phy@1 { - reg = <1>; - }; - - phy_port3: phy@2 { - reg = <2>; - }; - - phy_port4: phy@3 { - reg = <3>; - }; - - phy_port5: phy@4 { - reg = <4>; - }; - }; - }; - }; diff --git a/Documentation/devicetree/bindings/net/dsa/qca8k.yaml b/Documentation/devicetree/bindings/net/dsa/qca8k.yaml new file mode 100644 index 000000000000..48de0ace265d --- /dev/null +++ b/Documentation/devicetree/bindings/net/dsa/qca8k.yaml @@ -0,0 +1,362 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/dsa/qca8k.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Qualcomm Atheros QCA83xx switch family + +maintainers: + - John Crispin + +description: + If the QCA8K switch is connect to an SoC's external mdio-bus, each subnode + describing a port needs to have a valid phandle referencing the internal PHY + it is connected to. This is because there is no N:N mapping of port and PHY + ID. To declare the internal mdio-bus configuration, declare an MDIO node in + the switch node and declare the phandle for the port, referencing the internal + PHY it is connected to. In this config, an internal mdio-bus is registered and + the MDIO master is used for communication. Mixed external and internal + mdio-bus configurations are not supported by the hardware. + +properties: + compatible: + oneOf: + - enum: + - qca,qca8327 + - qca,qca8328 + - qca,qca8334 + - qca,qca8337 + description: | + qca,qca8328: referenced as AR8328(N)-AK1(A/B) QFN 176 pin package + qca,qca8327: referenced as AR8327(N)-AL1A DR-QFN 148 pin package + qca,qca8334: referenced as QCA8334-AL3C QFN 88 pin package + qca,qca8337: referenced as QCA8337N-AL3(B/C) DR-QFN 148 pin package + + reg: + maxItems: 1 + + reset-gpios: + description: + GPIO to be used to reset the whole device + maxItems: 1 + + qca,ignore-power-on-sel: + $ref: /schemas/types.yaml#/definitions/flag + description: + Ignore power-on pin strapping to configure LED open-drain or EEPROM + presence. This is needed for devices with incorrect configuration or when + the OEM has decided not to use pin strapping and falls back to SW regs. + + qca,led-open-drain: + $ref: /schemas/types.yaml#/definitions/flag + description: + Set LEDs to open-drain mode. This requires the qca,ignore-power-on-sel to + be set, otherwise the driver will fail at probe. This is required if the + OEM does not use pin strapping to set this mode and prefers to set it + using SW regs. The pin strappings related to LED open-drain mode are + B68 on the QCA832x and B49 on the QCA833x. + + mdio: + type: object + description: Qca8k switch have an internal mdio to access switch port. + If this is not present, the legacy mapping is used and the + internal mdio access is used. + With the legacy mapping the reg corresponding to the internal + mdio is the switch reg with an offset of -1. + + properties: + '#address-cells': + const: 1 + '#size-cells': + const: 0 + + patternProperties: + "^(ethernet-)?phy@[0-4]$": + type: object + + allOf: + - $ref: "http://devicetree.org/schemas/net/mdio.yaml#" + + properties: + reg: + maxItems: 1 + + required: + - reg + +patternProperties: + "^(ethernet-)?ports$": + type: object + properties: + '#address-cells': + const: 1 + '#size-cells': + const: 0 + + patternProperties: + "^(ethernet-)?port@[0-6]$": + type: object + description: Ethernet switch ports + + properties: + reg: + description: Port number + + label: + description: + Describes the label associated with this port, which will become + the netdev name + $ref: /schemas/types.yaml#/definitions/string + + link: + description: + Should be a list of phandles to other switch's DSA port. This + port is used as the outgoing port towards the phandle ports. The + full routing information must be given, not just the one hop + routes to neighbouring switches + $ref: /schemas/types.yaml#/definitions/phandle-array + + ethernet: + description: + Should be a phandle to a valid Ethernet device node. This host + device is what the switch port is connected to + $ref: /schemas/types.yaml#/definitions/phandle + + phy-handle: true + + phy-mode: true + + fixed-link: true + + mac-address: true + + sfp: true + + qca,sgmii-rxclk-falling-edge: + $ref: /schemas/types.yaml#/definitions/flag + description: + Set the receive clock phase to falling edge. Mostly commonly used on + the QCA8327 with CPU port 0 set to SGMII. + + qca,sgmii-txclk-falling-edge: + $ref: /schemas/types.yaml#/definitions/flag + description: + Set the transmit clock phase to falling edge. + + qca,sgmii-enable-pll: + $ref: /schemas/types.yaml#/definitions/flag + description: + For SGMII CPU port, explicitly enable PLL, TX and RX chain along with + Signal Detection. On the QCA8327 this should not be enabled, otherwise + the SGMII port will not initialize. When used on the QCA8337, revision 3 + or greater, a warning will be displayed. When the CPU port is set to + SGMII on the QCA8337, it is advised to set this unless a communication + issue is observed. + + required: + - reg + + additionalProperties: false + +oneOf: + - required: + - ports + - required: + - ethernet-ports + +required: + - compatible + - reg + +additionalProperties: true + +examples: + - | + #include + + mdio { + #address-cells = <1>; + #size-cells = <0>; + + external_phy_port1: ethernet-phy@0 { + reg = <0>; + }; + + external_phy_port2: ethernet-phy@1 { + reg = <1>; + }; + + external_phy_port3: ethernet-phy@2 { + reg = <2>; + }; + + external_phy_port4: ethernet-phy@3 { + reg = <3>; + }; + + external_phy_port5: ethernet-phy@4 { + reg = <4>; + }; + + switch@10 { + compatible = "qca,qca8337"; + #address-cells = <1>; + #size-cells = <0>; + reset-gpios = <&gpio 42 GPIO_ACTIVE_LOW>; + reg = <0x10>; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + label = "cpu"; + ethernet = <&gmac1>; + phy-mode = "rgmii"; + + fixed-link { + speed = <1000>; + full-duplex; + }; + }; + + port@1 { + reg = <1>; + label = "lan1"; + phy-handle = <&external_phy_port1>; + }; + + port@2 { + reg = <2>; + label = "lan2"; + phy-handle = <&external_phy_port2>; + }; + + port@3 { + reg = <3>; + label = "lan3"; + phy-handle = <&external_phy_port3>; + }; + + port@4 { + reg = <4>; + label = "lan4"; + phy-handle = <&external_phy_port4>; + }; + + port@5 { + reg = <5>; + label = "wan"; + phy-handle = <&external_phy_port5>; + }; + }; + }; + }; + - | + #include + + mdio { + #address-cells = <1>; + #size-cells = <0>; + + switch@10 { + compatible = "qca,qca8337"; + #address-cells = <1>; + #size-cells = <0>; + reset-gpios = <&gpio 42 GPIO_ACTIVE_LOW>; + reg = <0x10>; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + label = "cpu"; + ethernet = <&gmac1>; + phy-mode = "rgmii"; + + fixed-link { + speed = <1000>; + full-duplex; + }; + }; + + port@1 { + reg = <1>; + label = "lan1"; + phy-mode = "internal"; + phy-handle = <&internal_phy_port1>; + }; + + port@2 { + reg = <2>; + label = "lan2"; + phy-mode = "internal"; + phy-handle = <&internal_phy_port2>; + }; + + port@3 { + reg = <3>; + label = "lan3"; + phy-mode = "internal"; + phy-handle = <&internal_phy_port3>; + }; + + port@4 { + reg = <4>; + label = "lan4"; + phy-mode = "internal"; + phy-handle = <&internal_phy_port4>; + }; + + port@5 { + reg = <5>; + label = "wan"; + phy-mode = "internal"; + phy-handle = <&internal_phy_port5>; + }; + + port@6 { + reg = <0>; + label = "cpu"; + ethernet = <&gmac1>; + phy-mode = "sgmii"; + + qca,sgmii-rxclk-falling-edge; + + fixed-link { + speed = <1000>; + full-duplex; + }; + }; + }; + + mdio { + #address-cells = <1>; + #size-cells = <0>; + + internal_phy_port1: ethernet-phy@0 { + reg = <0>; + }; + + internal_phy_port2: ethernet-phy@1 { + reg = <1>; + }; + + internal_phy_port3: ethernet-phy@2 { + reg = <2>; + }; + + internal_phy_port4: ethernet-phy@3 { + reg = <3>; + }; + + internal_phy_port5: ethernet-phy@4 { + reg = <4>; + }; + }; + }; + }; diff --git a/Documentation/devicetree/bindings/net/dsa/realtek-smi.txt b/Documentation/devicetree/bindings/net/dsa/realtek-smi.txt index b6ae8541bd55..7959ec237983 100644 --- a/Documentation/devicetree/bindings/net/dsa/realtek-smi.txt +++ b/Documentation/devicetree/bindings/net/dsa/realtek-smi.txt @@ -9,6 +9,7 @@ SMI-based Realtek devices. Required properties: - compatible: must be exactly one of: + "realtek,rtl8365mb" (4+1 ports) "realtek,rtl8366" "realtek,rtl8366rb" (4+1 ports) "realtek,rtl8366s" (4+1 ports) @@ -62,6 +63,8 @@ and subnodes of DSA switches. Examples: +An example for the RTL8366RB: + switch { compatible = "realtek,rtl8366rb"; /* 22 = MDIO (has input reads), 21 = MDC (clock, output only) */ @@ -151,3 +154,87 @@ switch { }; }; }; + +An example for the RTL8365MB-VC: + +switch { + compatible = "realtek,rtl8365mb"; + mdc-gpios = <&gpio1 16 GPIO_ACTIVE_HIGH>; + mdio-gpios = <&gpio1 17 GPIO_ACTIVE_HIGH>; + reset-gpios = <&gpio5 0 GPIO_ACTIVE_LOW>; + + switch_intc: interrupt-controller { + interrupt-parent = <&gpio5>; + interrupts = <1 IRQ_TYPE_LEVEL_LOW>; + interrupt-controller; + #address-cells = <0>; + #interrupt-cells = <1>; + }; + + ports { + #address-cells = <1>; + #size-cells = <0>; + reg = <0>; + port@0 { + reg = <0>; + label = "swp0"; + phy-handle = <ðphy0>; + }; + port@1 { + reg = <1>; + label = "swp1"; + phy-handle = <ðphy1>; + }; + port@2 { + reg = <2>; + label = "swp2"; + phy-handle = <ðphy2>; + }; + port@3 { + reg = <3>; + label = "swp3"; + phy-handle = <ðphy3>; + }; + port@6 { + reg = <6>; + label = "cpu"; + ethernet = <&fec1>; + phy-mode = "rgmii"; + tx-internal-delay-ps = <2000>; + rx-internal-delay-ps = <2000>; + + fixed-link { + speed = <1000>; + full-duplex; + pause; + }; + }; + }; + + mdio { + compatible = "realtek,smi-mdio"; + #address-cells = <1>; + #size-cells = <0>; + + ethphy0: phy@0 { + reg = <0>; + interrupt-parent = <&switch_intc>; + interrupts = <0>; + }; + ethphy1: phy@1 { + reg = <1>; + interrupt-parent = <&switch_intc>; + interrupts = <1>; + }; + ethphy2: phy@2 { + reg = <2>; + interrupt-parent = <&switch_intc>; + interrupts = <2>; + }; + ethphy3: phy@3 { + reg = <3>; + interrupt-parent = <&switch_intc>; + interrupts = <3>; + }; + }; +}; diff --git a/Documentation/devicetree/bindings/net/qcom,ipq8064-mdio.yaml b/Documentation/devicetree/bindings/net/qcom,ipq8064-mdio.yaml index 948677ade6d1..d7748dd33199 100644 --- a/Documentation/devicetree/bindings/net/qcom,ipq8064-mdio.yaml +++ b/Documentation/devicetree/bindings/net/qcom,ipq8064-mdio.yaml @@ -51,6 +51,9 @@ examples: switch@10 { compatible = "qca,qca8337"; reg = <0x10>; - /* ... */ + + ports { + /* ... */ + }; }; }; diff --git a/Documentation/devicetree/bindings/net/socionext,uniphier-ave4.yaml b/Documentation/devicetree/bindings/net/socionext,uniphier-ave4.yaml index 8a03a24a2019..6bc61c42418f 100644 --- a/Documentation/devicetree/bindings/net/socionext,uniphier-ave4.yaml +++ b/Documentation/devicetree/bindings/net/socionext,uniphier-ave4.yaml @@ -24,6 +24,7 @@ properties: - socionext,uniphier-ld11-ave4 - socionext,uniphier-ld20-ave4 - socionext,uniphier-pxs3-ave4 + - socionext,uniphier-nx1-ave4 reg: maxItems: 1 diff --git a/Documentation/devicetree/bindings/vendor-prefixes.yaml b/Documentation/devicetree/bindings/vendor-prefixes.yaml index 952553759ac4..0aa9e7676fcf 100644 --- a/Documentation/devicetree/bindings/vendor-prefixes.yaml +++ b/Documentation/devicetree/bindings/vendor-prefixes.yaml @@ -131,6 +131,8 @@ patternProperties: description: Asahi Kasei Corp. "^asc,.*": description: All Sensors Corporation + "^asix,.*": + description: ASIX Electronics Corporation "^aspeed,.*": description: ASPEED Technology Inc. "^asus,.*": diff --git a/Documentation/networking/ipvs-sysctl.rst b/Documentation/networking/ipvs-sysctl.rst index 2afccc63856e..95ef56d62077 100644 --- a/Documentation/networking/ipvs-sysctl.rst +++ b/Documentation/networking/ipvs-sysctl.rst @@ -300,3 +300,14 @@ sync_version - INTEGER Kernels with this sync_version entry are able to receive messages of both version 1 and version 2 of the synchronisation protocol. + +run_estimation - BOOLEAN + 0 - disabled + not 0 - enabled (default) + + If disabled, the estimation will be stop, and you can't see + any update on speed estimation data. + + You can always re-enable estimation by setting this value to 1. + But be careful, the first estimation after re-enable is not + accurate. diff --git a/MAINTAINERS b/MAINTAINERS index 68bc7e55fc64..9f12cf0c4f8c 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2908,6 +2908,12 @@ S: Maintained F: Documentation/hwmon/asc7621.rst F: drivers/hwmon/asc7621.c +ASIX AX88796C SPI ETHERNET ADAPTER +M: Łukasz Stelmach +S: Maintained +F: Documentation/devicetree/bindings/net/asix,ax88796c.yaml +F: drivers/net/ethernet/asix/ax88796c_* + ASPEED PINCTRL DRIVERS M: Andrew Jeffery L: linux-aspeed@lists.ozlabs.org (moderated for non-subscribers) @@ -7034,7 +7040,6 @@ F: drivers/net/mdio/fwnode_mdio.c F: drivers/net/mdio/of_mdio.c F: drivers/net/pcs/ F: drivers/net/phy/ -F: drivers/of/of_net.c F: include/dt-bindings/net/qca-ar803x.h F: include/linux/*mdio*.h F: include/linux/mdio/*.h @@ -7046,6 +7051,7 @@ F: include/linux/platform_data/mdio-gpio.h F: include/trace/events/mdio.h F: include/uapi/linux/mdio.h F: include/uapi/linux/mii.h +F: net/core/of_net.c EXFAT FILE SYSTEM M: Namjae Jeon diff --git a/drivers/hsi/clients/ssi_protocol.c b/drivers/hsi/clients/ssi_protocol.c index 96d0eccca3aa..21f11a5b965b 100644 --- a/drivers/hsi/clients/ssi_protocol.c +++ b/drivers/hsi/clients/ssi_protocol.c @@ -1055,14 +1055,16 @@ static const struct net_device_ops ssip_pn_ops = { static void ssip_pn_setup(struct net_device *dev) { + static const u8 addr = PN_MEDIA_SOS; + dev->features = 0; dev->netdev_ops = &ssip_pn_ops; dev->type = ARPHRD_PHONET; dev->flags = IFF_POINTOPOINT | IFF_NOARP; dev->mtu = SSIP_DEFAULT_MTU; dev->hard_header_len = 1; - dev->dev_addr[0] = PN_MEDIA_SOS; dev->addr_len = 1; + dev_addr_set(dev, &addr); dev->tx_queue_len = SSIP_TXQUEUE_LEN; dev->needs_free_netdev = true; diff --git a/drivers/net/appletalk/cops.c b/drivers/net/appletalk/cops.c index f0695d68c47e..97f254bdbb16 100644 --- a/drivers/net/appletalk/cops.c +++ b/drivers/net/appletalk/cops.c @@ -945,8 +945,8 @@ static int cops_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) dev->broadcast[0] = 0xFF; /* Set hardware address. */ - dev->dev_addr[0] = aa->s_node; dev->addr_len = 1; + dev_addr_set(dev, &aa->s_node); return 0; case SIOCGIFADDR: diff --git a/drivers/net/appletalk/ltpc.c b/drivers/net/appletalk/ltpc.c index 1f8925e75b3f..388d7b3bd4c2 100644 --- a/drivers/net/appletalk/ltpc.c +++ b/drivers/net/appletalk/ltpc.c @@ -846,9 +846,8 @@ static int ltpc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) set_30 (dev,ltflags); dev->broadcast[0] = 0xFF; - dev->dev_addr[0] = aa->s_node; - dev->addr_len=1; + dev_addr_set(dev, &aa->s_node); return 0; diff --git a/drivers/net/arcnet/arc-rimi.c b/drivers/net/arcnet/arc-rimi.c index 12d085405bd0..8c3ccc7c83cd 100644 --- a/drivers/net/arcnet/arc-rimi.c +++ b/drivers/net/arcnet/arc-rimi.c @@ -207,7 +207,8 @@ static int __init arcrimi_found(struct net_device *dev) } /* get and check the station ID from offset 1 in shmem */ - dev->dev_addr[0] = arcnet_readb(lp->mem_start, COM9026_REG_R_STATION); + arcnet_set_addr(dev, arcnet_readb(lp->mem_start, + COM9026_REG_R_STATION)); arc_printk(D_NORMAL, dev, "ARCnet RIM I: station %02Xh found at IRQ %d, ShMem %lXh (%ld*%d bytes)\n", dev->dev_addr[0], @@ -324,7 +325,7 @@ static int __init arc_rimi_init(void) return -ENOMEM; if (node && node != 0xff) - dev->dev_addr[0] = node; + arcnet_set_addr(dev, node); dev->mem_start = io; dev->irq = irq; diff --git a/drivers/net/arcnet/arcdevice.h b/drivers/net/arcnet/arcdevice.h index 5d4a4c7efbbf..19e996a829c9 100644 --- a/drivers/net/arcnet/arcdevice.h +++ b/drivers/net/arcnet/arcdevice.h @@ -364,6 +364,11 @@ netdev_tx_t arcnet_send_packet(struct sk_buff *skb, struct net_device *dev); void arcnet_timeout(struct net_device *dev, unsigned int txqueue); +static inline void arcnet_set_addr(struct net_device *dev, u8 addr) +{ + dev_addr_set(dev, &addr); +} + /* I/O equivalents */ #ifdef CONFIG_SA1100_CT6001 diff --git a/drivers/net/arcnet/com20020-isa.c b/drivers/net/arcnet/com20020-isa.c index be618e4b9ed5..293a621e654c 100644 --- a/drivers/net/arcnet/com20020-isa.c +++ b/drivers/net/arcnet/com20020-isa.c @@ -151,7 +151,7 @@ static int __init com20020_init(void) return -ENOMEM; if (node && node != 0xff) - dev->dev_addr[0] = node; + arcnet_set_addr(dev, node); dev->netdev_ops = &com20020_netdev_ops; diff --git a/drivers/net/arcnet/com20020-pci.c b/drivers/net/arcnet/com20020-pci.c index 3c8f665c1558..6382e1937cca 100644 --- a/drivers/net/arcnet/com20020-pci.c +++ b/drivers/net/arcnet/com20020-pci.c @@ -194,7 +194,7 @@ static int com20020pci_probe(struct pci_dev *pdev, SET_NETDEV_DEV(dev, &pdev->dev); dev->base_addr = ioaddr; - dev->dev_addr[0] = node; + arcnet_set_addr(dev, node); dev->sysfs_groups[0] = &com20020_state_group; dev->irq = pdev->irq; lp->card_name = "PCI COM20020"; diff --git a/drivers/net/arcnet/com20020.c b/drivers/net/arcnet/com20020.c index 78043a9c5981..06e1651b594b 100644 --- a/drivers/net/arcnet/com20020.c +++ b/drivers/net/arcnet/com20020.c @@ -157,7 +157,7 @@ static int com20020_set_hwaddr(struct net_device *dev, void *addr) struct arcnet_local *lp = netdev_priv(dev); struct sockaddr *hwaddr = addr; - memcpy(dev->dev_addr, hwaddr->sa_data, 1); + dev_addr_set(dev, hwaddr->sa_data); com20020_set_subaddress(lp, ioaddr, SUB_NODE); arcnet_outb(dev->dev_addr[0], ioaddr, COM20020_REG_W_XREG); @@ -220,7 +220,7 @@ int com20020_found(struct net_device *dev, int shared) /* FIXME: do this some other way! */ if (!dev->dev_addr[0]) - dev->dev_addr[0] = arcnet_inb(ioaddr, 8); + arcnet_set_addr(dev, arcnet_inb(ioaddr, 8)); com20020_set_subaddress(lp, ioaddr, SUB_SETUP1); arcnet_outb(lp->setup, ioaddr, COM20020_REG_W_XREG); diff --git a/drivers/net/arcnet/com20020_cs.c b/drivers/net/arcnet/com20020_cs.c index b88a109b3b15..24150c933fcb 100644 --- a/drivers/net/arcnet/com20020_cs.c +++ b/drivers/net/arcnet/com20020_cs.c @@ -133,7 +133,7 @@ static int com20020_probe(struct pcmcia_device *p_dev) lp->hw.owner = THIS_MODULE; /* fill in our module parameters as defaults */ - dev->dev_addr[0] = node; + arcnet_set_addr(dev, node); p_dev->resource[0]->flags |= IO_DATA_PATH_WIDTH_8; p_dev->resource[0]->end = 16; diff --git a/drivers/net/arcnet/com90io.c b/drivers/net/arcnet/com90io.c index 3856b447d38e..37b47749fc8b 100644 --- a/drivers/net/arcnet/com90io.c +++ b/drivers/net/arcnet/com90io.c @@ -252,7 +252,7 @@ static int __init com90io_found(struct net_device *dev) /* get and check the station ID from offset 1 in shmem */ - dev->dev_addr[0] = get_buffer_byte(dev, 1); + arcnet_set_addr(dev, get_buffer_byte(dev, 1)); err = register_netdev(dev); if (err) { diff --git a/drivers/net/arcnet/com90xx.c b/drivers/net/arcnet/com90xx.c index d8dfb9ea0de8..f49dae194284 100644 --- a/drivers/net/arcnet/com90xx.c +++ b/drivers/net/arcnet/com90xx.c @@ -531,7 +531,8 @@ static int __init com90xx_found(int ioaddr, int airq, u_long shmem, } /* get and check the station ID from offset 1 in shmem */ - dev->dev_addr[0] = arcnet_readb(lp->mem_start, COM9026_REG_R_STATION); + arcnet_set_addr(dev, arcnet_readb(lp->mem_start, + COM9026_REG_R_STATION)); dev->base_addr = ioaddr; diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 77dc79a7f574..0c52612cb8e9 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -4414,7 +4414,7 @@ static int bond_set_mac_address(struct net_device *bond_dev, void *addr) } /* success */ - memcpy(bond_dev->dev_addr, ss->__data, bond_dev->addr_len); + dev_addr_set(bond_dev, ss->__data); return 0; unwind: diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c index b9e9842fed94..c48b77167fab 100644 --- a/drivers/net/bonding/bond_sysfs.c +++ b/drivers/net/bonding/bond_sysfs.c @@ -811,8 +811,8 @@ int bond_create_sysfs(struct bond_net *bn) */ if (ret == -EEXIST) { /* Is someone being kinky and naming a device bonding_master? */ - if (__dev_get_by_name(bn->net, - class_attr_bonding_masters.attr.name)) + if (netdev_name_in_use(bn->net, + class_attr_bonding_masters.attr.name)) pr_err("network device named %s already exists in sysfs\n", class_attr_bonding_masters.attr.name); ret = 0; diff --git a/drivers/net/dsa/Kconfig b/drivers/net/dsa/Kconfig index a5f1aa911fe2..7b1457a6e327 100644 --- a/drivers/net/dsa/Kconfig +++ b/drivers/net/dsa/Kconfig @@ -70,6 +70,7 @@ config NET_DSA_QCA8K config NET_DSA_REALTEK_SMI tristate "Realtek SMI Ethernet switch family support" select NET_DSA_TAG_RTL4_A + select NET_DSA_TAG_RTL8_4 select FIXED_PHY select IRQ_DOMAIN select REALTEK_PHY diff --git a/drivers/net/dsa/Makefile b/drivers/net/dsa/Makefile index f3598c040994..8da1569a34e6 100644 --- a/drivers/net/dsa/Makefile +++ b/drivers/net/dsa/Makefile @@ -10,7 +10,7 @@ obj-$(CONFIG_NET_DSA_MT7530) += mt7530.o obj-$(CONFIG_NET_DSA_MV88E6060) += mv88e6060.o obj-$(CONFIG_NET_DSA_QCA8K) += qca8k.o obj-$(CONFIG_NET_DSA_REALTEK_SMI) += realtek-smi.o -realtek-smi-objs := realtek-smi-core.o rtl8366.o rtl8366rb.o +realtek-smi-objs := realtek-smi-core.o rtl8366.o rtl8366rb.o rtl8365mb.o obj-$(CONFIG_NET_DSA_SMSC_LAN9303) += lan9303-core.o obj-$(CONFIG_NET_DSA_SMSC_LAN9303_I2C) += lan9303_i2c.o obj-$(CONFIG_NET_DSA_SMSC_LAN9303_MDIO) += lan9303_mdio.o diff --git a/drivers/net/dsa/qca8k.c b/drivers/net/dsa/qca8k.c index a984f06f6f04..ea7f12778922 100644 --- a/drivers/net/dsa/qca8k.c +++ b/drivers/net/dsa/qca8k.c @@ -889,62 +889,183 @@ qca8k_setup_mdio_bus(struct qca8k_priv *priv) } static int -qca8k_setup_of_rgmii_delay(struct qca8k_priv *priv) +qca8k_setup_mac_pwr_sel(struct qca8k_priv *priv) { + u32 mask = 0; + int ret = 0; + + /* SoC specific settings for ipq8064. + * If more device require this consider adding + * a dedicated binding. + */ + if (of_machine_is_compatible("qcom,ipq8064")) + mask |= QCA8K_MAC_PWR_RGMII0_1_8V; + + /* SoC specific settings for ipq8065 */ + if (of_machine_is_compatible("qcom,ipq8065")) + mask |= QCA8K_MAC_PWR_RGMII1_1_8V; + + if (mask) { + ret = qca8k_rmw(priv, QCA8K_REG_MAC_PWR_SEL, + QCA8K_MAC_PWR_RGMII0_1_8V | + QCA8K_MAC_PWR_RGMII1_1_8V, + mask); + } + + return ret; +} + +static int qca8k_find_cpu_port(struct dsa_switch *ds) +{ + struct qca8k_priv *priv = ds->priv; + + /* Find the connected cpu port. Valid port are 0 or 6 */ + if (dsa_is_cpu_port(ds, 0)) + return 0; + + dev_dbg(priv->dev, "port 0 is not the CPU port. Checking port 6"); + + if (dsa_is_cpu_port(ds, 6)) + return 6; + + return -EINVAL; +} + +static int +qca8k_setup_of_pws_reg(struct qca8k_priv *priv) +{ + struct device_node *node = priv->dev->of_node; + const struct qca8k_match_data *data; + u32 val = 0; + int ret; + + /* QCA8327 require to set to the correct mode. + * His bigger brother QCA8328 have the 172 pin layout. + * Should be applied by default but we set this just to make sure. + */ + if (priv->switch_id == QCA8K_ID_QCA8327) { + data = of_device_get_match_data(priv->dev); + + /* Set the correct package of 148 pin for QCA8327 */ + if (data->reduced_package) + val |= QCA8327_PWS_PACKAGE148_EN; + + ret = qca8k_rmw(priv, QCA8K_REG_PWS, QCA8327_PWS_PACKAGE148_EN, + val); + if (ret) + return ret; + } + + if (of_property_read_bool(node, "qca,ignore-power-on-sel")) + val |= QCA8K_PWS_POWER_ON_SEL; + + if (of_property_read_bool(node, "qca,led-open-drain")) { + if (!(val & QCA8K_PWS_POWER_ON_SEL)) { + dev_err(priv->dev, "qca,led-open-drain require qca,ignore-power-on-sel to be set."); + return -EINVAL; + } + + val |= QCA8K_PWS_LED_OPEN_EN_CSR; + } + + return qca8k_rmw(priv, QCA8K_REG_PWS, + QCA8K_PWS_LED_OPEN_EN_CSR | QCA8K_PWS_POWER_ON_SEL, + val); +} + +static int +qca8k_parse_port_config(struct qca8k_priv *priv) +{ + int port, cpu_port_index = -1, ret; struct device_node *port_dn; phy_interface_t mode; struct dsa_port *dp; - u32 val; + u32 delay; - /* CPU port is already checked */ - dp = dsa_to_port(priv->ds, 0); + /* We have 2 CPU port. Check them */ + for (port = 0; port < QCA8K_NUM_PORTS && cpu_port_index < QCA8K_NUM_CPU_PORTS; port++) { + /* Skip every other port */ + if (port != 0 && port != 6) + continue; - port_dn = dp->dn; + dp = dsa_to_port(priv->ds, port); + port_dn = dp->dn; + cpu_port_index++; - /* Check if port 0 is set to the correct type */ - of_get_phy_mode(port_dn, &mode); - if (mode != PHY_INTERFACE_MODE_RGMII_ID && - mode != PHY_INTERFACE_MODE_RGMII_RXID && - mode != PHY_INTERFACE_MODE_RGMII_TXID) { - return 0; - } + if (!of_device_is_available(port_dn)) + continue; - switch (mode) { - case PHY_INTERFACE_MODE_RGMII_ID: - case PHY_INTERFACE_MODE_RGMII_RXID: - if (of_property_read_u32(port_dn, "rx-internal-delay-ps", &val)) - val = 2; - else - /* Switch regs accept value in ns, convert ps to ns */ - val = val / 1000; + ret = of_get_phy_mode(port_dn, &mode); + if (ret) + continue; - if (val > QCA8K_MAX_DELAY) { - dev_err(priv->dev, "rgmii rx delay is limited to a max value of 3ns, setting to the max value"); - val = 3; - } + switch (mode) { + case PHY_INTERFACE_MODE_RGMII: + case PHY_INTERFACE_MODE_RGMII_ID: + case PHY_INTERFACE_MODE_RGMII_TXID: + case PHY_INTERFACE_MODE_RGMII_RXID: + case PHY_INTERFACE_MODE_SGMII: + delay = 0; + + if (!of_property_read_u32(port_dn, "tx-internal-delay-ps", &delay)) + /* Switch regs accept value in ns, convert ps to ns */ + delay = delay / 1000; + else if (mode == PHY_INTERFACE_MODE_RGMII_ID || + mode == PHY_INTERFACE_MODE_RGMII_TXID) + delay = 1; + + if (delay > QCA8K_MAX_DELAY) { + dev_err(priv->dev, "rgmii tx delay is limited to a max value of 3ns, setting to the max value"); + delay = 3; + } + + priv->ports_config.rgmii_tx_delay[cpu_port_index] = delay; + + delay = 0; + + if (!of_property_read_u32(port_dn, "rx-internal-delay-ps", &delay)) + /* Switch regs accept value in ns, convert ps to ns */ + delay = delay / 1000; + else if (mode == PHY_INTERFACE_MODE_RGMII_ID || + mode == PHY_INTERFACE_MODE_RGMII_RXID) + delay = 2; + + if (delay > QCA8K_MAX_DELAY) { + dev_err(priv->dev, "rgmii rx delay is limited to a max value of 3ns, setting to the max value"); + delay = 3; + } + + priv->ports_config.rgmii_rx_delay[cpu_port_index] = delay; + + /* Skip sgmii parsing for rgmii* mode */ + if (mode == PHY_INTERFACE_MODE_RGMII || + mode == PHY_INTERFACE_MODE_RGMII_ID || + mode == PHY_INTERFACE_MODE_RGMII_TXID || + mode == PHY_INTERFACE_MODE_RGMII_RXID) + break; + + if (of_property_read_bool(port_dn, "qca,sgmii-txclk-falling-edge")) + priv->ports_config.sgmii_tx_clk_falling_edge = true; + + if (of_property_read_bool(port_dn, "qca,sgmii-rxclk-falling-edge")) + priv->ports_config.sgmii_rx_clk_falling_edge = true; + + if (of_property_read_bool(port_dn, "qca,sgmii-enable-pll")) { + priv->ports_config.sgmii_enable_pll = true; + + if (priv->switch_id == QCA8K_ID_QCA8327) { + dev_err(priv->dev, "SGMII PLL should NOT be enabled for qca8327. Aborting enabling"); + priv->ports_config.sgmii_enable_pll = false; + } + + if (priv->switch_revision < 2) + dev_warn(priv->dev, "SGMII PLL should NOT be enabled for qca8337 with revision 2 or more."); + } - priv->rgmii_rx_delay = val; - /* Stop here if we need to check only for rx delay */ - if (mode != PHY_INTERFACE_MODE_RGMII_ID) break; - - fallthrough; - case PHY_INTERFACE_MODE_RGMII_TXID: - if (of_property_read_u32(port_dn, "tx-internal-delay-ps", &val)) - val = 1; - else - /* Switch regs accept value in ns, convert ps to ns */ - val = val / 1000; - - if (val > QCA8K_MAX_DELAY) { - dev_err(priv->dev, "rgmii tx delay is limited to a max value of 3ns, setting to the max value"); - val = 3; + default: + continue; } - - priv->rgmii_tx_delay = val; - break; - default: - return 0; } return 0; @@ -954,15 +1075,20 @@ static int qca8k_setup(struct dsa_switch *ds) { struct qca8k_priv *priv = (struct qca8k_priv *)ds->priv; - int ret, i; + int cpu_port, ret, i; u32 mask; - /* Make sure that port 0 is the cpu port */ - if (!dsa_is_cpu_port(ds, 0)) { - dev_err(priv->dev, "port 0 is not the CPU port"); - return -EINVAL; + cpu_port = qca8k_find_cpu_port(ds); + if (cpu_port < 0) { + dev_err(priv->dev, "No cpu port configured in both cpu port0 and port6"); + return cpu_port; } + /* Parse CPU port config to be later used in phy_link mac_config */ + ret = qca8k_parse_port_config(priv); + if (ret) + return ret; + mutex_init(&priv->reg_mutex); /* Start by setting up the register mapping */ @@ -975,7 +1101,11 @@ qca8k_setup(struct dsa_switch *ds) if (ret) return ret; - ret = qca8k_setup_of_rgmii_delay(priv); + ret = qca8k_setup_of_pws_reg(priv); + if (ret) + return ret; + + ret = qca8k_setup_mac_pwr_sel(priv); if (ret) return ret; @@ -992,41 +1122,49 @@ qca8k_setup(struct dsa_switch *ds) if (ret) dev_warn(priv->dev, "mib init failed"); - /* Enable QCA header mode on the cpu port */ - ret = qca8k_write(priv, QCA8K_REG_PORT_HDR_CTRL(QCA8K_CPU_PORT), - QCA8K_PORT_HDR_CTRL_ALL << QCA8K_PORT_HDR_CTRL_TX_S | - QCA8K_PORT_HDR_CTRL_ALL << QCA8K_PORT_HDR_CTRL_RX_S); - if (ret) { - dev_err(priv->dev, "failed enabling QCA header mode"); - return ret; - } - - /* Disable forwarding by default on all ports */ + /* Initial setup of all ports */ for (i = 0; i < QCA8K_NUM_PORTS; i++) { + /* Disable forwarding by default on all ports */ ret = qca8k_rmw(priv, QCA8K_PORT_LOOKUP_CTRL(i), QCA8K_PORT_LOOKUP_MEMBER, 0); if (ret) return ret; + + /* Enable QCA header mode on all cpu ports */ + if (dsa_is_cpu_port(ds, i)) { + ret = qca8k_write(priv, QCA8K_REG_PORT_HDR_CTRL(i), + QCA8K_PORT_HDR_CTRL_ALL << QCA8K_PORT_HDR_CTRL_TX_S | + QCA8K_PORT_HDR_CTRL_ALL << QCA8K_PORT_HDR_CTRL_RX_S); + if (ret) { + dev_err(priv->dev, "failed enabling QCA header mode"); + return ret; + } + } + + /* Disable MAC by default on all user ports */ + if (dsa_is_user_port(ds, i)) + qca8k_port_set_status(priv, i, 0); } - /* Disable MAC by default on all ports */ - for (i = 1; i < QCA8K_NUM_PORTS; i++) - qca8k_port_set_status(priv, i, 0); - - /* Forward all unknown frames to CPU port for Linux processing */ + /* Forward all unknown frames to CPU port for Linux processing + * Notice that in multi-cpu config only one port should be set + * for igmp, unknown, multicast and broadcast packet + */ ret = qca8k_write(priv, QCA8K_REG_GLOBAL_FW_CTRL1, - BIT(0) << QCA8K_GLOBAL_FW_CTRL1_IGMP_DP_S | - BIT(0) << QCA8K_GLOBAL_FW_CTRL1_BC_DP_S | - BIT(0) << QCA8K_GLOBAL_FW_CTRL1_MC_DP_S | - BIT(0) << QCA8K_GLOBAL_FW_CTRL1_UC_DP_S); + BIT(cpu_port) << QCA8K_GLOBAL_FW_CTRL1_IGMP_DP_S | + BIT(cpu_port) << QCA8K_GLOBAL_FW_CTRL1_BC_DP_S | + BIT(cpu_port) << QCA8K_GLOBAL_FW_CTRL1_MC_DP_S | + BIT(cpu_port) << QCA8K_GLOBAL_FW_CTRL1_UC_DP_S); if (ret) return ret; - /* Setup connection between CPU port & user ports */ + /* Setup connection between CPU port & user ports + * Configure specific switch configuration for ports + */ for (i = 0; i < QCA8K_NUM_PORTS; i++) { /* CPU port gets connected to all user ports of the switch */ if (dsa_is_cpu_port(ds, i)) { - ret = qca8k_rmw(priv, QCA8K_PORT_LOOKUP_CTRL(QCA8K_CPU_PORT), + ret = qca8k_rmw(priv, QCA8K_PORT_LOOKUP_CTRL(i), QCA8K_PORT_LOOKUP_MEMBER, dsa_user_ports(ds)); if (ret) return ret; @@ -1038,7 +1176,7 @@ qca8k_setup(struct dsa_switch *ds) ret = qca8k_rmw(priv, QCA8K_PORT_LOOKUP_CTRL(i), QCA8K_PORT_LOOKUP_MEMBER, - BIT(QCA8K_CPU_PORT)); + BIT(cpu_port)); if (ret) return ret; @@ -1063,16 +1201,14 @@ qca8k_setup(struct dsa_switch *ds) if (ret) return ret; } - } - /* The port 5 of the qca8337 have some problem in flood condition. The - * original legacy driver had some specific buffer and priority settings - * for the different port suggested by the QCA switch team. Add this - * missing settings to improve switch stability under load condition. - * This problem is limited to qca8337 and other qca8k switch are not affected. - */ - if (priv->switch_id == QCA8K_ID_QCA8337) { - for (i = 0; i < QCA8K_NUM_PORTS; i++) { + /* The port 5 of the qca8337 have some problem in flood condition. The + * original legacy driver had some specific buffer and priority settings + * for the different port suggested by the QCA switch team. Add this + * missing settings to improve switch stability under load condition. + * This problem is limited to qca8337 and other qca8k switch are not affected. + */ + if (priv->switch_id == QCA8K_ID_QCA8337) { switch (i) { /* The 2 CPU port and port 5 requires some different * priority than any other ports. @@ -1108,6 +1244,12 @@ qca8k_setup(struct dsa_switch *ds) QCA8K_PORT_HOL_CTRL1_WRED_EN, mask); } + + /* Set initial MTU for every port. + * We have only have a general MTU setting. So track + * every port and set the max across all port. + */ + priv->port_mtu[i] = ETH_FRAME_LEN + ETH_FCS_LEN; } /* Special GLOBAL_FC_THRESH value are needed for ar8327 switch */ @@ -1121,8 +1263,6 @@ qca8k_setup(struct dsa_switch *ds) } /* Setup our port MTUs to match power on defaults */ - for (i = 0; i < QCA8K_NUM_PORTS; i++) - priv->port_mtu[i] = ETH_FRAME_LEN + ETH_FCS_LEN; ret = qca8k_write(priv, QCA8K_MAX_FRAME_SIZE, ETH_FRAME_LEN + ETH_FCS_LEN); if (ret) dev_warn(priv->dev, "failed setting MTU settings"); @@ -1136,13 +1276,54 @@ qca8k_setup(struct dsa_switch *ds) return 0; } +static void +qca8k_mac_config_setup_internal_delay(struct qca8k_priv *priv, int cpu_port_index, + u32 reg) +{ + u32 delay, val = 0; + int ret; + + /* Delay can be declared in 3 different way. + * Mode to rgmii and internal-delay standard binding defined + * rgmii-id or rgmii-tx/rx phy mode set. + * The parse logic set a delay different than 0 only when one + * of the 3 different way is used. In all other case delay is + * not enabled. With ID or TX/RXID delay is enabled and set + * to the default and recommended value. + */ + if (priv->ports_config.rgmii_tx_delay[cpu_port_index]) { + delay = priv->ports_config.rgmii_tx_delay[cpu_port_index]; + + val |= QCA8K_PORT_PAD_RGMII_TX_DELAY(delay) | + QCA8K_PORT_PAD_RGMII_TX_DELAY_EN; + } + + if (priv->ports_config.rgmii_rx_delay[cpu_port_index]) { + delay = priv->ports_config.rgmii_rx_delay[cpu_port_index]; + + val |= QCA8K_PORT_PAD_RGMII_RX_DELAY(delay) | + QCA8K_PORT_PAD_RGMII_RX_DELAY_EN; + } + + /* Set RGMII delay based on the selected values */ + ret = qca8k_rmw(priv, reg, + QCA8K_PORT_PAD_RGMII_TX_DELAY_MASK | + QCA8K_PORT_PAD_RGMII_RX_DELAY_MASK | + QCA8K_PORT_PAD_RGMII_TX_DELAY_EN | + QCA8K_PORT_PAD_RGMII_RX_DELAY_EN, + val); + if (ret) + dev_err(priv->dev, "Failed to set internal delay for CPU port%d", + cpu_port_index == QCA8K_CPU_PORT0 ? 0 : 6); +} + static void qca8k_phylink_mac_config(struct dsa_switch *ds, int port, unsigned int mode, const struct phylink_link_state *state) { struct qca8k_priv *priv = ds->priv; + int cpu_port_index, ret; u32 reg, val; - int ret; switch (port) { case 0: /* 1st CPU port */ @@ -1154,6 +1335,7 @@ qca8k_phylink_mac_config(struct dsa_switch *ds, int port, unsigned int mode, return; reg = QCA8K_REG_PORT0_PAD_CTRL; + cpu_port_index = QCA8K_CPU_PORT0; break; case 1: case 2: @@ -1172,6 +1354,7 @@ qca8k_phylink_mac_config(struct dsa_switch *ds, int port, unsigned int mode, return; reg = QCA8K_REG_PORT6_PAD_CTRL; + cpu_port_index = QCA8K_CPU_PORT6; break; default: dev_err(ds->dev, "%s: unsupported port: %i\n", __func__, port); @@ -1186,23 +1369,18 @@ qca8k_phylink_mac_config(struct dsa_switch *ds, int port, unsigned int mode, switch (state->interface) { case PHY_INTERFACE_MODE_RGMII: - /* RGMII mode means no delay so don't enable the delay */ - qca8k_write(priv, reg, QCA8K_PORT_PAD_RGMII_EN); - break; case PHY_INTERFACE_MODE_RGMII_ID: case PHY_INTERFACE_MODE_RGMII_TXID: case PHY_INTERFACE_MODE_RGMII_RXID: - /* RGMII_ID needs internal delay. This is enabled through - * PORT5_PAD_CTRL for all ports, rather than individual port - * registers + qca8k_write(priv, reg, QCA8K_PORT_PAD_RGMII_EN); + + /* Configure rgmii delay */ + qca8k_mac_config_setup_internal_delay(priv, cpu_port_index, reg); + + /* QCA8337 requires to set rgmii rx delay for all ports. + * This is enabled through PORT5_PAD_CTRL for all ports, + * rather than individual port registers. */ - qca8k_write(priv, reg, - QCA8K_PORT_PAD_RGMII_EN | - QCA8K_PORT_PAD_RGMII_TX_DELAY(priv->rgmii_tx_delay) | - QCA8K_PORT_PAD_RGMII_RX_DELAY(priv->rgmii_rx_delay) | - QCA8K_PORT_PAD_RGMII_TX_DELAY_EN | - QCA8K_PORT_PAD_RGMII_RX_DELAY_EN); - /* QCA8337 requires to set rgmii rx delay */ if (priv->switch_id == QCA8K_ID_QCA8337) qca8k_write(priv, QCA8K_REG_PORT5_PAD_CTRL, QCA8K_PORT_PAD_RGMII_RX_DELAY_EN); @@ -1227,8 +1405,11 @@ qca8k_phylink_mac_config(struct dsa_switch *ds, int port, unsigned int mode, if (ret) return; - val |= QCA8K_SGMII_EN_PLL | QCA8K_SGMII_EN_RX | - QCA8K_SGMII_EN_TX | QCA8K_SGMII_EN_SD; + val |= QCA8K_SGMII_EN_SD; + + if (priv->ports_config.sgmii_enable_pll) + val |= QCA8K_SGMII_EN_PLL | QCA8K_SGMII_EN_RX | + QCA8K_SGMII_EN_TX; if (dsa_is_cpu_port(ds, port)) { /* CPU port, we're talking to the CPU MAC, be a PHY */ @@ -1243,6 +1424,35 @@ qca8k_phylink_mac_config(struct dsa_switch *ds, int port, unsigned int mode, } qca8k_write(priv, QCA8K_REG_SGMII_CTRL, val); + + /* For qca8327/qca8328/qca8334/qca8338 sgmii is unique and + * falling edge is set writing in the PORT0 PAD reg + */ + if (priv->switch_id == QCA8K_ID_QCA8327 || + priv->switch_id == QCA8K_ID_QCA8337) + reg = QCA8K_REG_PORT0_PAD_CTRL; + + val = 0; + + /* SGMII Clock phase configuration */ + if (priv->ports_config.sgmii_rx_clk_falling_edge) + val |= QCA8K_PORT0_PAD_SGMII_RXCLK_FALLING_EDGE; + + if (priv->ports_config.sgmii_tx_clk_falling_edge) + val |= QCA8K_PORT0_PAD_SGMII_TXCLK_FALLING_EDGE; + + if (val) + ret = qca8k_rmw(priv, reg, + QCA8K_PORT0_PAD_SGMII_RXCLK_FALLING_EDGE | + QCA8K_PORT0_PAD_SGMII_TXCLK_FALLING_EDGE, + val); + + /* From original code is reported port instability as SGMII also + * require delay set. Apply advised values here or take them from DT. + */ + if (state->interface == PHY_INTERFACE_MODE_SGMII) + qca8k_mac_config_setup_internal_delay(priv, cpu_port_index, reg); + break; default: dev_err(ds->dev, "xMII mode %s not supported for port %d\n", @@ -1522,10 +1732,15 @@ static int qca8k_port_bridge_join(struct dsa_switch *ds, int port, struct net_device *br) { struct qca8k_priv *priv = (struct qca8k_priv *)ds->priv; - int port_mask = BIT(QCA8K_CPU_PORT); + int port_mask, cpu_port; int i, ret; - for (i = 1; i < QCA8K_NUM_PORTS; i++) { + cpu_port = dsa_to_port(ds, port)->cpu_dp->index; + port_mask = BIT(cpu_port); + + for (i = 0; i < QCA8K_NUM_PORTS; i++) { + if (dsa_is_cpu_port(ds, i)) + continue; if (dsa_to_port(ds, i)->bridge_dev != br) continue; /* Add this port to the portvlan mask of the other ports @@ -1551,9 +1766,13 @@ static void qca8k_port_bridge_leave(struct dsa_switch *ds, int port, struct net_device *br) { struct qca8k_priv *priv = (struct qca8k_priv *)ds->priv; - int i; + int cpu_port, i; - for (i = 1; i < QCA8K_NUM_PORTS; i++) { + cpu_port = dsa_to_port(ds, port)->cpu_dp->index; + + for (i = 0; i < QCA8K_NUM_PORTS; i++) { + if (dsa_is_cpu_port(ds, i)) + continue; if (dsa_to_port(ds, i)->bridge_dev != br) continue; /* Remove this port to the portvlan mask of the other ports @@ -1568,7 +1787,7 @@ qca8k_port_bridge_leave(struct dsa_switch *ds, int port, struct net_device *br) * this port */ qca8k_rmw(priv, QCA8K_PORT_LOOKUP_CTRL(port), - QCA8K_PORT_LOOKUP_MEMBER, BIT(QCA8K_CPU_PORT)); + QCA8K_PORT_LOOKUP_MEMBER, BIT(cpu_port)); } static int @@ -1939,7 +2158,12 @@ static int qca8k_resume(struct device *dev) static SIMPLE_DEV_PM_OPS(qca8k_pm_ops, qca8k_suspend, qca8k_resume); -static const struct qca8k_match_data qca832x = { +static const struct qca8k_match_data qca8327 = { + .id = QCA8K_ID_QCA8327, + .reduced_package = true, +}; + +static const struct qca8k_match_data qca8328 = { .id = QCA8K_ID_QCA8327, }; @@ -1948,7 +2172,8 @@ static const struct qca8k_match_data qca833x = { }; static const struct of_device_id qca8k_of_match[] = { - { .compatible = "qca,qca8327", .data = &qca832x }, + { .compatible = "qca,qca8327", .data = &qca8327 }, + { .compatible = "qca,qca8328", .data = &qca8328 }, { .compatible = "qca,qca8334", .data = &qca833x }, { .compatible = "qca,qca8337", .data = &qca833x }, { /* sentinel */ }, diff --git a/drivers/net/dsa/qca8k.h b/drivers/net/dsa/qca8k.h index ed3b05ad6745..e10571a398c9 100644 --- a/drivers/net/dsa/qca8k.h +++ b/drivers/net/dsa/qca8k.h @@ -13,6 +13,7 @@ #include #define QCA8K_NUM_PORTS 7 +#define QCA8K_NUM_CPU_PORTS 2 #define QCA8K_MAX_MTU 9000 #define PHY_ID_QCA8327 0x004dd034 @@ -24,8 +25,6 @@ #define QCA8K_NUM_FDB_RECORDS 2048 -#define QCA8K_CPU_PORT 0 - #define QCA8K_PORT_VID_DEF 1 /* Global control registers */ @@ -35,16 +34,26 @@ #define QCA8K_MASK_CTRL_DEVICE_ID_MASK GENMASK(15, 8) #define QCA8K_MASK_CTRL_DEVICE_ID(x) ((x) >> 8) #define QCA8K_REG_PORT0_PAD_CTRL 0x004 +#define QCA8K_PORT0_PAD_SGMII_RXCLK_FALLING_EDGE BIT(19) +#define QCA8K_PORT0_PAD_SGMII_TXCLK_FALLING_EDGE BIT(18) #define QCA8K_REG_PORT5_PAD_CTRL 0x008 #define QCA8K_REG_PORT6_PAD_CTRL 0x00c #define QCA8K_PORT_PAD_RGMII_EN BIT(26) +#define QCA8K_PORT_PAD_RGMII_TX_DELAY_MASK GENMASK(23, 22) #define QCA8K_PORT_PAD_RGMII_TX_DELAY(x) ((x) << 22) +#define QCA8K_PORT_PAD_RGMII_RX_DELAY_MASK GENMASK(21, 20) #define QCA8K_PORT_PAD_RGMII_RX_DELAY(x) ((x) << 20) #define QCA8K_PORT_PAD_RGMII_TX_DELAY_EN BIT(25) #define QCA8K_PORT_PAD_RGMII_RX_DELAY_EN BIT(24) #define QCA8K_MAX_DELAY 3 #define QCA8K_PORT_PAD_SGMII_EN BIT(7) #define QCA8K_REG_PWS 0x010 +#define QCA8K_PWS_POWER_ON_SEL BIT(31) +/* This reg is only valid for QCA832x and toggle the package + * type from 176 pin (by default) to 148 pin used on QCA8327 + */ +#define QCA8327_PWS_PACKAGE148_EN BIT(30) +#define QCA8K_PWS_LED_OPEN_EN_CSR BIT(24) #define QCA8K_PWS_SERDES_AEN_DIS BIT(7) #define QCA8K_REG_MODULE_EN 0x030 #define QCA8K_MODULE_EN_MIB BIT(0) @@ -100,6 +109,11 @@ #define QCA8K_SGMII_MODE_CTRL_PHY (1 << 22) #define QCA8K_SGMII_MODE_CTRL_MAC (2 << 22) +/* MAC_PWR_SEL registers */ +#define QCA8K_REG_MAC_PWR_SEL 0x0e4 +#define QCA8K_MAC_PWR_RGMII1_1_8V BIT(18) +#define QCA8K_MAC_PWR_RGMII0_1_8V BIT(19) + /* EEE control registers */ #define QCA8K_REG_EEE_CTRL 0x100 #define QCA8K_REG_EEE_CTRL_LPI_EN(_i) ((_i + 1) * 2) @@ -248,14 +262,27 @@ struct ar8xxx_port_status { struct qca8k_match_data { u8 id; + bool reduced_package; +}; + +enum { + QCA8K_CPU_PORT0, + QCA8K_CPU_PORT6, +}; + +struct qca8k_ports_config { + bool sgmii_rx_clk_falling_edge; + bool sgmii_tx_clk_falling_edge; + bool sgmii_enable_pll; + u8 rgmii_rx_delay[QCA8K_NUM_CPU_PORTS]; /* 0: CPU port0, 1: CPU port6 */ + u8 rgmii_tx_delay[QCA8K_NUM_CPU_PORTS]; /* 0: CPU port0, 1: CPU port6 */ }; struct qca8k_priv { u8 switch_id; u8 switch_revision; - u8 rgmii_tx_delay; - u8 rgmii_rx_delay; bool legacy_phy_port_mapping; + struct qca8k_ports_config ports_config; struct regmap *regmap; struct mii_bus *bus; struct ar8xxx_port_status port_sts[QCA8K_NUM_PORTS]; diff --git a/drivers/net/dsa/realtek-smi-core.c b/drivers/net/dsa/realtek-smi-core.c index 2fcfd917b876..c66ebd0ee217 100644 --- a/drivers/net/dsa/realtek-smi-core.c +++ b/drivers/net/dsa/realtek-smi-core.c @@ -501,6 +501,10 @@ static const struct of_device_id realtek_smi_of_match[] = { .compatible = "realtek,rtl8366s", .data = NULL, }, + { + .compatible = "realtek,rtl8365mb", + .data = &rtl8365mb_variant, + }, { /* sentinel */ }, }; MODULE_DEVICE_TABLE(of, realtek_smi_of_match); diff --git a/drivers/net/dsa/realtek-smi-core.h b/drivers/net/dsa/realtek-smi-core.h index 214f710d7dd5..5bfa53e2480a 100644 --- a/drivers/net/dsa/realtek-smi-core.h +++ b/drivers/net/dsa/realtek-smi-core.h @@ -140,5 +140,6 @@ int rtl8366_get_sset_count(struct dsa_switch *ds, int port, int sset); void rtl8366_get_ethtool_stats(struct dsa_switch *ds, int port, uint64_t *data); extern const struct realtek_smi_variant rtl8366rb_variant; +extern const struct realtek_smi_variant rtl8365mb_variant; #endif /* _REALTEK_SMI_H */ diff --git a/drivers/net/dsa/rtl8365mb.c b/drivers/net/dsa/rtl8365mb.c new file mode 100644 index 000000000000..baaae97283c5 --- /dev/null +++ b/drivers/net/dsa/rtl8365mb.c @@ -0,0 +1,1982 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Realtek SMI subdriver for the Realtek RTL8365MB-VC ethernet switch. + * + * Copyright (C) 2021 Alvin Šipraga + * Copyright (C) 2021 Michael Rasmussen + * + * The RTL8365MB-VC is a 4+1 port 10/100/1000M switch controller. It includes 4 + * integrated PHYs for the user facing ports, and an extension interface which + * can be connected to the CPU - or another PHY - via either MII, RMII, or + * RGMII. The switch is configured via the Realtek Simple Management Interface + * (SMI), which uses the MDIO/MDC lines. + * + * Below is a simplified block diagram of the chip and its relevant interfaces. + * + * .-----------------------------------. + * | | + * UTP <---------------> Giga PHY <-> PCS <-> P0 GMAC | + * UTP <---------------> Giga PHY <-> PCS <-> P1 GMAC | + * UTP <---------------> Giga PHY <-> PCS <-> P2 GMAC | + * UTP <---------------> Giga PHY <-> PCS <-> P3 GMAC | + * | | + * CPU/PHY <-MII/RMII/RGMII---> Extension <---> Extension | + * | interface 1 GMAC 1 | + * | | + * SMI driver/ <-MDC/SCL---> Management ~~~~~~~~~~~~~~ | + * EEPROM <-MDIO/SDA--> interface ~REALTEK ~~~~~ | + * | ~RTL8365MB ~~~ | + * | ~GXXXC TAIWAN~ | + * GPIO <--------------> Reset ~~~~~~~~~~~~~~ | + * | | + * Interrupt <----------> Link UP/DOWN events | + * controller | | + * '-----------------------------------' + * + * The driver uses DSA to integrate the 4 user and 1 extension ports into the + * kernel. Netdevices are created for the user ports, as are PHY devices for + * their integrated PHYs. The device tree firmware should also specify the link + * partner of the extension port - either via a fixed-link or other phy-handle. + * See the device tree bindings for more detailed information. Note that the + * driver has only been tested with a fixed-link, but in principle it should not + * matter. + * + * NOTE: Currently, only the RGMII interface is implemented in this driver. + * + * The interrupt line is asserted on link UP/DOWN events. The driver creates a + * custom irqchip to handle this interrupt and demultiplex the events by reading + * the status registers via SMI. Interrupts are then propagated to the relevant + * PHY device. + * + * The EEPROM contains initial register values which the chip will read over I2C + * upon hardware reset. It is also possible to omit the EEPROM. In both cases, + * the driver will manually reprogram some registers using jam tables to reach + * an initial state defined by the vendor driver. + * + * This Linux driver is written based on an OS-agnostic vendor driver from + * Realtek. The reference GPL-licensed sources can be found in the OpenWrt + * source tree under the name rtl8367c. The vendor driver claims to support a + * number of similar switch controllers from Realtek, but the only hardware we + * have is the RTL8365MB-VC. Moreover, there does not seem to be any chip under + * the name RTL8367C. Although one wishes that the 'C' stood for some kind of + * common hardware revision, there exist examples of chips with the suffix -VC + * which are explicitly not supported by the rtl8367c driver and which instead + * require the rtl8367d vendor driver. With all this uncertainty, the driver has + * been modestly named rtl8365mb. Future implementors may wish to rename things + * accordingly. + * + * In the same family of chips, some carry up to 8 user ports and up to 2 + * extension ports. Where possible this driver tries to make things generic, but + * more work must be done to support these configurations. According to + * documentation from Realtek, the family should include the following chips: + * + * - RTL8363NB + * - RTL8363NB-VB + * - RTL8363SC + * - RTL8363SC-VB + * - RTL8364NB + * - RTL8364NB-VB + * - RTL8365MB-VC + * - RTL8366SC + * - RTL8367RB-VB + * - RTL8367SB + * - RTL8367S + * - RTL8370MB + * - RTL8310SR + * + * Some of the register logic for these additional chips has been skipped over + * while implementing this driver. It is therefore not possible to assume that + * things will work out-of-the-box for other chips, and a careful review of the + * vendor driver may be needed to expand support. The RTL8365MB-VC seems to be + * one of the simpler chips. + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#include "realtek-smi-core.h" + +/* Chip-specific data and limits */ +#define RTL8365MB_CHIP_ID_8365MB_VC 0x6367 +#define RTL8365MB_CPU_PORT_NUM_8365MB_VC 6 +#define RTL8365MB_LEARN_LIMIT_MAX_8365MB_VC 2112 + +/* Family-specific data and limits */ +#define RTL8365MB_NUM_PHYREGS 32 +#define RTL8365MB_PHYREGMAX (RTL8365MB_NUM_PHYREGS - 1) +#define RTL8365MB_MAX_NUM_PORTS (RTL8365MB_CPU_PORT_NUM_8365MB_VC + 1) + +/* Chip identification registers */ +#define RTL8365MB_CHIP_ID_REG 0x1300 + +#define RTL8365MB_CHIP_VER_REG 0x1301 + +#define RTL8365MB_MAGIC_REG 0x13C2 +#define RTL8365MB_MAGIC_VALUE 0x0249 + +/* Chip reset register */ +#define RTL8365MB_CHIP_RESET_REG 0x1322 +#define RTL8365MB_CHIP_RESET_SW_MASK 0x0002 +#define RTL8365MB_CHIP_RESET_HW_MASK 0x0001 + +/* Interrupt polarity register */ +#define RTL8365MB_INTR_POLARITY_REG 0x1100 +#define RTL8365MB_INTR_POLARITY_MASK 0x0001 +#define RTL8365MB_INTR_POLARITY_HIGH 0 +#define RTL8365MB_INTR_POLARITY_LOW 1 + +/* Interrupt control/status register - enable/check specific interrupt types */ +#define RTL8365MB_INTR_CTRL_REG 0x1101 +#define RTL8365MB_INTR_STATUS_REG 0x1102 +#define RTL8365MB_INTR_SLIENT_START_2_MASK 0x1000 +#define RTL8365MB_INTR_SLIENT_START_MASK 0x0800 +#define RTL8365MB_INTR_ACL_ACTION_MASK 0x0200 +#define RTL8365MB_INTR_CABLE_DIAG_FIN_MASK 0x0100 +#define RTL8365MB_INTR_INTERRUPT_8051_MASK 0x0080 +#define RTL8365MB_INTR_LOOP_DETECTION_MASK 0x0040 +#define RTL8365MB_INTR_GREEN_TIMER_MASK 0x0020 +#define RTL8365MB_INTR_SPECIAL_CONGEST_MASK 0x0010 +#define RTL8365MB_INTR_SPEED_CHANGE_MASK 0x0008 +#define RTL8365MB_INTR_LEARN_OVER_MASK 0x0004 +#define RTL8365MB_INTR_METER_EXCEEDED_MASK 0x0002 +#define RTL8365MB_INTR_LINK_CHANGE_MASK 0x0001 +#define RTL8365MB_INTR_ALL_MASK \ + (RTL8365MB_INTR_SLIENT_START_2_MASK | \ + RTL8365MB_INTR_SLIENT_START_MASK | \ + RTL8365MB_INTR_ACL_ACTION_MASK | \ + RTL8365MB_INTR_CABLE_DIAG_FIN_MASK | \ + RTL8365MB_INTR_INTERRUPT_8051_MASK | \ + RTL8365MB_INTR_LOOP_DETECTION_MASK | \ + RTL8365MB_INTR_GREEN_TIMER_MASK | \ + RTL8365MB_INTR_SPECIAL_CONGEST_MASK | \ + RTL8365MB_INTR_SPEED_CHANGE_MASK | \ + RTL8365MB_INTR_LEARN_OVER_MASK | \ + RTL8365MB_INTR_METER_EXCEEDED_MASK | \ + RTL8365MB_INTR_LINK_CHANGE_MASK) + +/* Per-port interrupt type status registers */ +#define RTL8365MB_PORT_LINKDOWN_IND_REG 0x1106 +#define RTL8365MB_PORT_LINKDOWN_IND_MASK 0x07FF + +#define RTL8365MB_PORT_LINKUP_IND_REG 0x1107 +#define RTL8365MB_PORT_LINKUP_IND_MASK 0x07FF + +/* PHY indirect access registers */ +#define RTL8365MB_INDIRECT_ACCESS_CTRL_REG 0x1F00 +#define RTL8365MB_INDIRECT_ACCESS_CTRL_RW_MASK 0x0002 +#define RTL8365MB_INDIRECT_ACCESS_CTRL_RW_READ 0 +#define RTL8365MB_INDIRECT_ACCESS_CTRL_RW_WRITE 1 +#define RTL8365MB_INDIRECT_ACCESS_CTRL_CMD_MASK 0x0001 +#define RTL8365MB_INDIRECT_ACCESS_CTRL_CMD_VALUE 1 +#define RTL8365MB_INDIRECT_ACCESS_STATUS_REG 0x1F01 +#define RTL8365MB_INDIRECT_ACCESS_ADDRESS_REG 0x1F02 +#define RTL8365MB_INDIRECT_ACCESS_ADDRESS_OCPADR_5_1_MASK GENMASK(4, 0) +#define RTL8365MB_INDIRECT_ACCESS_ADDRESS_PHYNUM_MASK GENMASK(6, 5) +#define RTL8365MB_INDIRECT_ACCESS_ADDRESS_OCPADR_9_6_MASK GENMASK(11, 8) +#define RTL8365MB_PHY_BASE 0x2000 +#define RTL8365MB_INDIRECT_ACCESS_WRITE_DATA_REG 0x1F03 +#define RTL8365MB_INDIRECT_ACCESS_READ_DATA_REG 0x1F04 + +/* PHY OCP address prefix register */ +#define RTL8365MB_GPHY_OCP_MSB_0_REG 0x1D15 +#define RTL8365MB_GPHY_OCP_MSB_0_CFG_CPU_OCPADR_MASK 0x0FC0 +#define RTL8365MB_PHY_OCP_ADDR_PREFIX_MASK 0xFC00 + +/* The PHY OCP addresses of PHY registers 0~31 start here */ +#define RTL8365MB_PHY_OCP_ADDR_PHYREG_BASE 0xA400 + +/* EXT port interface mode values - used in DIGITAL_INTERFACE_SELECT */ +#define RTL8365MB_EXT_PORT_MODE_DISABLE 0 +#define RTL8365MB_EXT_PORT_MODE_RGMII 1 +#define RTL8365MB_EXT_PORT_MODE_MII_MAC 2 +#define RTL8365MB_EXT_PORT_MODE_MII_PHY 3 +#define RTL8365MB_EXT_PORT_MODE_TMII_MAC 4 +#define RTL8365MB_EXT_PORT_MODE_TMII_PHY 5 +#define RTL8365MB_EXT_PORT_MODE_GMII 6 +#define RTL8365MB_EXT_PORT_MODE_RMII_MAC 7 +#define RTL8365MB_EXT_PORT_MODE_RMII_PHY 8 +#define RTL8365MB_EXT_PORT_MODE_SGMII 9 +#define RTL8365MB_EXT_PORT_MODE_HSGMII 10 +#define RTL8365MB_EXT_PORT_MODE_1000X_100FX 11 +#define RTL8365MB_EXT_PORT_MODE_1000X 12 +#define RTL8365MB_EXT_PORT_MODE_100FX 13 + +/* EXT port interface mode configuration registers 0~1 */ +#define RTL8365MB_DIGITAL_INTERFACE_SELECT_REG0 0x1305 +#define RTL8365MB_DIGITAL_INTERFACE_SELECT_REG1 0x13C3 +#define RTL8365MB_DIGITAL_INTERFACE_SELECT_REG(_extport) \ + (RTL8365MB_DIGITAL_INTERFACE_SELECT_REG0 + \ + ((_extport) >> 1) * (0x13C3 - 0x1305)) +#define RTL8365MB_DIGITAL_INTERFACE_SELECT_MODE_MASK(_extport) \ + (0xF << (((_extport) % 2))) +#define RTL8365MB_DIGITAL_INTERFACE_SELECT_MODE_OFFSET(_extport) \ + (((_extport) % 2) * 4) + +/* EXT port RGMII TX/RX delay configuration registers 1~2 */ +#define RTL8365MB_EXT_RGMXF_REG1 0x1307 +#define RTL8365MB_EXT_RGMXF_REG2 0x13C5 +#define RTL8365MB_EXT_RGMXF_REG(_extport) \ + (RTL8365MB_EXT_RGMXF_REG1 + \ + (((_extport) >> 1) * (0x13C5 - 0x1307))) +#define RTL8365MB_EXT_RGMXF_RXDELAY_MASK 0x0007 +#define RTL8365MB_EXT_RGMXF_TXDELAY_MASK 0x0008 + +/* External port speed values - used in DIGITAL_INTERFACE_FORCE */ +#define RTL8365MB_PORT_SPEED_10M 0 +#define RTL8365MB_PORT_SPEED_100M 1 +#define RTL8365MB_PORT_SPEED_1000M 2 + +/* EXT port force configuration registers 0~2 */ +#define RTL8365MB_DIGITAL_INTERFACE_FORCE_REG0 0x1310 +#define RTL8365MB_DIGITAL_INTERFACE_FORCE_REG1 0x1311 +#define RTL8365MB_DIGITAL_INTERFACE_FORCE_REG2 0x13C4 +#define RTL8365MB_DIGITAL_INTERFACE_FORCE_REG(_extport) \ + (RTL8365MB_DIGITAL_INTERFACE_FORCE_REG0 + \ + ((_extport) & 0x1) + \ + ((((_extport) >> 1) & 0x1) * (0x13C4 - 0x1310))) +#define RTL8365MB_DIGITAL_INTERFACE_FORCE_EN_MASK 0x1000 +#define RTL8365MB_DIGITAL_INTERFACE_FORCE_NWAY_MASK 0x0080 +#define RTL8365MB_DIGITAL_INTERFACE_FORCE_TXPAUSE_MASK 0x0040 +#define RTL8365MB_DIGITAL_INTERFACE_FORCE_RXPAUSE_MASK 0x0020 +#define RTL8365MB_DIGITAL_INTERFACE_FORCE_LINK_MASK 0x0010 +#define RTL8365MB_DIGITAL_INTERFACE_FORCE_DUPLEX_MASK 0x0004 +#define RTL8365MB_DIGITAL_INTERFACE_FORCE_SPEED_MASK 0x0003 + +/* CPU port mask register - controls which ports are treated as CPU ports */ +#define RTL8365MB_CPU_PORT_MASK_REG 0x1219 +#define RTL8365MB_CPU_PORT_MASK_MASK 0x07FF + +/* CPU control register */ +#define RTL8365MB_CPU_CTRL_REG 0x121A +#define RTL8365MB_CPU_CTRL_TRAP_PORT_EXT_MASK 0x0400 +#define RTL8365MB_CPU_CTRL_TAG_FORMAT_MASK 0x0200 +#define RTL8365MB_CPU_CTRL_RXBYTECOUNT_MASK 0x0080 +#define RTL8365MB_CPU_CTRL_TAG_POSITION_MASK 0x0040 +#define RTL8365MB_CPU_CTRL_TRAP_PORT_MASK 0x0038 +#define RTL8365MB_CPU_CTRL_INSERTMODE_MASK 0x0006 +#define RTL8365MB_CPU_CTRL_EN_MASK 0x0001 + +/* Maximum packet length register */ +#define RTL8365MB_CFG0_MAX_LEN_REG 0x088C +#define RTL8365MB_CFG0_MAX_LEN_MASK 0x3FFF + +/* Port learning limit registers */ +#define RTL8365MB_LUT_PORT_LEARN_LIMIT_BASE 0x0A20 +#define RTL8365MB_LUT_PORT_LEARN_LIMIT_REG(_physport) \ + (RTL8365MB_LUT_PORT_LEARN_LIMIT_BASE + (_physport)) + +/* Port isolation (forwarding mask) registers */ +#define RTL8365MB_PORT_ISOLATION_REG_BASE 0x08A2 +#define RTL8365MB_PORT_ISOLATION_REG(_physport) \ + (RTL8365MB_PORT_ISOLATION_REG_BASE + (_physport)) +#define RTL8365MB_PORT_ISOLATION_MASK 0x07FF + +/* MSTP port state registers - indexed by tree instancrSTI (tree ine */ +#define RTL8365MB_MSTI_CTRL_BASE 0x0A00 +#define RTL8365MB_MSTI_CTRL_REG(_msti, _physport) \ + (RTL8365MB_MSTI_CTRL_BASE + ((_msti) << 1) + ((_physport) >> 3)) +#define RTL8365MB_MSTI_CTRL_PORT_STATE_OFFSET(_physport) ((_physport) << 1) +#define RTL8365MB_MSTI_CTRL_PORT_STATE_MASK(_physport) \ + (0x3 << RTL8365MB_MSTI_CTRL_PORT_STATE_OFFSET((_physport))) + +/* MIB counter value registers */ +#define RTL8365MB_MIB_COUNTER_BASE 0x1000 +#define RTL8365MB_MIB_COUNTER_REG(_x) (RTL8365MB_MIB_COUNTER_BASE + (_x)) + +/* MIB counter address register */ +#define RTL8365MB_MIB_ADDRESS_REG 0x1004 +#define RTL8365MB_MIB_ADDRESS_PORT_OFFSET 0x007C +#define RTL8365MB_MIB_ADDRESS(_p, _x) \ + (((RTL8365MB_MIB_ADDRESS_PORT_OFFSET) * (_p) + (_x)) >> 2) + +#define RTL8365MB_MIB_CTRL0_REG 0x1005 +#define RTL8365MB_MIB_CTRL0_RESET_MASK 0x0002 +#define RTL8365MB_MIB_CTRL0_BUSY_MASK 0x0001 + +/* The DSA callback .get_stats64 runs in atomic context, so we are not allowed + * to block. On the other hand, accessing MIB counters absolutely requires us to + * block. The solution is thus to schedule work which polls the MIB counters + * asynchronously and updates some private data, which the callback can then + * fetch atomically. Three seconds should be a good enough polling interval. + */ +#define RTL8365MB_STATS_INTERVAL_JIFFIES (3 * HZ) + +enum rtl8365mb_mib_counter_index { + RTL8365MB_MIB_ifInOctets, + RTL8365MB_MIB_dot3StatsFCSErrors, + RTL8365MB_MIB_dot3StatsSymbolErrors, + RTL8365MB_MIB_dot3InPauseFrames, + RTL8365MB_MIB_dot3ControlInUnknownOpcodes, + RTL8365MB_MIB_etherStatsFragments, + RTL8365MB_MIB_etherStatsJabbers, + RTL8365MB_MIB_ifInUcastPkts, + RTL8365MB_MIB_etherStatsDropEvents, + RTL8365MB_MIB_ifInMulticastPkts, + RTL8365MB_MIB_ifInBroadcastPkts, + RTL8365MB_MIB_inMldChecksumError, + RTL8365MB_MIB_inIgmpChecksumError, + RTL8365MB_MIB_inMldSpecificQuery, + RTL8365MB_MIB_inMldGeneralQuery, + RTL8365MB_MIB_inIgmpSpecificQuery, + RTL8365MB_MIB_inIgmpGeneralQuery, + RTL8365MB_MIB_inMldLeaves, + RTL8365MB_MIB_inIgmpLeaves, + RTL8365MB_MIB_etherStatsOctets, + RTL8365MB_MIB_etherStatsUnderSizePkts, + RTL8365MB_MIB_etherOversizeStats, + RTL8365MB_MIB_etherStatsPkts64Octets, + RTL8365MB_MIB_etherStatsPkts65to127Octets, + RTL8365MB_MIB_etherStatsPkts128to255Octets, + RTL8365MB_MIB_etherStatsPkts256to511Octets, + RTL8365MB_MIB_etherStatsPkts512to1023Octets, + RTL8365MB_MIB_etherStatsPkts1024to1518Octets, + RTL8365MB_MIB_ifOutOctets, + RTL8365MB_MIB_dot3StatsSingleCollisionFrames, + RTL8365MB_MIB_dot3StatsMultipleCollisionFrames, + RTL8365MB_MIB_dot3StatsDeferredTransmissions, + RTL8365MB_MIB_dot3StatsLateCollisions, + RTL8365MB_MIB_etherStatsCollisions, + RTL8365MB_MIB_dot3StatsExcessiveCollisions, + RTL8365MB_MIB_dot3OutPauseFrames, + RTL8365MB_MIB_ifOutDiscards, + RTL8365MB_MIB_dot1dTpPortInDiscards, + RTL8365MB_MIB_ifOutUcastPkts, + RTL8365MB_MIB_ifOutMulticastPkts, + RTL8365MB_MIB_ifOutBroadcastPkts, + RTL8365MB_MIB_outOampduPkts, + RTL8365MB_MIB_inOampduPkts, + RTL8365MB_MIB_inIgmpJoinsSuccess, + RTL8365MB_MIB_inIgmpJoinsFail, + RTL8365MB_MIB_inMldJoinsSuccess, + RTL8365MB_MIB_inMldJoinsFail, + RTL8365MB_MIB_inReportSuppressionDrop, + RTL8365MB_MIB_inLeaveSuppressionDrop, + RTL8365MB_MIB_outIgmpReports, + RTL8365MB_MIB_outIgmpLeaves, + RTL8365MB_MIB_outIgmpGeneralQuery, + RTL8365MB_MIB_outIgmpSpecificQuery, + RTL8365MB_MIB_outMldReports, + RTL8365MB_MIB_outMldLeaves, + RTL8365MB_MIB_outMldGeneralQuery, + RTL8365MB_MIB_outMldSpecificQuery, + RTL8365MB_MIB_inKnownMulticastPkts, + RTL8365MB_MIB_END, +}; + +struct rtl8365mb_mib_counter { + u32 offset; + u32 length; + const char *name; +}; + +#define RTL8365MB_MAKE_MIB_COUNTER(_offset, _length, _name) \ + [RTL8365MB_MIB_ ## _name] = { _offset, _length, #_name } + +static struct rtl8365mb_mib_counter rtl8365mb_mib_counters[] = { + RTL8365MB_MAKE_MIB_COUNTER(0, 4, ifInOctets), + RTL8365MB_MAKE_MIB_COUNTER(4, 2, dot3StatsFCSErrors), + RTL8365MB_MAKE_MIB_COUNTER(6, 2, dot3StatsSymbolErrors), + RTL8365MB_MAKE_MIB_COUNTER(8, 2, dot3InPauseFrames), + RTL8365MB_MAKE_MIB_COUNTER(10, 2, dot3ControlInUnknownOpcodes), + RTL8365MB_MAKE_MIB_COUNTER(12, 2, etherStatsFragments), + RTL8365MB_MAKE_MIB_COUNTER(14, 2, etherStatsJabbers), + RTL8365MB_MAKE_MIB_COUNTER(16, 2, ifInUcastPkts), + RTL8365MB_MAKE_MIB_COUNTER(18, 2, etherStatsDropEvents), + RTL8365MB_MAKE_MIB_COUNTER(20, 2, ifInMulticastPkts), + RTL8365MB_MAKE_MIB_COUNTER(22, 2, ifInBroadcastPkts), + RTL8365MB_MAKE_MIB_COUNTER(24, 2, inMldChecksumError), + RTL8365MB_MAKE_MIB_COUNTER(26, 2, inIgmpChecksumError), + RTL8365MB_MAKE_MIB_COUNTER(28, 2, inMldSpecificQuery), + RTL8365MB_MAKE_MIB_COUNTER(30, 2, inMldGeneralQuery), + RTL8365MB_MAKE_MIB_COUNTER(32, 2, inIgmpSpecificQuery), + RTL8365MB_MAKE_MIB_COUNTER(34, 2, inIgmpGeneralQuery), + RTL8365MB_MAKE_MIB_COUNTER(36, 2, inMldLeaves), + RTL8365MB_MAKE_MIB_COUNTER(38, 2, inIgmpLeaves), + RTL8365MB_MAKE_MIB_COUNTER(40, 4, etherStatsOctets), + RTL8365MB_MAKE_MIB_COUNTER(44, 2, etherStatsUnderSizePkts), + RTL8365MB_MAKE_MIB_COUNTER(46, 2, etherOversizeStats), + RTL8365MB_MAKE_MIB_COUNTER(48, 2, etherStatsPkts64Octets), + RTL8365MB_MAKE_MIB_COUNTER(50, 2, etherStatsPkts65to127Octets), + RTL8365MB_MAKE_MIB_COUNTER(52, 2, etherStatsPkts128to255Octets), + RTL8365MB_MAKE_MIB_COUNTER(54, 2, etherStatsPkts256to511Octets), + RTL8365MB_MAKE_MIB_COUNTER(56, 2, etherStatsPkts512to1023Octets), + RTL8365MB_MAKE_MIB_COUNTER(58, 2, etherStatsPkts1024to1518Octets), + RTL8365MB_MAKE_MIB_COUNTER(60, 4, ifOutOctets), + RTL8365MB_MAKE_MIB_COUNTER(64, 2, dot3StatsSingleCollisionFrames), + RTL8365MB_MAKE_MIB_COUNTER(66, 2, dot3StatsMultipleCollisionFrames), + RTL8365MB_MAKE_MIB_COUNTER(68, 2, dot3StatsDeferredTransmissions), + RTL8365MB_MAKE_MIB_COUNTER(70, 2, dot3StatsLateCollisions), + RTL8365MB_MAKE_MIB_COUNTER(72, 2, etherStatsCollisions), + RTL8365MB_MAKE_MIB_COUNTER(74, 2, dot3StatsExcessiveCollisions), + RTL8365MB_MAKE_MIB_COUNTER(76, 2, dot3OutPauseFrames), + RTL8365MB_MAKE_MIB_COUNTER(78, 2, ifOutDiscards), + RTL8365MB_MAKE_MIB_COUNTER(80, 2, dot1dTpPortInDiscards), + RTL8365MB_MAKE_MIB_COUNTER(82, 2, ifOutUcastPkts), + RTL8365MB_MAKE_MIB_COUNTER(84, 2, ifOutMulticastPkts), + RTL8365MB_MAKE_MIB_COUNTER(86, 2, ifOutBroadcastPkts), + RTL8365MB_MAKE_MIB_COUNTER(88, 2, outOampduPkts), + RTL8365MB_MAKE_MIB_COUNTER(90, 2, inOampduPkts), + RTL8365MB_MAKE_MIB_COUNTER(92, 4, inIgmpJoinsSuccess), + RTL8365MB_MAKE_MIB_COUNTER(96, 2, inIgmpJoinsFail), + RTL8365MB_MAKE_MIB_COUNTER(98, 2, inMldJoinsSuccess), + RTL8365MB_MAKE_MIB_COUNTER(100, 2, inMldJoinsFail), + RTL8365MB_MAKE_MIB_COUNTER(102, 2, inReportSuppressionDrop), + RTL8365MB_MAKE_MIB_COUNTER(104, 2, inLeaveSuppressionDrop), + RTL8365MB_MAKE_MIB_COUNTER(106, 2, outIgmpReports), + RTL8365MB_MAKE_MIB_COUNTER(108, 2, outIgmpLeaves), + RTL8365MB_MAKE_MIB_COUNTER(110, 2, outIgmpGeneralQuery), + RTL8365MB_MAKE_MIB_COUNTER(112, 2, outIgmpSpecificQuery), + RTL8365MB_MAKE_MIB_COUNTER(114, 2, outMldReports), + RTL8365MB_MAKE_MIB_COUNTER(116, 2, outMldLeaves), + RTL8365MB_MAKE_MIB_COUNTER(118, 2, outMldGeneralQuery), + RTL8365MB_MAKE_MIB_COUNTER(120, 2, outMldSpecificQuery), + RTL8365MB_MAKE_MIB_COUNTER(122, 2, inKnownMulticastPkts), +}; + +static_assert(ARRAY_SIZE(rtl8365mb_mib_counters) == RTL8365MB_MIB_END); + +struct rtl8365mb_jam_tbl_entry { + u16 reg; + u16 val; +}; + +/* Lifted from the vendor driver sources */ +static const struct rtl8365mb_jam_tbl_entry rtl8365mb_init_jam_8365mb_vc[] = { + { 0x13EB, 0x15BB }, { 0x1303, 0x06D6 }, { 0x1304, 0x0700 }, + { 0x13E2, 0x003F }, { 0x13F9, 0x0090 }, { 0x121E, 0x03CA }, + { 0x1233, 0x0352 }, { 0x1237, 0x00A0 }, { 0x123A, 0x0030 }, + { 0x1239, 0x0084 }, { 0x0301, 0x1000 }, { 0x1349, 0x001F }, + { 0x18E0, 0x4004 }, { 0x122B, 0x241C }, { 0x1305, 0xC000 }, + { 0x13F0, 0x0000 }, +}; + +static const struct rtl8365mb_jam_tbl_entry rtl8365mb_init_jam_common[] = { + { 0x1200, 0x7FCB }, { 0x0884, 0x0003 }, { 0x06EB, 0x0001 }, + { 0x03Fa, 0x0007 }, { 0x08C8, 0x00C0 }, { 0x0A30, 0x020E }, + { 0x0800, 0x0000 }, { 0x0802, 0x0000 }, { 0x09DA, 0x0013 }, + { 0x1D32, 0x0002 }, +}; + +enum rtl8365mb_stp_state { + RTL8365MB_STP_STATE_DISABLED = 0, + RTL8365MB_STP_STATE_BLOCKING = 1, + RTL8365MB_STP_STATE_LEARNING = 2, + RTL8365MB_STP_STATE_FORWARDING = 3, +}; + +enum rtl8365mb_cpu_insert { + RTL8365MB_CPU_INSERT_TO_ALL = 0, + RTL8365MB_CPU_INSERT_TO_TRAPPING = 1, + RTL8365MB_CPU_INSERT_TO_NONE = 2, +}; + +enum rtl8365mb_cpu_position { + RTL8365MB_CPU_POS_AFTER_SA = 0, + RTL8365MB_CPU_POS_BEFORE_CRC = 1, +}; + +enum rtl8365mb_cpu_format { + RTL8365MB_CPU_FORMAT_8BYTES = 0, + RTL8365MB_CPU_FORMAT_4BYTES = 1, +}; + +enum rtl8365mb_cpu_rxlen { + RTL8365MB_CPU_RXLEN_72BYTES = 0, + RTL8365MB_CPU_RXLEN_64BYTES = 1, +}; + +/** + * struct rtl8365mb_cpu - CPU port configuration + * @enable: enable/disable hardware insertion of CPU tag in switch->CPU frames + * @mask: port mask of ports that parse should parse CPU tags + * @trap_port: forward trapped frames to this port + * @insert: CPU tag insertion mode in switch->CPU frames + * @position: position of CPU tag in frame + * @rx_length: minimum CPU RX length + * @format: CPU tag format + * + * Represents the CPU tagging and CPU port configuration of the switch. These + * settings are configurable at runtime. + */ +struct rtl8365mb_cpu { + bool enable; + u32 mask; + u32 trap_port; + enum rtl8365mb_cpu_insert insert; + enum rtl8365mb_cpu_position position; + enum rtl8365mb_cpu_rxlen rx_length; + enum rtl8365mb_cpu_format format; +}; + +/** + * struct rtl8365mb_port - private per-port data + * @smi: pointer to parent realtek_smi data + * @index: DSA port index, same as dsa_port::index + * @stats: link statistics populated by rtl8365mb_stats_poll, ready for atomic + * access via rtl8365mb_get_stats64 + * @stats_lock: protect the stats structure during read/update + * @mib_work: delayed work for polling MIB counters + */ +struct rtl8365mb_port { + struct realtek_smi *smi; + unsigned int index; + struct rtnl_link_stats64 stats; + spinlock_t stats_lock; + struct delayed_work mib_work; +}; + +/** + * struct rtl8365mb - private chip-specific driver data + * @smi: pointer to parent realtek_smi data + * @irq: registered IRQ or zero + * @chip_id: chip identifier + * @chip_ver: chip silicon revision + * @port_mask: mask of all ports + * @learn_limit_max: maximum number of L2 addresses the chip can learn + * @cpu: CPU tagging and CPU port configuration for this chip + * @mib_lock: prevent concurrent reads of MIB counters + * @ports: per-port data + * @jam_table: chip-specific initialization jam table + * @jam_size: size of the chip's jam table + * + * Private data for this driver. + */ +struct rtl8365mb { + struct realtek_smi *smi; + int irq; + u32 chip_id; + u32 chip_ver; + u32 port_mask; + u32 learn_limit_max; + struct rtl8365mb_cpu cpu; + struct mutex mib_lock; + struct rtl8365mb_port ports[RTL8365MB_MAX_NUM_PORTS]; + const struct rtl8365mb_jam_tbl_entry *jam_table; + size_t jam_size; +}; + +static int rtl8365mb_phy_poll_busy(struct realtek_smi *smi) +{ + u32 val; + + return regmap_read_poll_timeout(smi->map, + RTL8365MB_INDIRECT_ACCESS_STATUS_REG, + val, !val, 10, 100); +} + +static int rtl8365mb_phy_ocp_prepare(struct realtek_smi *smi, int phy, + u32 ocp_addr) +{ + u32 val; + int ret; + + /* Set OCP prefix */ + val = FIELD_GET(RTL8365MB_PHY_OCP_ADDR_PREFIX_MASK, ocp_addr); + ret = regmap_update_bits( + smi->map, RTL8365MB_GPHY_OCP_MSB_0_REG, + RTL8365MB_GPHY_OCP_MSB_0_CFG_CPU_OCPADR_MASK, + FIELD_PREP(RTL8365MB_GPHY_OCP_MSB_0_CFG_CPU_OCPADR_MASK, val)); + if (ret) + return ret; + + /* Set PHY register address */ + val = RTL8365MB_PHY_BASE; + val |= FIELD_PREP(RTL8365MB_INDIRECT_ACCESS_ADDRESS_PHYNUM_MASK, phy); + val |= FIELD_PREP(RTL8365MB_INDIRECT_ACCESS_ADDRESS_OCPADR_5_1_MASK, + ocp_addr >> 1); + val |= FIELD_PREP(RTL8365MB_INDIRECT_ACCESS_ADDRESS_OCPADR_9_6_MASK, + ocp_addr >> 6); + ret = regmap_write(smi->map, RTL8365MB_INDIRECT_ACCESS_ADDRESS_REG, + val); + if (ret) + return ret; + + return 0; +} + +static int rtl8365mb_phy_ocp_read(struct realtek_smi *smi, int phy, + u32 ocp_addr, u16 *data) +{ + u32 val; + int ret; + + ret = rtl8365mb_phy_poll_busy(smi); + if (ret) + return ret; + + ret = rtl8365mb_phy_ocp_prepare(smi, phy, ocp_addr); + if (ret) + return ret; + + /* Execute read operation */ + val = FIELD_PREP(RTL8365MB_INDIRECT_ACCESS_CTRL_CMD_MASK, + RTL8365MB_INDIRECT_ACCESS_CTRL_CMD_VALUE) | + FIELD_PREP(RTL8365MB_INDIRECT_ACCESS_CTRL_RW_MASK, + RTL8365MB_INDIRECT_ACCESS_CTRL_RW_READ); + ret = regmap_write(smi->map, RTL8365MB_INDIRECT_ACCESS_CTRL_REG, val); + if (ret) + return ret; + + ret = rtl8365mb_phy_poll_busy(smi); + if (ret) + return ret; + + /* Get PHY register data */ + ret = regmap_read(smi->map, RTL8365MB_INDIRECT_ACCESS_READ_DATA_REG, + &val); + if (ret) + return ret; + + *data = val & 0xFFFF; + + return 0; +} + +static int rtl8365mb_phy_ocp_write(struct realtek_smi *smi, int phy, + u32 ocp_addr, u16 data) +{ + u32 val; + int ret; + + ret = rtl8365mb_phy_poll_busy(smi); + if (ret) + return ret; + + ret = rtl8365mb_phy_ocp_prepare(smi, phy, ocp_addr); + if (ret) + return ret; + + /* Set PHY register data */ + ret = regmap_write(smi->map, RTL8365MB_INDIRECT_ACCESS_WRITE_DATA_REG, + data); + if (ret) + return ret; + + /* Execute write operation */ + val = FIELD_PREP(RTL8365MB_INDIRECT_ACCESS_CTRL_CMD_MASK, + RTL8365MB_INDIRECT_ACCESS_CTRL_CMD_VALUE) | + FIELD_PREP(RTL8365MB_INDIRECT_ACCESS_CTRL_RW_MASK, + RTL8365MB_INDIRECT_ACCESS_CTRL_RW_WRITE); + ret = regmap_write(smi->map, RTL8365MB_INDIRECT_ACCESS_CTRL_REG, val); + if (ret) + return ret; + + ret = rtl8365mb_phy_poll_busy(smi); + if (ret) + return ret; + + return 0; +} + +static int rtl8365mb_phy_read(struct realtek_smi *smi, int phy, int regnum) +{ + u32 ocp_addr; + u16 val; + int ret; + + if (regnum > RTL8365MB_PHYREGMAX) + return -EINVAL; + + ocp_addr = RTL8365MB_PHY_OCP_ADDR_PHYREG_BASE + regnum * 2; + + ret = rtl8365mb_phy_ocp_read(smi, phy, ocp_addr, &val); + if (ret) { + dev_err(smi->dev, + "failed to read PHY%d reg %02x @ %04x, ret %d\n", phy, + regnum, ocp_addr, ret); + return ret; + } + + dev_dbg(smi->dev, "read PHY%d register 0x%02x @ %04x, val <- %04x\n", + phy, regnum, ocp_addr, val); + + return val; +} + +static int rtl8365mb_phy_write(struct realtek_smi *smi, int phy, int regnum, + u16 val) +{ + u32 ocp_addr; + int ret; + + if (regnum > RTL8365MB_PHYREGMAX) + return -EINVAL; + + ocp_addr = RTL8365MB_PHY_OCP_ADDR_PHYREG_BASE + regnum * 2; + + ret = rtl8365mb_phy_ocp_write(smi, phy, ocp_addr, val); + if (ret) { + dev_err(smi->dev, + "failed to write PHY%d reg %02x @ %04x, ret %d\n", phy, + regnum, ocp_addr, ret); + return ret; + } + + dev_dbg(smi->dev, "write PHY%d register 0x%02x @ %04x, val -> %04x\n", + phy, regnum, ocp_addr, val); + + return 0; +} + +static enum dsa_tag_protocol +rtl8365mb_get_tag_protocol(struct dsa_switch *ds, int port, + enum dsa_tag_protocol mp) +{ + return DSA_TAG_PROTO_RTL8_4; +} + +static int rtl8365mb_ext_config_rgmii(struct realtek_smi *smi, int port, + phy_interface_t interface) +{ + struct device_node *dn; + struct dsa_port *dp; + int tx_delay = 0; + int rx_delay = 0; + int ext_port; + u32 val; + int ret; + + if (port == smi->cpu_port) { + ext_port = 1; + } else { + dev_err(smi->dev, "only one EXT port is currently supported\n"); + return -EINVAL; + } + + dp = dsa_to_port(smi->ds, port); + dn = dp->dn; + + /* Set the RGMII TX/RX delay + * + * The Realtek vendor driver indicates the following possible + * configuration settings: + * + * TX delay: + * 0 = no delay, 1 = 2 ns delay + * RX delay: + * 0 = no delay, 7 = maximum delay + * No units are specified, but there are a total of 8 steps. + * + * The vendor driver also states that this must be configured *before* + * forcing the external interface into a particular mode, which is done + * in the rtl8365mb_phylink_mac_link_{up,down} functions. + * + * Only configure an RGMII TX (resp. RX) delay if the + * tx-internal-delay-ps (resp. rx-internal-delay-ps) OF property is + * specified. We ignore the detail of the RGMII interface mode + * (RGMII_{RXID, TXID, etc.}), as this is considered to be a PHY-only + * property. + * + * For the RX delay, we assume that a register value of 4 corresponds to + * 2 ns. But this is just an educated guess, so ignore all other values + * to avoid too much confusion. + */ + if (!of_property_read_u32(dn, "tx-internal-delay-ps", &val)) { + val = val / 1000; /* convert to ns */ + + if (val == 0 || val == 2) + tx_delay = val / 2; + else + dev_warn(smi->dev, + "EXT port TX delay must be 0 or 2 ns\n"); + } + + if (!of_property_read_u32(dn, "rx-internal-delay-ps", &val)) { + val = val / 1000; /* convert to ns */ + + if (val == 0 || val == 2) + rx_delay = val * 2; + else + dev_warn(smi->dev, + "EXT port RX delay must be 0 to 2 ns\n"); + } + + ret = regmap_update_bits( + smi->map, RTL8365MB_EXT_RGMXF_REG(ext_port), + RTL8365MB_EXT_RGMXF_TXDELAY_MASK | + RTL8365MB_EXT_RGMXF_RXDELAY_MASK, + FIELD_PREP(RTL8365MB_EXT_RGMXF_TXDELAY_MASK, tx_delay) | + FIELD_PREP(RTL8365MB_EXT_RGMXF_RXDELAY_MASK, rx_delay)); + if (ret) + return ret; + + ret = regmap_update_bits( + smi->map, RTL8365MB_DIGITAL_INTERFACE_SELECT_REG(ext_port), + RTL8365MB_DIGITAL_INTERFACE_SELECT_MODE_MASK(ext_port), + RTL8365MB_EXT_PORT_MODE_RGMII + << RTL8365MB_DIGITAL_INTERFACE_SELECT_MODE_OFFSET( + ext_port)); + if (ret) + return ret; + + return 0; +} + +static int rtl8365mb_ext_config_forcemode(struct realtek_smi *smi, int port, + bool link, int speed, int duplex, + bool tx_pause, bool rx_pause) +{ + u32 r_tx_pause; + u32 r_rx_pause; + u32 r_duplex; + u32 r_speed; + u32 r_link; + int ext_port; + int val; + int ret; + + if (port == smi->cpu_port) { + ext_port = 1; + } else { + dev_err(smi->dev, "only one EXT port is currently supported\n"); + return -EINVAL; + } + + if (link) { + /* Force the link up with the desired configuration */ + r_link = 1; + r_rx_pause = rx_pause ? 1 : 0; + r_tx_pause = tx_pause ? 1 : 0; + + if (speed == SPEED_1000) { + r_speed = RTL8365MB_PORT_SPEED_1000M; + } else if (speed == SPEED_100) { + r_speed = RTL8365MB_PORT_SPEED_100M; + } else if (speed == SPEED_10) { + r_speed = RTL8365MB_PORT_SPEED_10M; + } else { + dev_err(smi->dev, "unsupported port speed %s\n", + phy_speed_to_str(speed)); + return -EINVAL; + } + + if (duplex == DUPLEX_FULL) { + r_duplex = 1; + } else if (duplex == DUPLEX_HALF) { + r_duplex = 0; + } else { + dev_err(smi->dev, "unsupported duplex %s\n", + phy_duplex_to_str(duplex)); + return -EINVAL; + } + } else { + /* Force the link down and reset any programmed configuration */ + r_link = 0; + r_tx_pause = 0; + r_rx_pause = 0; + r_speed = 0; + r_duplex = 0; + } + + val = FIELD_PREP(RTL8365MB_DIGITAL_INTERFACE_FORCE_EN_MASK, 1) | + FIELD_PREP(RTL8365MB_DIGITAL_INTERFACE_FORCE_TXPAUSE_MASK, + r_tx_pause) | + FIELD_PREP(RTL8365MB_DIGITAL_INTERFACE_FORCE_RXPAUSE_MASK, + r_rx_pause) | + FIELD_PREP(RTL8365MB_DIGITAL_INTERFACE_FORCE_LINK_MASK, r_link) | + FIELD_PREP(RTL8365MB_DIGITAL_INTERFACE_FORCE_DUPLEX_MASK, + r_duplex) | + FIELD_PREP(RTL8365MB_DIGITAL_INTERFACE_FORCE_SPEED_MASK, r_speed); + ret = regmap_write(smi->map, + RTL8365MB_DIGITAL_INTERFACE_FORCE_REG(ext_port), + val); + if (ret) + return ret; + + return 0; +} + +static bool rtl8365mb_phy_mode_supported(struct dsa_switch *ds, int port, + phy_interface_t interface) +{ + if (dsa_is_user_port(ds, port) && + (interface == PHY_INTERFACE_MODE_NA || + interface == PHY_INTERFACE_MODE_INTERNAL)) + /* Internal PHY */ + return true; + else if (dsa_is_cpu_port(ds, port) && + phy_interface_mode_is_rgmii(interface)) + /* Extension MAC */ + return true; + + return false; +} + +static void rtl8365mb_phylink_validate(struct dsa_switch *ds, int port, + unsigned long *supported, + struct phylink_link_state *state) +{ + struct realtek_smi *smi = ds->priv; + __ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0 }; + + /* include/linux/phylink.h says: + * When @state->interface is %PHY_INTERFACE_MODE_NA, phylink + * expects the MAC driver to return all supported link modes. + */ + if (state->interface != PHY_INTERFACE_MODE_NA && + !rtl8365mb_phy_mode_supported(ds, port, state->interface)) { + dev_err(smi->dev, "phy mode %s is unsupported on port %d\n", + phy_modes(state->interface), port); + linkmode_zero(supported); + return; + } + + phylink_set_port_modes(mask); + + phylink_set(mask, Autoneg); + phylink_set(mask, Pause); + phylink_set(mask, Asym_Pause); + + phylink_set(mask, 10baseT_Half); + phylink_set(mask, 10baseT_Full); + phylink_set(mask, 100baseT_Half); + phylink_set(mask, 100baseT_Full); + phylink_set(mask, 1000baseT_Full); + + linkmode_and(supported, supported, mask); + linkmode_and(state->advertising, state->advertising, mask); +} + +static void rtl8365mb_phylink_mac_config(struct dsa_switch *ds, int port, + unsigned int mode, + const struct phylink_link_state *state) +{ + struct realtek_smi *smi = ds->priv; + int ret; + + if (!rtl8365mb_phy_mode_supported(ds, port, state->interface)) { + dev_err(smi->dev, "phy mode %s is unsupported on port %d\n", + phy_modes(state->interface), port); + return; + } + + if (mode != MLO_AN_PHY && mode != MLO_AN_FIXED) { + dev_err(smi->dev, + "port %d supports only conventional PHY or fixed-link\n", + port); + return; + } + + if (phy_interface_mode_is_rgmii(state->interface)) { + ret = rtl8365mb_ext_config_rgmii(smi, port, state->interface); + if (ret) + dev_err(smi->dev, + "failed to configure RGMII mode on port %d: %d\n", + port, ret); + return; + } + + /* TODO: Implement MII and RMII modes, which the RTL8365MB-VC also + * supports + */ +} + +static void rtl8365mb_phylink_mac_link_down(struct dsa_switch *ds, int port, + unsigned int mode, + phy_interface_t interface) +{ + struct realtek_smi *smi = ds->priv; + struct rtl8365mb_port *p; + struct rtl8365mb *mb; + int ret; + + mb = smi->chip_data; + p = &mb->ports[port]; + cancel_delayed_work_sync(&p->mib_work); + + if (phy_interface_mode_is_rgmii(interface)) { + ret = rtl8365mb_ext_config_forcemode(smi, port, false, 0, 0, + false, false); + if (ret) + dev_err(smi->dev, + "failed to reset forced mode on port %d: %d\n", + port, ret); + + return; + } +} + +static void rtl8365mb_phylink_mac_link_up(struct dsa_switch *ds, int port, + unsigned int mode, + phy_interface_t interface, + struct phy_device *phydev, int speed, + int duplex, bool tx_pause, + bool rx_pause) +{ + struct realtek_smi *smi = ds->priv; + struct rtl8365mb_port *p; + struct rtl8365mb *mb; + int ret; + + mb = smi->chip_data; + p = &mb->ports[port]; + schedule_delayed_work(&p->mib_work, 0); + + if (phy_interface_mode_is_rgmii(interface)) { + ret = rtl8365mb_ext_config_forcemode(smi, port, true, speed, + duplex, tx_pause, + rx_pause); + if (ret) + dev_err(smi->dev, + "failed to force mode on port %d: %d\n", port, + ret); + + return; + } +} + +static void rtl8365mb_port_stp_state_set(struct dsa_switch *ds, int port, + u8 state) +{ + struct realtek_smi *smi = ds->priv; + enum rtl8365mb_stp_state val; + int msti = 0; + + switch (state) { + case BR_STATE_DISABLED: + val = RTL8365MB_STP_STATE_DISABLED; + break; + case BR_STATE_BLOCKING: + case BR_STATE_LISTENING: + val = RTL8365MB_STP_STATE_BLOCKING; + break; + case BR_STATE_LEARNING: + val = RTL8365MB_STP_STATE_LEARNING; + break; + case BR_STATE_FORWARDING: + val = RTL8365MB_STP_STATE_FORWARDING; + break; + default: + dev_err(smi->dev, "invalid STP state: %u\n", state); + return; + } + + regmap_update_bits(smi->map, RTL8365MB_MSTI_CTRL_REG(msti, port), + RTL8365MB_MSTI_CTRL_PORT_STATE_MASK(port), + val << RTL8365MB_MSTI_CTRL_PORT_STATE_OFFSET(port)); +} + +static int rtl8365mb_port_set_learning(struct realtek_smi *smi, int port, + bool enable) +{ + struct rtl8365mb *mb = smi->chip_data; + + /* Enable/disable learning by limiting the number of L2 addresses the + * port can learn. Realtek documentation states that a limit of zero + * disables learning. When enabling learning, set it to the chip's + * maximum. + */ + return regmap_write(smi->map, RTL8365MB_LUT_PORT_LEARN_LIMIT_REG(port), + enable ? mb->learn_limit_max : 0); +} + +static int rtl8365mb_port_set_isolation(struct realtek_smi *smi, int port, + u32 mask) +{ + return regmap_write(smi->map, RTL8365MB_PORT_ISOLATION_REG(port), mask); +} + +static int rtl8365mb_mib_counter_read(struct realtek_smi *smi, int port, + u32 offset, u32 length, u64 *mibvalue) +{ + u64 tmpvalue = 0; + u32 val; + int ret; + int i; + + /* The MIB address is an SRAM address. We request a particular address + * and then poll the control register before reading the value from some + * counter registers. + */ + ret = regmap_write(smi->map, RTL8365MB_MIB_ADDRESS_REG, + RTL8365MB_MIB_ADDRESS(port, offset)); + if (ret) + return ret; + + /* Poll for completion */ + ret = regmap_read_poll_timeout(smi->map, RTL8365MB_MIB_CTRL0_REG, val, + !(val & RTL8365MB_MIB_CTRL0_BUSY_MASK), + 10, 100); + if (ret) + return ret; + + /* Presumably this indicates a MIB counter read failure */ + if (val & RTL8365MB_MIB_CTRL0_RESET_MASK) + return -EIO; + + /* There are four MIB counter registers each holding a 16 bit word of a + * MIB counter. Depending on the offset, we should read from the upper + * two or lower two registers. In case the MIB counter is 4 words, we + * read from all four registers. + */ + if (length == 4) + offset = 3; + else + offset = (offset + 1) % 4; + + /* Read the MIB counter 16 bits at a time */ + for (i = 0; i < length; i++) { + ret = regmap_read(smi->map, + RTL8365MB_MIB_COUNTER_REG(offset - i), &val); + if (ret) + return ret; + + tmpvalue = ((tmpvalue) << 16) | (val & 0xFFFF); + } + + /* Only commit the result if no error occurred */ + *mibvalue = tmpvalue; + + return 0; +} + +static void rtl8365mb_get_ethtool_stats(struct dsa_switch *ds, int port, u64 *data) +{ + struct realtek_smi *smi = ds->priv; + struct rtl8365mb *mb; + int ret; + int i; + + mb = smi->chip_data; + + mutex_lock(&mb->mib_lock); + for (i = 0; i < RTL8365MB_MIB_END; i++) { + struct rtl8365mb_mib_counter *mib = &rtl8365mb_mib_counters[i]; + + ret = rtl8365mb_mib_counter_read(smi, port, mib->offset, + mib->length, &data[i]); + if (ret) { + dev_err(smi->dev, + "failed to read port %d counters: %d\n", port, + ret); + break; + } + } + mutex_unlock(&mb->mib_lock); +} + +static void rtl8365mb_get_strings(struct dsa_switch *ds, int port, u32 stringset, u8 *data) +{ + int i; + + if (stringset != ETH_SS_STATS) + return; + + for (i = 0; i < RTL8365MB_MIB_END; i++) { + struct rtl8365mb_mib_counter *mib = &rtl8365mb_mib_counters[i]; + + strncpy(data + i * ETH_GSTRING_LEN, mib->name, ETH_GSTRING_LEN); + } +} + +static int rtl8365mb_get_sset_count(struct dsa_switch *ds, int port, int sset) +{ + if (sset != ETH_SS_STATS) + return -EOPNOTSUPP; + + return RTL8365MB_MIB_END; +} + +static void rtl8365mb_get_phy_stats(struct dsa_switch *ds, int port, + struct ethtool_eth_phy_stats *phy_stats) +{ + struct realtek_smi *smi = ds->priv; + struct rtl8365mb_mib_counter *mib; + struct rtl8365mb *mb; + + mb = smi->chip_data; + mib = &rtl8365mb_mib_counters[RTL8365MB_MIB_dot3StatsSymbolErrors]; + + mutex_lock(&mb->mib_lock); + rtl8365mb_mib_counter_read(smi, port, mib->offset, mib->length, + &phy_stats->SymbolErrorDuringCarrier); + mutex_unlock(&mb->mib_lock); +} + +static void rtl8365mb_get_mac_stats(struct dsa_switch *ds, int port, + struct ethtool_eth_mac_stats *mac_stats) +{ + u64 cnt[RTL8365MB_MIB_END] = { + [RTL8365MB_MIB_ifOutOctets] = 1, + [RTL8365MB_MIB_ifOutUcastPkts] = 1, + [RTL8365MB_MIB_ifOutMulticastPkts] = 1, + [RTL8365MB_MIB_ifOutBroadcastPkts] = 1, + [RTL8365MB_MIB_dot3OutPauseFrames] = 1, + [RTL8365MB_MIB_ifOutDiscards] = 1, + [RTL8365MB_MIB_ifInOctets] = 1, + [RTL8365MB_MIB_ifInUcastPkts] = 1, + [RTL8365MB_MIB_ifInMulticastPkts] = 1, + [RTL8365MB_MIB_ifInBroadcastPkts] = 1, + [RTL8365MB_MIB_dot3InPauseFrames] = 1, + [RTL8365MB_MIB_dot3StatsSingleCollisionFrames] = 1, + [RTL8365MB_MIB_dot3StatsMultipleCollisionFrames] = 1, + [RTL8365MB_MIB_dot3StatsFCSErrors] = 1, + [RTL8365MB_MIB_dot3StatsDeferredTransmissions] = 1, + [RTL8365MB_MIB_dot3StatsLateCollisions] = 1, + [RTL8365MB_MIB_dot3StatsExcessiveCollisions] = 1, + + }; + struct realtek_smi *smi = ds->priv; + struct rtl8365mb *mb; + int ret; + int i; + + mb = smi->chip_data; + + mutex_lock(&mb->mib_lock); + for (i = 0; i < RTL8365MB_MIB_END; i++) { + struct rtl8365mb_mib_counter *mib = &rtl8365mb_mib_counters[i]; + + /* Only fetch required MIB counters (marked = 1 above) */ + if (!cnt[i]) + continue; + + ret = rtl8365mb_mib_counter_read(smi, port, mib->offset, + mib->length, &cnt[i]); + if (ret) + break; + } + mutex_unlock(&mb->mib_lock); + + /* The RTL8365MB-VC exposes MIB objects, which we have to translate into + * IEEE 802.3 Managed Objects. This is not always completely faithful, + * but we try out best. See RFC 3635 for a detailed treatment of the + * subject. + */ + + mac_stats->FramesTransmittedOK = cnt[RTL8365MB_MIB_ifOutUcastPkts] + + cnt[RTL8365MB_MIB_ifOutMulticastPkts] + + cnt[RTL8365MB_MIB_ifOutBroadcastPkts] + + cnt[RTL8365MB_MIB_dot3OutPauseFrames] - + cnt[RTL8365MB_MIB_ifOutDiscards]; + mac_stats->SingleCollisionFrames = + cnt[RTL8365MB_MIB_dot3StatsSingleCollisionFrames]; + mac_stats->MultipleCollisionFrames = + cnt[RTL8365MB_MIB_dot3StatsMultipleCollisionFrames]; + mac_stats->FramesReceivedOK = cnt[RTL8365MB_MIB_ifInUcastPkts] + + cnt[RTL8365MB_MIB_ifInMulticastPkts] + + cnt[RTL8365MB_MIB_ifInBroadcastPkts] + + cnt[RTL8365MB_MIB_dot3InPauseFrames]; + mac_stats->FrameCheckSequenceErrors = + cnt[RTL8365MB_MIB_dot3StatsFCSErrors]; + mac_stats->OctetsTransmittedOK = cnt[RTL8365MB_MIB_ifOutOctets] - + 18 * mac_stats->FramesTransmittedOK; + mac_stats->FramesWithDeferredXmissions = + cnt[RTL8365MB_MIB_dot3StatsDeferredTransmissions]; + mac_stats->LateCollisions = cnt[RTL8365MB_MIB_dot3StatsLateCollisions]; + mac_stats->FramesAbortedDueToXSColls = + cnt[RTL8365MB_MIB_dot3StatsExcessiveCollisions]; + mac_stats->OctetsReceivedOK = cnt[RTL8365MB_MIB_ifInOctets] - + 18 * mac_stats->FramesReceivedOK; + mac_stats->MulticastFramesXmittedOK = + cnt[RTL8365MB_MIB_ifOutMulticastPkts]; + mac_stats->BroadcastFramesXmittedOK = + cnt[RTL8365MB_MIB_ifOutBroadcastPkts]; + mac_stats->MulticastFramesReceivedOK = + cnt[RTL8365MB_MIB_ifInMulticastPkts]; + mac_stats->BroadcastFramesReceivedOK = + cnt[RTL8365MB_MIB_ifInBroadcastPkts]; +} + +static void rtl8365mb_get_ctrl_stats(struct dsa_switch *ds, int port, + struct ethtool_eth_ctrl_stats *ctrl_stats) +{ + struct realtek_smi *smi = ds->priv; + struct rtl8365mb_mib_counter *mib; + struct rtl8365mb *mb; + + mb = smi->chip_data; + mib = &rtl8365mb_mib_counters[RTL8365MB_MIB_dot3ControlInUnknownOpcodes]; + + mutex_lock(&mb->mib_lock); + rtl8365mb_mib_counter_read(smi, port, mib->offset, mib->length, + &ctrl_stats->UnsupportedOpcodesReceived); + mutex_unlock(&mb->mib_lock); +} + +static void rtl8365mb_stats_update(struct realtek_smi *smi, int port) +{ + u64 cnt[RTL8365MB_MIB_END] = { + [RTL8365MB_MIB_ifOutOctets] = 1, + [RTL8365MB_MIB_ifOutUcastPkts] = 1, + [RTL8365MB_MIB_ifOutMulticastPkts] = 1, + [RTL8365MB_MIB_ifOutBroadcastPkts] = 1, + [RTL8365MB_MIB_ifOutDiscards] = 1, + [RTL8365MB_MIB_ifInOctets] = 1, + [RTL8365MB_MIB_ifInUcastPkts] = 1, + [RTL8365MB_MIB_ifInMulticastPkts] = 1, + [RTL8365MB_MIB_ifInBroadcastPkts] = 1, + [RTL8365MB_MIB_etherStatsDropEvents] = 1, + [RTL8365MB_MIB_etherStatsCollisions] = 1, + [RTL8365MB_MIB_etherStatsFragments] = 1, + [RTL8365MB_MIB_etherStatsJabbers] = 1, + [RTL8365MB_MIB_dot3StatsFCSErrors] = 1, + [RTL8365MB_MIB_dot3StatsLateCollisions] = 1, + }; + struct rtl8365mb *mb = smi->chip_data; + struct rtnl_link_stats64 *stats; + int ret; + int i; + + stats = &mb->ports[port].stats; + + mutex_lock(&mb->mib_lock); + for (i = 0; i < RTL8365MB_MIB_END; i++) { + struct rtl8365mb_mib_counter *c = &rtl8365mb_mib_counters[i]; + + /* Only fetch required MIB counters (marked = 1 above) */ + if (!cnt[i]) + continue; + + ret = rtl8365mb_mib_counter_read(smi, port, c->offset, + c->length, &cnt[i]); + if (ret) + break; + } + mutex_unlock(&mb->mib_lock); + + /* Don't update statistics if there was an error reading the counters */ + if (ret) + return; + + spin_lock(&mb->ports[port].stats_lock); + + stats->rx_packets = cnt[RTL8365MB_MIB_ifInUcastPkts] + + cnt[RTL8365MB_MIB_ifInMulticastPkts] + + cnt[RTL8365MB_MIB_ifInBroadcastPkts] - + cnt[RTL8365MB_MIB_ifOutDiscards]; + + stats->tx_packets = cnt[RTL8365MB_MIB_ifOutUcastPkts] + + cnt[RTL8365MB_MIB_ifOutMulticastPkts] + + cnt[RTL8365MB_MIB_ifOutBroadcastPkts]; + + /* if{In,Out}Octets includes FCS - remove it */ + stats->rx_bytes = cnt[RTL8365MB_MIB_ifInOctets] - 4 * stats->rx_packets; + stats->tx_bytes = + cnt[RTL8365MB_MIB_ifOutOctets] - 4 * stats->tx_packets; + + stats->rx_dropped = cnt[RTL8365MB_MIB_etherStatsDropEvents]; + stats->tx_dropped = cnt[RTL8365MB_MIB_ifOutDiscards]; + + stats->multicast = cnt[RTL8365MB_MIB_ifInMulticastPkts]; + stats->collisions = cnt[RTL8365MB_MIB_etherStatsCollisions]; + + stats->rx_length_errors = cnt[RTL8365MB_MIB_etherStatsFragments] + + cnt[RTL8365MB_MIB_etherStatsJabbers]; + stats->rx_crc_errors = cnt[RTL8365MB_MIB_dot3StatsFCSErrors]; + stats->rx_errors = stats->rx_length_errors + stats->rx_crc_errors; + + stats->tx_aborted_errors = cnt[RTL8365MB_MIB_ifOutDiscards]; + stats->tx_window_errors = cnt[RTL8365MB_MIB_dot3StatsLateCollisions]; + stats->tx_errors = stats->tx_aborted_errors + stats->tx_window_errors; + + spin_unlock(&mb->ports[port].stats_lock); +} + +static void rtl8365mb_stats_poll(struct work_struct *work) +{ + struct rtl8365mb_port *p = container_of(to_delayed_work(work), + struct rtl8365mb_port, + mib_work); + struct realtek_smi *smi = p->smi; + + rtl8365mb_stats_update(smi, p->index); + + schedule_delayed_work(&p->mib_work, RTL8365MB_STATS_INTERVAL_JIFFIES); +} + +static void rtl8365mb_get_stats64(struct dsa_switch *ds, int port, + struct rtnl_link_stats64 *s) +{ + struct realtek_smi *smi = ds->priv; + struct rtl8365mb_port *p; + struct rtl8365mb *mb; + + mb = smi->chip_data; + p = &mb->ports[port]; + + spin_lock(&p->stats_lock); + memcpy(s, &p->stats, sizeof(*s)); + spin_unlock(&p->stats_lock); +} + +static void rtl8365mb_stats_setup(struct realtek_smi *smi) +{ + struct rtl8365mb *mb = smi->chip_data; + int i; + + /* Per-chip global mutex to protect MIB counter access, since doing + * so requires accessing a series of registers in a particular order. + */ + mutex_init(&mb->mib_lock); + + for (i = 0; i < smi->num_ports; i++) { + struct rtl8365mb_port *p = &mb->ports[i]; + + if (dsa_is_unused_port(smi->ds, i)) + continue; + + /* Per-port spinlock to protect the stats64 data */ + spin_lock_init(&p->stats_lock); + + /* This work polls the MIB counters and keeps the stats64 data + * up-to-date. + */ + INIT_DELAYED_WORK(&p->mib_work, rtl8365mb_stats_poll); + } +} + +static void rtl8365mb_stats_teardown(struct realtek_smi *smi) +{ + struct rtl8365mb *mb = smi->chip_data; + int i; + + for (i = 0; i < smi->num_ports; i++) { + struct rtl8365mb_port *p = &mb->ports[i]; + + if (dsa_is_unused_port(smi->ds, i)) + continue; + + cancel_delayed_work_sync(&p->mib_work); + } +} + +static int rtl8365mb_get_and_clear_status_reg(struct realtek_smi *smi, u32 reg, + u32 *val) +{ + int ret; + + ret = regmap_read(smi->map, reg, val); + if (ret) + return ret; + + return regmap_write(smi->map, reg, *val); +} + +static irqreturn_t rtl8365mb_irq(int irq, void *data) +{ + struct realtek_smi *smi = data; + unsigned long line_changes = 0; + struct rtl8365mb *mb; + u32 stat; + int line; + int ret; + + mb = smi->chip_data; + + ret = rtl8365mb_get_and_clear_status_reg(smi, RTL8365MB_INTR_STATUS_REG, + &stat); + if (ret) + goto out_error; + + if (stat & RTL8365MB_INTR_LINK_CHANGE_MASK) { + u32 linkdown_ind; + u32 linkup_ind; + u32 val; + + ret = rtl8365mb_get_and_clear_status_reg( + smi, RTL8365MB_PORT_LINKUP_IND_REG, &val); + if (ret) + goto out_error; + + linkup_ind = FIELD_GET(RTL8365MB_PORT_LINKUP_IND_MASK, val); + + ret = rtl8365mb_get_and_clear_status_reg( + smi, RTL8365MB_PORT_LINKDOWN_IND_REG, &val); + if (ret) + goto out_error; + + linkdown_ind = FIELD_GET(RTL8365MB_PORT_LINKDOWN_IND_MASK, val); + + line_changes = (linkup_ind | linkdown_ind) & mb->port_mask; + } + + if (!line_changes) + goto out_none; + + for_each_set_bit(line, &line_changes, smi->num_ports) { + int child_irq = irq_find_mapping(smi->irqdomain, line); + + handle_nested_irq(child_irq); + } + + return IRQ_HANDLED; + +out_error: + dev_err(smi->dev, "failed to read interrupt status: %d\n", ret); + +out_none: + return IRQ_NONE; +} + +static struct irq_chip rtl8365mb_irq_chip = { + .name = "rtl8365mb", + /* The hardware doesn't support masking IRQs on a per-port basis */ +}; + +static int rtl8365mb_irq_map(struct irq_domain *domain, unsigned int irq, + irq_hw_number_t hwirq) +{ + irq_set_chip_data(irq, domain->host_data); + irq_set_chip_and_handler(irq, &rtl8365mb_irq_chip, handle_simple_irq); + irq_set_nested_thread(irq, 1); + irq_set_noprobe(irq); + + return 0; +} + +static void rtl8365mb_irq_unmap(struct irq_domain *d, unsigned int irq) +{ + irq_set_nested_thread(irq, 0); + irq_set_chip_and_handler(irq, NULL, NULL); + irq_set_chip_data(irq, NULL); +} + +static const struct irq_domain_ops rtl8365mb_irqdomain_ops = { + .map = rtl8365mb_irq_map, + .unmap = rtl8365mb_irq_unmap, + .xlate = irq_domain_xlate_onecell, +}; + +static int rtl8365mb_set_irq_enable(struct realtek_smi *smi, bool enable) +{ + return regmap_update_bits(smi->map, RTL8365MB_INTR_CTRL_REG, + RTL8365MB_INTR_LINK_CHANGE_MASK, + FIELD_PREP(RTL8365MB_INTR_LINK_CHANGE_MASK, + enable ? 1 : 0)); +} + +static int rtl8365mb_irq_enable(struct realtek_smi *smi) +{ + return rtl8365mb_set_irq_enable(smi, true); +} + +static int rtl8365mb_irq_disable(struct realtek_smi *smi) +{ + return rtl8365mb_set_irq_enable(smi, false); +} + +static int rtl8365mb_irq_setup(struct realtek_smi *smi) +{ + struct rtl8365mb *mb = smi->chip_data; + struct device_node *intc; + u32 irq_trig; + int virq; + int irq; + u32 val; + int ret; + int i; + + intc = of_get_child_by_name(smi->dev->of_node, "interrupt-controller"); + if (!intc) { + dev_err(smi->dev, "missing child interrupt-controller node\n"); + return -EINVAL; + } + + /* rtl8365mb IRQs cascade off this one */ + irq = of_irq_get(intc, 0); + if (irq <= 0) { + if (irq != -EPROBE_DEFER) + dev_err(smi->dev, "failed to get parent irq: %d\n", + irq); + ret = irq ? irq : -EINVAL; + goto out_put_node; + } + + smi->irqdomain = irq_domain_add_linear(intc, smi->num_ports, + &rtl8365mb_irqdomain_ops, smi); + if (!smi->irqdomain) { + dev_err(smi->dev, "failed to add irq domain\n"); + ret = -ENOMEM; + goto out_put_node; + } + + for (i = 0; i < smi->num_ports; i++) { + virq = irq_create_mapping(smi->irqdomain, i); + if (!virq) { + dev_err(smi->dev, + "failed to create irq domain mapping\n"); + ret = -EINVAL; + goto out_remove_irqdomain; + } + + irq_set_parent(virq, irq); + } + + /* Configure chip interrupt signal polarity */ + irq_trig = irqd_get_trigger_type(irq_get_irq_data(irq)); + switch (irq_trig) { + case IRQF_TRIGGER_RISING: + case IRQF_TRIGGER_HIGH: + val = RTL8365MB_INTR_POLARITY_HIGH; + break; + case IRQF_TRIGGER_FALLING: + case IRQF_TRIGGER_LOW: + val = RTL8365MB_INTR_POLARITY_LOW; + break; + default: + dev_err(smi->dev, "unsupported irq trigger type %u\n", + irq_trig); + ret = -EINVAL; + goto out_remove_irqdomain; + } + + ret = regmap_update_bits(smi->map, RTL8365MB_INTR_POLARITY_REG, + RTL8365MB_INTR_POLARITY_MASK, + FIELD_PREP(RTL8365MB_INTR_POLARITY_MASK, val)); + if (ret) + goto out_remove_irqdomain; + + /* Disable the interrupt in case the chip has it enabled on reset */ + ret = rtl8365mb_irq_disable(smi); + if (ret) + goto out_remove_irqdomain; + + /* Clear the interrupt status register */ + ret = regmap_write(smi->map, RTL8365MB_INTR_STATUS_REG, + RTL8365MB_INTR_ALL_MASK); + if (ret) + goto out_remove_irqdomain; + + ret = request_threaded_irq(irq, NULL, rtl8365mb_irq, IRQF_ONESHOT, + "rtl8365mb", smi); + if (ret) { + dev_err(smi->dev, "failed to request irq: %d\n", ret); + goto out_remove_irqdomain; + } + + /* Store the irq so that we know to free it during teardown */ + mb->irq = irq; + + ret = rtl8365mb_irq_enable(smi); + if (ret) + goto out_free_irq; + + of_node_put(intc); + + return 0; + +out_free_irq: + free_irq(mb->irq, smi); + mb->irq = 0; + +out_remove_irqdomain: + for (i = 0; i < smi->num_ports; i++) { + virq = irq_find_mapping(smi->irqdomain, i); + irq_dispose_mapping(virq); + } + + irq_domain_remove(smi->irqdomain); + smi->irqdomain = NULL; + +out_put_node: + of_node_put(intc); + + return ret; +} + +static void rtl8365mb_irq_teardown(struct realtek_smi *smi) +{ + struct rtl8365mb *mb = smi->chip_data; + int virq; + int i; + + if (mb->irq) { + free_irq(mb->irq, smi); + mb->irq = 0; + } + + if (smi->irqdomain) { + for (i = 0; i < smi->num_ports; i++) { + virq = irq_find_mapping(smi->irqdomain, i); + irq_dispose_mapping(virq); + } + + irq_domain_remove(smi->irqdomain); + smi->irqdomain = NULL; + } +} + +static int rtl8365mb_cpu_config(struct realtek_smi *smi) +{ + struct rtl8365mb *mb = smi->chip_data; + struct rtl8365mb_cpu *cpu = &mb->cpu; + u32 val; + int ret; + + ret = regmap_update_bits(smi->map, RTL8365MB_CPU_PORT_MASK_REG, + RTL8365MB_CPU_PORT_MASK_MASK, + FIELD_PREP(RTL8365MB_CPU_PORT_MASK_MASK, + cpu->mask)); + if (ret) + return ret; + + val = FIELD_PREP(RTL8365MB_CPU_CTRL_EN_MASK, cpu->enable ? 1 : 0) | + FIELD_PREP(RTL8365MB_CPU_CTRL_INSERTMODE_MASK, cpu->insert) | + FIELD_PREP(RTL8365MB_CPU_CTRL_TAG_POSITION_MASK, cpu->position) | + FIELD_PREP(RTL8365MB_CPU_CTRL_RXBYTECOUNT_MASK, cpu->rx_length) | + FIELD_PREP(RTL8365MB_CPU_CTRL_TAG_FORMAT_MASK, cpu->format) | + FIELD_PREP(RTL8365MB_CPU_CTRL_TRAP_PORT_MASK, cpu->trap_port) | + FIELD_PREP(RTL8365MB_CPU_CTRL_TRAP_PORT_EXT_MASK, + cpu->trap_port >> 3); + ret = regmap_write(smi->map, RTL8365MB_CPU_CTRL_REG, val); + if (ret) + return ret; + + return 0; +} + +static int rtl8365mb_switch_init(struct realtek_smi *smi) +{ + struct rtl8365mb *mb = smi->chip_data; + int ret; + int i; + + /* Do any chip-specific init jam before getting to the common stuff */ + if (mb->jam_table) { + for (i = 0; i < mb->jam_size; i++) { + ret = regmap_write(smi->map, mb->jam_table[i].reg, + mb->jam_table[i].val); + if (ret) + return ret; + } + } + + /* Common init jam */ + for (i = 0; i < ARRAY_SIZE(rtl8365mb_init_jam_common); i++) { + ret = regmap_write(smi->map, rtl8365mb_init_jam_common[i].reg, + rtl8365mb_init_jam_common[i].val); + if (ret) + return ret; + } + + return 0; +} + +static int rtl8365mb_reset_chip(struct realtek_smi *smi) +{ + u32 val; + + realtek_smi_write_reg_noack(smi, RTL8365MB_CHIP_RESET_REG, + FIELD_PREP(RTL8365MB_CHIP_RESET_HW_MASK, + 1)); + + /* Realtek documentation says the chip needs 1 second to reset. Sleep + * for 100 ms before accessing any registers to prevent ACK timeouts. + */ + msleep(100); + return regmap_read_poll_timeout(smi->map, RTL8365MB_CHIP_RESET_REG, val, + !(val & RTL8365MB_CHIP_RESET_HW_MASK), + 20000, 1e6); +} + +static int rtl8365mb_setup(struct dsa_switch *ds) +{ + struct realtek_smi *smi = ds->priv; + struct rtl8365mb *mb; + int ret; + int i; + + mb = smi->chip_data; + + ret = rtl8365mb_reset_chip(smi); + if (ret) { + dev_err(smi->dev, "failed to reset chip: %d\n", ret); + goto out_error; + } + + /* Configure switch to vendor-defined initial state */ + ret = rtl8365mb_switch_init(smi); + if (ret) { + dev_err(smi->dev, "failed to initialize switch: %d\n", ret); + goto out_error; + } + + /* Set up cascading IRQs */ + ret = rtl8365mb_irq_setup(smi); + if (ret == -EPROBE_DEFER) + return ret; + else if (ret) + dev_info(smi->dev, "no interrupt support\n"); + + /* Configure CPU tagging */ + ret = rtl8365mb_cpu_config(smi); + if (ret) + goto out_teardown_irq; + + /* Configure ports */ + for (i = 0; i < smi->num_ports; i++) { + struct rtl8365mb_port *p = &mb->ports[i]; + + if (dsa_is_unused_port(smi->ds, i)) + continue; + + /* Set up per-port private data */ + p->smi = smi; + p->index = i; + + /* Forward only to the CPU */ + ret = rtl8365mb_port_set_isolation(smi, i, BIT(smi->cpu_port)); + if (ret) + goto out_teardown_irq; + + /* Disable learning */ + ret = rtl8365mb_port_set_learning(smi, i, false); + if (ret) + goto out_teardown_irq; + + /* Set the initial STP state of all ports to DISABLED, otherwise + * ports will still forward frames to the CPU despite being + * administratively down by default. + */ + rtl8365mb_port_stp_state_set(smi->ds, i, BR_STATE_DISABLED); + } + + /* Set maximum packet length to 1536 bytes */ + ret = regmap_update_bits(smi->map, RTL8365MB_CFG0_MAX_LEN_REG, + RTL8365MB_CFG0_MAX_LEN_MASK, + FIELD_PREP(RTL8365MB_CFG0_MAX_LEN_MASK, 1536)); + if (ret) + goto out_teardown_irq; + + ret = realtek_smi_setup_mdio(smi); + if (ret) { + dev_err(smi->dev, "could not set up MDIO bus\n"); + goto out_teardown_irq; + } + + /* Start statistics counter polling */ + rtl8365mb_stats_setup(smi); + + return 0; + +out_teardown_irq: + rtl8365mb_irq_teardown(smi); + +out_error: + return ret; +} + +static void rtl8365mb_teardown(struct dsa_switch *ds) +{ + struct realtek_smi *smi = ds->priv; + + rtl8365mb_stats_teardown(smi); + rtl8365mb_irq_teardown(smi); +} + +static int rtl8365mb_get_chip_id_and_ver(struct regmap *map, u32 *id, u32 *ver) +{ + int ret; + + /* For some reason we have to write a magic value to an arbitrary + * register whenever accessing the chip ID/version registers. + */ + ret = regmap_write(map, RTL8365MB_MAGIC_REG, RTL8365MB_MAGIC_VALUE); + if (ret) + return ret; + + ret = regmap_read(map, RTL8365MB_CHIP_ID_REG, id); + if (ret) + return ret; + + ret = regmap_read(map, RTL8365MB_CHIP_VER_REG, ver); + if (ret) + return ret; + + /* Reset magic register */ + ret = regmap_write(map, RTL8365MB_MAGIC_REG, 0); + if (ret) + return ret; + + return 0; +} + +static int rtl8365mb_detect(struct realtek_smi *smi) +{ + struct rtl8365mb *mb = smi->chip_data; + u32 chip_id; + u32 chip_ver; + int ret; + + ret = rtl8365mb_get_chip_id_and_ver(smi->map, &chip_id, &chip_ver); + if (ret) { + dev_err(smi->dev, "failed to read chip id and version: %d\n", + ret); + return ret; + } + + switch (chip_id) { + case RTL8365MB_CHIP_ID_8365MB_VC: + dev_info(smi->dev, + "found an RTL8365MB-VC switch (ver=0x%04x)\n", + chip_ver); + + smi->cpu_port = RTL8365MB_CPU_PORT_NUM_8365MB_VC; + smi->num_ports = smi->cpu_port + 1; + + mb->smi = smi; + mb->chip_id = chip_id; + mb->chip_ver = chip_ver; + mb->port_mask = BIT(smi->num_ports) - 1; + mb->learn_limit_max = RTL8365MB_LEARN_LIMIT_MAX_8365MB_VC; + mb->jam_table = rtl8365mb_init_jam_8365mb_vc; + mb->jam_size = ARRAY_SIZE(rtl8365mb_init_jam_8365mb_vc); + + mb->cpu.enable = 1; + mb->cpu.mask = BIT(smi->cpu_port); + mb->cpu.trap_port = smi->cpu_port; + mb->cpu.insert = RTL8365MB_CPU_INSERT_TO_ALL; + mb->cpu.position = RTL8365MB_CPU_POS_AFTER_SA; + mb->cpu.rx_length = RTL8365MB_CPU_RXLEN_64BYTES; + mb->cpu.format = RTL8365MB_CPU_FORMAT_8BYTES; + + break; + default: + dev_err(smi->dev, + "found an unknown Realtek switch (id=0x%04x, ver=0x%04x)\n", + chip_id, chip_ver); + return -ENODEV; + } + + return 0; +} + +static const struct dsa_switch_ops rtl8365mb_switch_ops = { + .get_tag_protocol = rtl8365mb_get_tag_protocol, + .setup = rtl8365mb_setup, + .teardown = rtl8365mb_teardown, + .phylink_validate = rtl8365mb_phylink_validate, + .phylink_mac_config = rtl8365mb_phylink_mac_config, + .phylink_mac_link_down = rtl8365mb_phylink_mac_link_down, + .phylink_mac_link_up = rtl8365mb_phylink_mac_link_up, + .port_stp_state_set = rtl8365mb_port_stp_state_set, + .get_strings = rtl8365mb_get_strings, + .get_ethtool_stats = rtl8365mb_get_ethtool_stats, + .get_sset_count = rtl8365mb_get_sset_count, + .get_eth_phy_stats = rtl8365mb_get_phy_stats, + .get_eth_mac_stats = rtl8365mb_get_mac_stats, + .get_eth_ctrl_stats = rtl8365mb_get_ctrl_stats, + .get_stats64 = rtl8365mb_get_stats64, +}; + +static const struct realtek_smi_ops rtl8365mb_smi_ops = { + .detect = rtl8365mb_detect, + .phy_read = rtl8365mb_phy_read, + .phy_write = rtl8365mb_phy_write, +}; + +const struct realtek_smi_variant rtl8365mb_variant = { + .ds_ops = &rtl8365mb_switch_ops, + .ops = &rtl8365mb_smi_ops, + .clk_delay = 10, + .cmd_read = 0xb9, + .cmd_write = 0xb8, + .chip_data_sz = sizeof(struct rtl8365mb), +}; +EXPORT_SYMBOL_GPL(rtl8365mb_variant); diff --git a/drivers/net/dsa/rtl8366rb.c b/drivers/net/dsa/rtl8366rb.c index d2370cda4be0..03deacd83e61 100644 --- a/drivers/net/dsa/rtl8366rb.c +++ b/drivers/net/dsa/rtl8366rb.c @@ -1345,7 +1345,7 @@ rtl8366rb_port_stp_state_set(struct dsa_switch *ds, int port, u8 state) default: dev_err(smi->dev, "unknown bridge state requested\n"); return; - }; + } /* Set the same status for the port on all the FIDs */ for (i = 0; i < RTL8366RB_NUM_FIDS; i++) { diff --git a/drivers/net/dsa/sja1105/sja1105.h b/drivers/net/dsa/sja1105/sja1105.h index 618c8d6a8be1..808419f3b808 100644 --- a/drivers/net/dsa/sja1105/sja1105.h +++ b/drivers/net/dsa/sja1105/sja1105.h @@ -20,6 +20,27 @@ #define SJA1105_AGEING_TIME_MS(ms) ((ms) / 10) #define SJA1105_NUM_L2_POLICERS SJA1110_MAX_L2_POLICING_COUNT +/* Calculated assuming 1Gbps, where the clock has 125 MHz (8 ns period) + * To avoid floating point operations, we'll multiply the degrees by 10 + * to get a "phase" and get 1 decimal point precision. + */ +#define SJA1105_RGMII_DELAY_PS_TO_PHASE(ps) \ + (((ps) * 360) / 800) +#define SJA1105_RGMII_DELAY_PHASE_TO_PS(phase) \ + ((800 * (phase)) / 360) +#define SJA1105_RGMII_DELAY_PHASE_TO_HW(phase) \ + (((phase) - 738) / 9) +#define SJA1105_RGMII_DELAY_PS_TO_HW(ps) \ + SJA1105_RGMII_DELAY_PHASE_TO_HW(SJA1105_RGMII_DELAY_PS_TO_PHASE(ps)) + +/* Valid range in degrees is a value between 73.8 and 101.7 + * in 0.9 degree increments + */ +#define SJA1105_RGMII_DELAY_MIN_PS \ + SJA1105_RGMII_DELAY_PHASE_TO_PS(738) +#define SJA1105_RGMII_DELAY_MAX_PS \ + SJA1105_RGMII_DELAY_PHASE_TO_PS(1017) + typedef enum { SPI_READ = 0, SPI_WRITE = 1, @@ -222,8 +243,8 @@ struct sja1105_flow_block { struct sja1105_private { struct sja1105_static_config static_config; - bool rgmii_rx_delay[SJA1105_MAX_NUM_PORTS]; - bool rgmii_tx_delay[SJA1105_MAX_NUM_PORTS]; + int rgmii_rx_delay_ps[SJA1105_MAX_NUM_PORTS]; + int rgmii_tx_delay_ps[SJA1105_MAX_NUM_PORTS]; phy_interface_t phy_mode[SJA1105_MAX_NUM_PORTS]; bool fixed_link[SJA1105_MAX_NUM_PORTS]; unsigned long ucast_egress_floods; diff --git a/drivers/net/dsa/sja1105/sja1105_clocking.c b/drivers/net/dsa/sja1105/sja1105_clocking.c index 5bbf1707f2af..e3699f76f6d7 100644 --- a/drivers/net/dsa/sja1105/sja1105_clocking.c +++ b/drivers/net/dsa/sja1105/sja1105_clocking.c @@ -498,17 +498,6 @@ sja1110_cfg_pad_mii_id_packing(void *buf, struct sja1105_cfg_pad_mii_id *cmd, sja1105_packing(buf, &cmd->txc_pd, 0, 0, size, op); } -/* Valid range in degrees is an integer between 73.8 and 101.7 */ -static u64 sja1105_rgmii_delay(u64 phase) -{ - /* UM11040.pdf: The delay in degree phase is 73.8 + delay_tune * 0.9. - * To avoid floating point operations we'll multiply by 10 - * and get 1 decimal point precision. - */ - phase *= 10; - return (phase - 738) / 9; -} - /* The RGMII delay setup procedure is 2-step and gets called upon each * .phylink_mac_config. Both are strategic. * The reason is that the RX Tunable Delay Line of the SJA1105 MAC has issues @@ -521,13 +510,15 @@ int sja1105pqrs_setup_rgmii_delay(const void *ctx, int port) const struct sja1105_private *priv = ctx; const struct sja1105_regs *regs = priv->info->regs; struct sja1105_cfg_pad_mii_id pad_mii_id = {0}; + int rx_delay = priv->rgmii_rx_delay_ps[port]; + int tx_delay = priv->rgmii_tx_delay_ps[port]; u8 packed_buf[SJA1105_SIZE_CGU_CMD] = {0}; int rc; - if (priv->rgmii_rx_delay[port]) - pad_mii_id.rxc_delay = sja1105_rgmii_delay(90); - if (priv->rgmii_tx_delay[port]) - pad_mii_id.txc_delay = sja1105_rgmii_delay(90); + if (rx_delay) + pad_mii_id.rxc_delay = SJA1105_RGMII_DELAY_PS_TO_HW(rx_delay); + if (tx_delay) + pad_mii_id.txc_delay = SJA1105_RGMII_DELAY_PS_TO_HW(tx_delay); /* Stage 1: Turn the RGMII delay lines off. */ pad_mii_id.rxc_bypass = 1; @@ -542,11 +533,11 @@ int sja1105pqrs_setup_rgmii_delay(const void *ctx, int port) return rc; /* Stage 2: Turn the RGMII delay lines on. */ - if (priv->rgmii_rx_delay[port]) { + if (rx_delay) { pad_mii_id.rxc_bypass = 0; pad_mii_id.rxc_pd = 0; } - if (priv->rgmii_tx_delay[port]) { + if (tx_delay) { pad_mii_id.txc_bypass = 0; pad_mii_id.txc_pd = 0; } @@ -561,20 +552,22 @@ int sja1110_setup_rgmii_delay(const void *ctx, int port) const struct sja1105_private *priv = ctx; const struct sja1105_regs *regs = priv->info->regs; struct sja1105_cfg_pad_mii_id pad_mii_id = {0}; + int rx_delay = priv->rgmii_rx_delay_ps[port]; + int tx_delay = priv->rgmii_tx_delay_ps[port]; u8 packed_buf[SJA1105_SIZE_CGU_CMD] = {0}; pad_mii_id.rxc_pd = 1; pad_mii_id.txc_pd = 1; - if (priv->rgmii_rx_delay[port]) { - pad_mii_id.rxc_delay = sja1105_rgmii_delay(90); + if (rx_delay) { + pad_mii_id.rxc_delay = SJA1105_RGMII_DELAY_PS_TO_HW(rx_delay); /* The "BYPASS" bit in SJA1110 is actually a "don't bypass" */ pad_mii_id.rxc_bypass = 1; pad_mii_id.rxc_pd = 0; } - if (priv->rgmii_tx_delay[port]) { - pad_mii_id.txc_delay = sja1105_rgmii_delay(90); + if (tx_delay) { + pad_mii_id.txc_delay = SJA1105_RGMII_DELAY_PS_TO_HW(tx_delay); pad_mii_id.txc_bypass = 1; pad_mii_id.txc_pd = 0; } diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index 0f1bba0076a8..1832d4bd3440 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -1109,27 +1109,78 @@ static int sja1105_static_config_load(struct sja1105_private *priv) return sja1105_static_config_upload(priv); } -static int sja1105_parse_rgmii_delays(struct sja1105_private *priv) +/* This is the "new way" for a MAC driver to configure its RGMII delay lines, + * based on the explicit "rx-internal-delay-ps" and "tx-internal-delay-ps" + * properties. It has the advantage of working with fixed links and with PHYs + * that apply RGMII delays too, and the MAC driver needs not perform any + * special checks. + * + * Previously we were acting upon the "phy-mode" property when we were + * operating in fixed-link, basically acting as a PHY, but with a reversed + * interpretation: PHY_INTERFACE_MODE_RGMII_TXID means that the MAC should + * behave as if it is connected to a PHY which has applied RGMII delays in the + * TX direction. So if anything, RX delays should have been added by the MAC, + * but we were adding TX delays. + * + * If the "{rx,tx}-internal-delay-ps" properties are not specified, we fall + * back to the legacy behavior and apply delays on fixed-link ports based on + * the reverse interpretation of the phy-mode. This is a deviation from the + * expected default behavior which is to simply apply no delays. To achieve + * that behavior with the new bindings, it is mandatory to specify + * "{rx,tx}-internal-delay-ps" with a value of 0. + */ +static int sja1105_parse_rgmii_delays(struct sja1105_private *priv, int port, + struct device_node *port_dn) { - struct dsa_switch *ds = priv->ds; - int port; + phy_interface_t phy_mode = priv->phy_mode[port]; + struct device *dev = &priv->spidev->dev; + int rx_delay = -1, tx_delay = -1; - for (port = 0; port < ds->num_ports; port++) { - if (!priv->fixed_link[port]) - continue; + if (!phy_interface_mode_is_rgmii(phy_mode)) + return 0; - if (priv->phy_mode[port] == PHY_INTERFACE_MODE_RGMII_RXID || - priv->phy_mode[port] == PHY_INTERFACE_MODE_RGMII_ID) - priv->rgmii_rx_delay[port] = true; + of_property_read_u32(port_dn, "rx-internal-delay-ps", &rx_delay); + of_property_read_u32(port_dn, "tx-internal-delay-ps", &tx_delay); - if (priv->phy_mode[port] == PHY_INTERFACE_MODE_RGMII_TXID || - priv->phy_mode[port] == PHY_INTERFACE_MODE_RGMII_ID) - priv->rgmii_tx_delay[port] = true; + if (rx_delay == -1 && tx_delay == -1 && priv->fixed_link[port]) { + dev_warn(dev, + "Port %d interpreting RGMII delay settings based on \"phy-mode\" property, " + "please update device tree to specify \"rx-internal-delay-ps\" and " + "\"tx-internal-delay-ps\"", + port); - if ((priv->rgmii_rx_delay[port] || priv->rgmii_tx_delay[port]) && - !priv->info->setup_rgmii_delay) - return -EINVAL; + if (phy_mode == PHY_INTERFACE_MODE_RGMII_RXID || + phy_mode == PHY_INTERFACE_MODE_RGMII_ID) + rx_delay = 2000; + + if (phy_mode == PHY_INTERFACE_MODE_RGMII_TXID || + phy_mode == PHY_INTERFACE_MODE_RGMII_ID) + tx_delay = 2000; } + + if (rx_delay < 0) + rx_delay = 0; + if (tx_delay < 0) + tx_delay = 0; + + if ((rx_delay || tx_delay) && !priv->info->setup_rgmii_delay) { + dev_err(dev, "Chip cannot apply RGMII delays\n"); + return -EINVAL; + } + + if ((rx_delay && rx_delay < SJA1105_RGMII_DELAY_MIN_PS) || + (tx_delay && tx_delay < SJA1105_RGMII_DELAY_MIN_PS) || + (rx_delay > SJA1105_RGMII_DELAY_MAX_PS) || + (tx_delay > SJA1105_RGMII_DELAY_MAX_PS)) { + dev_err(dev, + "port %d RGMII delay values out of range, must be between %d and %d ps\n", + port, SJA1105_RGMII_DELAY_MIN_PS, SJA1105_RGMII_DELAY_MAX_PS); + return -ERANGE; + } + + priv->rgmii_rx_delay_ps[port] = rx_delay; + priv->rgmii_tx_delay_ps[port] = tx_delay; + return 0; } @@ -1180,6 +1231,10 @@ static int sja1105_parse_ports_node(struct sja1105_private *priv, } priv->phy_mode[index] = phy_mode; + + err = sja1105_parse_rgmii_delays(priv, index, child); + if (err) + return err; } return 0; @@ -3317,15 +3372,6 @@ static int sja1105_probe(struct spi_device *spi) return rc; } - /* Error out early if internal delays are required through DT - * and we can't apply them. - */ - rc = sja1105_parse_rgmii_delays(priv); - if (rc < 0) { - dev_err(ds->dev, "RGMII delay not supported\n"); - return rc; - } - if (IS_ENABLED(CONFIG_NET_SCH_CBS)) { priv->cbs = devm_kcalloc(dev, priv->info->num_cbs_shapers, sizeof(struct sja1105_cbs_entry), diff --git a/drivers/net/dsa/sja1105/sja1105_vl.c b/drivers/net/dsa/sja1105/sja1105_vl.c index d55572994e1f..f5dca6a9b0f9 100644 --- a/drivers/net/dsa/sja1105/sja1105_vl.c +++ b/drivers/net/dsa/sja1105/sja1105_vl.c @@ -394,7 +394,8 @@ static int sja1105_init_virtual_links(struct sja1105_private *priv, vl_lookup[k].vlanid = rule->key.vl.vid; vl_lookup[k].vlanprior = rule->key.vl.pcp; } else { - u16 vid = dsa_8021q_rx_vid(priv->ds, port); + struct dsa_port *dp = dsa_to_port(priv->ds, port); + u16 vid = dsa_tag_8021q_rx_vid(dp); vl_lookup[k].vlanid = vid; vl_lookup[k].vlanprior = 0; diff --git a/drivers/net/ethernet/3com/3c515.c b/drivers/net/ethernet/3com/3c515.c index 6f0ea2facea9..1d124b0f65e7 100644 --- a/drivers/net/ethernet/3com/3c515.c +++ b/drivers/net/ethernet/3com/3c515.c @@ -567,6 +567,7 @@ static int corkscrew_setup(struct net_device *dev, int ioaddr, { struct corkscrew_private *vp = netdev_priv(dev); unsigned int eeprom[0x40], checksum = 0; /* EEPROM contents */ + __be16 addr[ETH_ALEN / 2]; int i; int irq; @@ -619,7 +620,6 @@ static int corkscrew_setup(struct net_device *dev, int ioaddr, /* Read the station address from the EEPROM. */ EL3WINDOW(0); for (i = 0; i < 0x18; i++) { - __be16 *phys_addr = (__be16 *) dev->dev_addr; int timer; outw(EEPROM_Read + i, ioaddr + Wn0EepromCmd); /* Pause for at least 162 us. for the read to take place. */ @@ -631,8 +631,9 @@ static int corkscrew_setup(struct net_device *dev, int ioaddr, eeprom[i] = inw(ioaddr + Wn0EepromData); checksum ^= eeprom[i]; if (i < 3) - phys_addr[i] = htons(eeprom[i]); + addr[i] = htons(eeprom[i]); } + eth_hw_addr_set(dev, (u8 *)addr); checksum = (checksum ^ (checksum >> 8)) & 0xff; if (checksum != 0x00) pr_cont(" ***INVALID CHECKSUM %4.4x*** ", checksum); diff --git a/drivers/net/ethernet/3com/3c574_cs.c b/drivers/net/ethernet/3com/3c574_cs.c index dd4d3c48b98d..dc3b7c960611 100644 --- a/drivers/net/ethernet/3com/3c574_cs.c +++ b/drivers/net/ethernet/3com/3c574_cs.c @@ -305,15 +305,13 @@ static int tc574_config(struct pcmcia_device *link) struct net_device *dev = link->priv; struct el3_private *lp = netdev_priv(dev); int ret, i, j; + __be16 addr[ETH_ALEN / 2]; unsigned int ioaddr; - __be16 *phys_addr; char *cardname; __u32 config; u8 *buf; size_t len; - phys_addr = (__be16 *)dev->dev_addr; - dev_dbg(&link->dev, "3c574_config()\n"); link->io_lines = 16; @@ -347,19 +345,20 @@ static int tc574_config(struct pcmcia_device *link) len = pcmcia_get_tuple(link, 0x88, &buf); if (buf && len >= 6) { for (i = 0; i < 3; i++) - phys_addr[i] = htons(le16_to_cpu(buf[i * 2])); + addr[i] = htons(le16_to_cpu(buf[i * 2])); kfree(buf); } else { kfree(buf); /* 0 < len < 6 */ EL3WINDOW(0); for (i = 0; i < 3; i++) - phys_addr[i] = htons(read_eeprom(ioaddr, i + 10)); - if (phys_addr[0] == htons(0x6060)) { + addr[i] = htons(read_eeprom(ioaddr, i + 10)); + if (addr[0] == htons(0x6060)) { pr_notice("IO port conflict at 0x%03lx-0x%03lx\n", dev->base_addr, dev->base_addr+15); goto failed; } } + eth_hw_addr_set(dev, (u8 *)addr); if (link->prod_id[1]) cardname = link->prod_id[1]; else diff --git a/drivers/net/ethernet/3com/3c589_cs.c b/drivers/net/ethernet/3com/3c589_cs.c index 09816e84314d..4673bc1604e7 100644 --- a/drivers/net/ethernet/3com/3c589_cs.c +++ b/drivers/net/ethernet/3com/3c589_cs.c @@ -237,8 +237,8 @@ static void tc589_detach(struct pcmcia_device *link) static int tc589_config(struct pcmcia_device *link) { struct net_device *dev = link->priv; - __be16 *phys_addr; int ret, i, j, multi = 0, fifo; + __be16 addr[ETH_ALEN / 2]; unsigned int ioaddr; static const char * const ram_split[] = {"5:3", "3:1", "1:1", "3:5"}; u8 *buf; @@ -246,7 +246,6 @@ static int tc589_config(struct pcmcia_device *link) dev_dbg(&link->dev, "3c589_config\n"); - phys_addr = (__be16 *)dev->dev_addr; /* Is this a 3c562? */ if (link->manf_id != MANFID_3COM) dev_info(&link->dev, "hmmm, is this really a 3Com card??\n"); @@ -285,18 +284,19 @@ static int tc589_config(struct pcmcia_device *link) len = pcmcia_get_tuple(link, 0x88, &buf); if (buf && len >= 6) { for (i = 0; i < 3; i++) - phys_addr[i] = htons(le16_to_cpu(buf[i*2])); + addr[i] = htons(le16_to_cpu(buf[i*2])); kfree(buf); } else { kfree(buf); /* 0 < len < 6 */ for (i = 0; i < 3; i++) - phys_addr[i] = htons(read_eeprom(ioaddr, i)); - if (phys_addr[0] == htons(0x6060)) { + addr[i] = htons(read_eeprom(ioaddr, i)); + if (addr[0] == htons(0x6060)) { dev_err(&link->dev, "IO port conflict at 0x%03lx-0x%03lx\n", dev->base_addr, dev->base_addr+15); goto failed; } } + eth_hw_addr_set(dev, (u8 *)addr); /* The address and resource configuration register aren't loaded from * the EEPROM and *must* be set to 0 and IRQ3 for the PCMCIA version. diff --git a/drivers/net/ethernet/3com/3c59x.c b/drivers/net/ethernet/3com/3c59x.c index 7b0ae9efc004..ccf07667aa5e 100644 --- a/drivers/net/ethernet/3com/3c59x.c +++ b/drivers/net/ethernet/3com/3c59x.c @@ -1091,6 +1091,7 @@ static int vortex_probe1(struct device *gendev, void __iomem *ioaddr, int irq, struct vortex_private *vp; int option; unsigned int eeprom[0x40], checksum = 0; /* EEPROM contents */ + __be16 addr[ETH_ALEN / 2]; int i, step; struct net_device *dev; static int printed_version; @@ -1284,7 +1285,8 @@ static int vortex_probe1(struct device *gendev, void __iomem *ioaddr, int irq, if ((checksum != 0x00) && !(vci->drv_flags & IS_TORNADO)) pr_cont(" ***INVALID CHECKSUM %4.4x*** ", checksum); for (i = 0; i < 3; i++) - ((__be16 *)dev->dev_addr)[i] = htons(eeprom[i + 10]); + addr[i] = htons(eeprom[i + 10]); + eth_hw_addr_set(dev, (u8 *)addr); if (print_info) pr_cont(" %pM", dev->dev_addr); /* Unfortunately an all zero eeprom passes the checksum and this diff --git a/drivers/net/ethernet/8390/apne.c b/drivers/net/ethernet/8390/apne.c index da1ae37a9d73..991ad953aa79 100644 --- a/drivers/net/ethernet/8390/apne.c +++ b/drivers/net/ethernet/8390/apne.c @@ -320,8 +320,7 @@ static int __init apne_probe1(struct net_device *dev, int ioaddr) i = request_irq(dev->irq, apne_interrupt, IRQF_SHARED, DRV_NAME, dev); if (i) return i; - for (i = 0; i < ETH_ALEN; i++) - dev->dev_addr[i] = SA_prom[i]; + eth_hw_addr_set(dev, SA_prom); pr_cont(" %pM\n", dev->dev_addr); diff --git a/drivers/net/ethernet/8390/ax88796.c b/drivers/net/ethernet/8390/ax88796.c index b3e612b18abd..1f8acbba5b6b 100644 --- a/drivers/net/ethernet/8390/ax88796.c +++ b/drivers/net/ethernet/8390/ax88796.c @@ -748,11 +748,13 @@ static int ax_init_dev(struct net_device *dev) /* load the mac-address from the device */ if (ax->plat->flags & AXFLG_MAC_FROMDEV) { + u8 addr[ETH_ALEN]; + ei_outb(E8390_NODMA + E8390_PAGE1 + E8390_STOP, ei_local->mem + E8390_CMD); /* 0x61 */ for (i = 0; i < ETH_ALEN; i++) - dev->dev_addr[i] = - ei_inb(ioaddr + EN1_PHYS_SHIFT(i)); + addr[i] = ei_inb(ioaddr + EN1_PHYS_SHIFT(i)); + eth_hw_addr_set(dev, addr); } if ((ax->plat->flags & AXFLG_MAC_FROMPLATFORM) && diff --git a/drivers/net/ethernet/8390/axnet_cs.c b/drivers/net/ethernet/8390/axnet_cs.c index 3c370e686ec3..3aef959fc25b 100644 --- a/drivers/net/ethernet/8390/axnet_cs.c +++ b/drivers/net/ethernet/8390/axnet_cs.c @@ -187,6 +187,7 @@ static int get_prom(struct pcmcia_device *link) { struct net_device *dev = link->priv; unsigned int ioaddr = dev->base_addr; + u8 addr[ETH_ALEN]; int i, j; /* This is based on drivers/net/ethernet/8390/ne.c */ @@ -220,9 +221,11 @@ static int get_prom(struct pcmcia_device *link) for (i = 0; i < 6; i += 2) { j = inw(ioaddr + AXNET_DATAPORT); - dev->dev_addr[i] = j & 0xff; - dev->dev_addr[i+1] = j >> 8; + addr[i] = j & 0xff; + addr[i+1] = j >> 8; } + eth_hw_addr_set(dev, addr); + return 1; } /* get_prom */ diff --git a/drivers/net/ethernet/8390/mcf8390.c b/drivers/net/ethernet/8390/mcf8390.c index 4ad8031ab669..e320cccba61a 100644 --- a/drivers/net/ethernet/8390/mcf8390.c +++ b/drivers/net/ethernet/8390/mcf8390.c @@ -374,8 +374,7 @@ static int mcf8390_init(struct net_device *dev) if (ret) return ret; - for (i = 0; i < ETH_ALEN; i++) - dev->dev_addr[i] = SA_prom[i]; + eth_hw_addr_set(dev, SA_prom); netdev_dbg(dev, "Found ethernet address: %pM\n", dev->dev_addr); diff --git a/drivers/net/ethernet/8390/ne.c b/drivers/net/ethernet/8390/ne.c index 9afc712f5948..0a9118b8be0c 100644 --- a/drivers/net/ethernet/8390/ne.c +++ b/drivers/net/ethernet/8390/ne.c @@ -500,9 +500,7 @@ static int __init ne_probe1(struct net_device *dev, unsigned long ioaddr) dev->base_addr = ioaddr; - for (i = 0; i < ETH_ALEN; i++) { - dev->dev_addr[i] = SA_prom[i]; - } + eth_hw_addr_set(dev, SA_prom); pr_cont("%pM\n", dev->dev_addr); diff --git a/drivers/net/ethernet/8390/pcnet_cs.c b/drivers/net/ethernet/8390/pcnet_cs.c index 96ad72abd373..0f07fe03da98 100644 --- a/drivers/net/ethernet/8390/pcnet_cs.c +++ b/drivers/net/ethernet/8390/pcnet_cs.c @@ -278,6 +278,7 @@ static struct hw_info *get_hwinfo(struct pcmcia_device *link) { struct net_device *dev = link->priv; u_char __iomem *base, *virt; + u8 addr[ETH_ALEN]; int i, j; /* Allocate a small memory window */ @@ -302,7 +303,8 @@ static struct hw_info *get_hwinfo(struct pcmcia_device *link) (readb(base+2) == hw_info[i].a1) && (readb(base+4) == hw_info[i].a2)) { for (j = 0; j < 6; j++) - dev->dev_addr[j] = readb(base + (j<<1)); + addr[j] = readb(base + (j<<1)); + eth_hw_addr_set(dev, addr); break; } } @@ -324,6 +326,7 @@ static struct hw_info *get_prom(struct pcmcia_device *link) { struct net_device *dev = link->priv; unsigned int ioaddr = dev->base_addr; + u8 addr[ETH_ALEN]; u_char prom[32]; int i, j; @@ -362,7 +365,8 @@ static struct hw_info *get_prom(struct pcmcia_device *link) } if ((i < NR_INFO) || ((prom[28] == 0x57) && (prom[30] == 0x57))) { for (j = 0; j < 6; j++) - dev->dev_addr[j] = prom[j<<1]; + addr[j] = prom[j<<1]; + eth_hw_addr_set(dev, addr); return (i < NR_INFO) ? hw_info+i : &default_info; } return NULL; @@ -377,6 +381,7 @@ static struct hw_info *get_prom(struct pcmcia_device *link) static struct hw_info *get_dl10019(struct pcmcia_device *link) { struct net_device *dev = link->priv; + u8 addr[ETH_ALEN]; int i; u_char sum; @@ -385,7 +390,8 @@ static struct hw_info *get_dl10019(struct pcmcia_device *link) if (sum != 0xff) return NULL; for (i = 0; i < 6; i++) - dev->dev_addr[i] = inb_p(dev->base_addr + 0x14 + i); + addr[i] = inb_p(dev->base_addr + 0x14 + i); + eth_hw_addr_set(dev, addr); i = inb(dev->base_addr + 0x1f); return ((i == 0x91)||(i == 0x99)) ? &dl10022_info : &dl10019_info; } @@ -400,6 +406,7 @@ static struct hw_info *get_ax88190(struct pcmcia_device *link) { struct net_device *dev = link->priv; unsigned int ioaddr = dev->base_addr; + u8 addr[ETH_ALEN]; int i, j; /* Not much of a test, but the alternatives are messy */ @@ -413,9 +420,10 @@ static struct hw_info *get_ax88190(struct pcmcia_device *link) for (i = 0; i < 6; i += 2) { j = inw(ioaddr + PCNET_DATAPORT); - dev->dev_addr[i] = j & 0xff; - dev->dev_addr[i+1] = j >> 8; + addr[i] = j & 0xff; + addr[i+1] = j >> 8; } + eth_hw_addr_set(dev, addr); return NULL; } @@ -430,6 +438,7 @@ static struct hw_info *get_ax88190(struct pcmcia_device *link) static struct hw_info *get_hwired(struct pcmcia_device *link) { struct net_device *dev = link->priv; + u8 addr[ETH_ALEN]; int i; for (i = 0; i < 6; i++) @@ -438,7 +447,8 @@ static struct hw_info *get_hwired(struct pcmcia_device *link) return NULL; for (i = 0; i < 6; i++) - dev->dev_addr[i] = hw_addr[i]; + addr[i] = hw_addr[i]; + eth_hw_addr_set(dev, addr); return &default_info; } /* get_hwired */ diff --git a/drivers/net/ethernet/8390/stnic.c b/drivers/net/ethernet/8390/stnic.c index fbbd7f22c142..bd89ca8a92df 100644 --- a/drivers/net/ethernet/8390/stnic.c +++ b/drivers/net/ethernet/8390/stnic.c @@ -104,8 +104,8 @@ STNIC_WRITE (int reg, byte val) static int __init stnic_probe(void) { struct net_device *dev; - int i, err; struct ei_device *ei_local; + int err; /* If we are not running on a SolutionEngine, give up now */ if (! MACH_SE) @@ -119,8 +119,7 @@ static int __init stnic_probe(void) #ifdef CONFIG_SH_STANDARD_BIOS sh_bios_get_node_addr (stnic_eadr); #endif - for (i = 0; i < ETH_ALEN; i++) - dev->dev_addr[i] = stnic_eadr[i]; + eth_hw_addr_set(dev, stnic_eadr); /* Set the base address to point to the NIC, not the "real" base! */ dev->base_addr = 0x1000; diff --git a/drivers/net/ethernet/8390/zorro8390.c b/drivers/net/ethernet/8390/zorro8390.c index 35a500a21521..e8b4fe813a08 100644 --- a/drivers/net/ethernet/8390/zorro8390.c +++ b/drivers/net/ethernet/8390/zorro8390.c @@ -364,8 +364,7 @@ static int zorro8390_init(struct net_device *dev, unsigned long board, if (i) return i; - for (i = 0; i < ETH_ALEN; i++) - dev->dev_addr[i] = SA_prom[i]; + eth_hw_addr_set(dev, SA_prom); pr_debug("Found ethernet address: %pM\n", dev->dev_addr); diff --git a/drivers/net/ethernet/Kconfig b/drivers/net/ethernet/Kconfig index 412ae3e43ffb..4601b38f532a 100644 --- a/drivers/net/ethernet/Kconfig +++ b/drivers/net/ethernet/Kconfig @@ -33,6 +33,7 @@ source "drivers/net/ethernet/apm/Kconfig" source "drivers/net/ethernet/apple/Kconfig" source "drivers/net/ethernet/aquantia/Kconfig" source "drivers/net/ethernet/arc/Kconfig" +source "drivers/net/ethernet/asix/Kconfig" source "drivers/net/ethernet/atheros/Kconfig" source "drivers/net/ethernet/broadcom/Kconfig" source "drivers/net/ethernet/brocade/Kconfig" diff --git a/drivers/net/ethernet/Makefile b/drivers/net/ethernet/Makefile index aaa5078cd7d1..fdd8c6c17451 100644 --- a/drivers/net/ethernet/Makefile +++ b/drivers/net/ethernet/Makefile @@ -19,6 +19,7 @@ obj-$(CONFIG_NET_XGENE) += apm/ obj-$(CONFIG_NET_VENDOR_APPLE) += apple/ obj-$(CONFIG_NET_VENDOR_AQUANTIA) += aquantia/ obj-$(CONFIG_NET_VENDOR_ARC) += arc/ +obj-$(CONFIG_NET_VENDOR_ASIX) += asix/ obj-$(CONFIG_NET_VENDOR_ATHEROS) += atheros/ obj-$(CONFIG_NET_VENDOR_CADENCE) += cadence/ obj-$(CONFIG_NET_VENDOR_BROADCOM) += broadcom/ diff --git a/drivers/net/ethernet/actions/owl-emac.c b/drivers/net/ethernet/actions/owl-emac.c index 2c25ff3623cd..1cfdd01b4c2e 100644 --- a/drivers/net/ethernet/actions/owl-emac.c +++ b/drivers/net/ethernet/actions/owl-emac.c @@ -342,7 +342,7 @@ static u32 owl_emac_dma_cmd_stop(struct owl_emac_priv *priv) static void owl_emac_set_hw_mac_addr(struct net_device *netdev) { struct owl_emac_priv *priv = netdev_priv(netdev); - u8 *mac_addr = netdev->dev_addr; + const u8 *mac_addr = netdev->dev_addr; u32 addr_high, addr_low; addr_high = mac_addr[0] << 8 | mac_addr[1]; @@ -1385,7 +1385,7 @@ static void owl_emac_get_mac_addr(struct net_device *netdev) struct device *dev = netdev->dev.parent; int ret; - ret = eth_platform_get_mac_address(dev, netdev->dev_addr); + ret = platform_get_ethdev_address(dev, netdev); if (!ret && is_valid_ether_addr(netdev->dev_addr)) return; diff --git a/drivers/net/ethernet/adaptec/starfire.c b/drivers/net/ethernet/adaptec/starfire.c index e0f6cc910bd2..c6982f7caf9b 100644 --- a/drivers/net/ethernet/adaptec/starfire.c +++ b/drivers/net/ethernet/adaptec/starfire.c @@ -641,6 +641,7 @@ static int starfire_init_one(struct pci_dev *pdev, struct netdev_private *np; int i, irq, chip_idx = ent->driver_data; struct net_device *dev; + u8 addr[ETH_ALEN]; long ioaddr; void __iomem *base; int drv_flags, io_size; @@ -696,7 +697,8 @@ static int starfire_init_one(struct pci_dev *pdev, /* Serial EEPROM reads are hidden by the hardware. */ for (i = 0; i < 6; i++) - dev->dev_addr[i] = readb(base + EEPROMCtrl + 20 - i); + addr[i] = readb(base + EEPROMCtrl + 20 - i); + eth_hw_addr_set(dev, addr); #if ! defined(final_version) /* Dump the EEPROM contents during development. */ if (debug > 4) @@ -955,7 +957,7 @@ static int netdev_open(struct net_device *dev) writew(0, ioaddr + PerfFilterTable + 4); writew(0, ioaddr + PerfFilterTable + 8); for (i = 1; i < 16; i++) { - __be16 *eaddrs = (__be16 *)dev->dev_addr; + const __be16 *eaddrs = (const __be16 *)dev->dev_addr; void __iomem *setup_frm = ioaddr + PerfFilterTable + i * 16; writew(be16_to_cpu(eaddrs[2]), setup_frm); setup_frm += 4; writew(be16_to_cpu(eaddrs[1]), setup_frm); setup_frm += 4; @@ -1787,14 +1789,14 @@ static void set_rx_mode(struct net_device *dev) } else if (netdev_mc_count(dev) <= 14) { /* Use the 16 element perfect filter, skip first two entries. */ void __iomem *filter_addr = ioaddr + PerfFilterTable + 2 * 16; - __be16 *eaddrs; + const __be16 *eaddrs; netdev_for_each_mc_addr(ha, dev) { eaddrs = (__be16 *) ha->addr; writew(be16_to_cpu(eaddrs[2]), filter_addr); filter_addr += 4; writew(be16_to_cpu(eaddrs[1]), filter_addr); filter_addr += 4; writew(be16_to_cpu(eaddrs[0]), filter_addr); filter_addr += 8; } - eaddrs = (__be16 *)dev->dev_addr; + eaddrs = (const __be16 *)dev->dev_addr; i = netdev_mc_count(dev) + 2; while (i++ < 16) { writew(be16_to_cpu(eaddrs[0]), filter_addr); filter_addr += 4; @@ -1805,7 +1807,7 @@ static void set_rx_mode(struct net_device *dev) } else { /* Must use a multicast hash table. */ void __iomem *filter_addr; - __be16 *eaddrs; + const __be16 *eaddrs; __le16 mc_filter[32] __attribute__ ((aligned(sizeof(long)))); /* Multicast hash filter */ memset(mc_filter, 0, sizeof(mc_filter)); @@ -1819,7 +1821,7 @@ static void set_rx_mode(struct net_device *dev) } /* Clear the perfect filter list, skip first two entries. */ filter_addr = ioaddr + PerfFilterTable + 2 * 16; - eaddrs = (__be16 *)dev->dev_addr; + eaddrs = (const __be16 *)dev->dev_addr; for (i = 2; i < 16; i++) { writew(be16_to_cpu(eaddrs[0]), filter_addr); filter_addr += 4; writew(be16_to_cpu(eaddrs[1]), filter_addr); filter_addr += 4; diff --git a/drivers/net/ethernet/aeroflex/greth.c b/drivers/net/ethernet/aeroflex/greth.c index cc34eaf0491f..447dc64a17e5 100644 --- a/drivers/net/ethernet/aeroflex/greth.c +++ b/drivers/net/ethernet/aeroflex/greth.c @@ -1346,6 +1346,7 @@ static int greth_of_probe(struct platform_device *ofdev) int i; int err; int tmp; + u8 addr[ETH_ALEN]; unsigned long timeout; dev = alloc_etherdev(sizeof(struct greth_private)); @@ -1449,8 +1450,6 @@ static int greth_of_probe(struct platform_device *ofdev) break; } if (i == 6) { - u8 addr[ETH_ALEN]; - err = of_get_mac_address(ofdev->dev.of_node, addr); if (!err) { for (i = 0; i < 6; i++) @@ -1464,7 +1463,8 @@ static int greth_of_probe(struct platform_device *ofdev) } for (i = 0; i < 6; i++) - dev->dev_addr[i] = macaddr[i]; + addr[i] = macaddr[i]; + eth_hw_addr_set(dev, addr); macaddr[5]++; diff --git a/drivers/net/ethernet/alacritech/slicoss.c b/drivers/net/ethernet/alacritech/slicoss.c index 82f4f2608102..1fc9a1cd3ef8 100644 --- a/drivers/net/ethernet/alacritech/slicoss.c +++ b/drivers/net/ethernet/alacritech/slicoss.c @@ -1008,7 +1008,7 @@ static void slic_set_link_autoneg(struct slic_device *sdev) static void slic_set_mac_address(struct slic_device *sdev) { - u8 *addr = sdev->netdev->dev_addr; + const u8 *addr = sdev->netdev->dev_addr; u32 val; val = addr[5] | addr[4] << 8 | addr[3] << 16 | addr[2] << 24; diff --git a/drivers/net/ethernet/alteon/acenic.c b/drivers/net/ethernet/alteon/acenic.c index 7aaef593b031..732da15a3827 100644 --- a/drivers/net/ethernet/alteon/acenic.c +++ b/drivers/net/ethernet/alteon/acenic.c @@ -869,6 +869,7 @@ static int ace_init(struct net_device *dev) int board_idx, ecode = 0; short i; unsigned char cache_size; + u8 addr[ETH_ALEN]; ap = netdev_priv(dev); regs = ap->regs; @@ -988,12 +989,13 @@ static int ace_init(struct net_device *dev) writel(mac1, ®s->MacAddrHi); writel(mac2, ®s->MacAddrLo); - dev->dev_addr[0] = (mac1 >> 8) & 0xff; - dev->dev_addr[1] = mac1 & 0xff; - dev->dev_addr[2] = (mac2 >> 24) & 0xff; - dev->dev_addr[3] = (mac2 >> 16) & 0xff; - dev->dev_addr[4] = (mac2 >> 8) & 0xff; - dev->dev_addr[5] = mac2 & 0xff; + addr[0] = (mac1 >> 8) & 0xff; + addr[1] = mac1 & 0xff; + addr[2] = (mac2 >> 24) & 0xff; + addr[3] = (mac2 >> 16) & 0xff; + addr[4] = (mac2 >> 8) & 0xff; + addr[5] = mac2 & 0xff; + eth_hw_addr_set(dev, addr); printk("MAC: %pM\n", dev->dev_addr); @@ -2712,7 +2714,7 @@ static int ace_set_mac_addr(struct net_device *dev, void *p) struct ace_private *ap = netdev_priv(dev); struct ace_regs __iomem *regs = ap->regs; struct sockaddr *addr=p; - u8 *da; + const u8 *da; struct cmd cmd; if(netif_running(dev)) @@ -2720,7 +2722,7 @@ static int ace_set_mac_addr(struct net_device *dev, void *p) eth_hw_addr_set(dev, addr->sa_data); - da = (u8 *)dev->dev_addr; + da = (const u8 *)dev->dev_addr; writel(da[0] << 8 | da[1], ®s->MacAddrHi); writel((da[2] << 24) | (da[3] << 16) | (da[4] << 8) | da[5], diff --git a/drivers/net/ethernet/altera/altera_tse_main.c b/drivers/net/ethernet/altera/altera_tse_main.c index 7b75b0cd7ac9..d75d95a97dd9 100644 --- a/drivers/net/ethernet/altera/altera_tse_main.c +++ b/drivers/net/ethernet/altera/altera_tse_main.c @@ -849,7 +849,7 @@ static int init_phy(struct net_device *dev) return 0; } -static void tse_update_mac_addr(struct altera_tse_private *priv, u8 *addr) +static void tse_update_mac_addr(struct altera_tse_private *priv, const u8 *addr) { u32 msb; u32 lsb; diff --git a/drivers/net/ethernet/amd/amd8111e.c b/drivers/net/ethernet/amd/amd8111e.c index 0b493467b042..9421afb950f7 100644 --- a/drivers/net/ethernet/amd/amd8111e.c +++ b/drivers/net/ethernet/amd/amd8111e.c @@ -1743,6 +1743,7 @@ static int amd8111e_probe_one(struct pci_dev *pdev, unsigned long reg_addr, reg_len; struct amd8111e_priv *lp; struct net_device *dev; + u8 addr[ETH_ALEN]; err = pci_enable_device(pdev); if (err) { @@ -1809,7 +1810,8 @@ static int amd8111e_probe_one(struct pci_dev *pdev, /* Initializing MAC address */ for (i = 0; i < ETH_ALEN; i++) - dev->dev_addr[i] = readb(lp->mmio + PADR + i); + addr[i] = readb(lp->mmio + PADR + i); + eth_hw_addr_set(dev, addr); /* Setting user defined parametrs */ lp->ext_phy_option = speed_duplex[card_idx]; diff --git a/drivers/net/ethernet/amd/nmclan_cs.c b/drivers/net/ethernet/amd/nmclan_cs.c index 2c07d15c8dfe..30ee5329bd7c 100644 --- a/drivers/net/ethernet/amd/nmclan_cs.c +++ b/drivers/net/ethernet/amd/nmclan_cs.c @@ -529,7 +529,8 @@ static void mace_write(mace_private *lp, unsigned int ioaddr, int reg, mace_init Resets the MACE chip. ---------------------------------------------------------------------------- */ -static int mace_init(mace_private *lp, unsigned int ioaddr, char *enet_addr) +static int mace_init(mace_private *lp, unsigned int ioaddr, + const char *enet_addr) { int i; int ct = 0; diff --git a/drivers/net/ethernet/amd/pcnet32.c b/drivers/net/ethernet/amd/pcnet32.c index 820baa2604ac..f5c50ff377ff 100644 --- a/drivers/net/ethernet/amd/pcnet32.c +++ b/drivers/net/ethernet/amd/pcnet32.c @@ -1595,6 +1595,7 @@ pcnet32_probe1(unsigned long ioaddr, int shared, struct pci_dev *pdev) struct net_device *dev; const struct pcnet32_access *a = NULL; u8 promaddr[ETH_ALEN]; + u8 addr[ETH_ALEN]; int ret = -ENODEV; /* reset the chip */ @@ -1760,9 +1761,10 @@ pcnet32_probe1(unsigned long ioaddr, int shared, struct pci_dev *pdev) unsigned int val; val = a->read_csr(ioaddr, i + 12) & 0x0ffff; /* There may be endianness issues here. */ - dev->dev_addr[2 * i] = val & 0x0ff; - dev->dev_addr[2 * i + 1] = (val >> 8) & 0x0ff; + addr[2 * i] = val & 0x0ff; + addr[2 * i + 1] = (val >> 8) & 0x0ff; } + eth_hw_addr_set(dev, addr); /* read PROM address and compare with CSR address */ for (i = 0; i < ETH_ALEN; i++) @@ -1780,8 +1782,11 @@ pcnet32_probe1(unsigned long ioaddr, int shared, struct pci_dev *pdev) } /* if the ethernet address is not valid, force to 00:00:00:00:00:00 */ - if (!is_valid_ether_addr(dev->dev_addr)) - eth_zero_addr(dev->dev_addr); + if (!is_valid_ether_addr(dev->dev_addr)) { + static const u8 zero_addr[ETH_ALEN] = {}; + + eth_hw_addr_set(dev, zero_addr); + } if (pcnet32_debug & NETIF_MSG_PROBE) { pr_cont(" %pM", dev->dev_addr); diff --git a/drivers/net/ethernet/amd/sun3lance.c b/drivers/net/ethernet/amd/sun3lance.c index 4a845bc071b2..007bd7787291 100644 --- a/drivers/net/ethernet/amd/sun3lance.c +++ b/drivers/net/ethernet/amd/sun3lance.c @@ -305,7 +305,6 @@ static int __init lance_probe( struct net_device *dev) unsigned long ioaddr; struct lance_private *lp; - int i; static int did_version; volatile unsigned short *ioaddr_probe; unsigned short tmp1, tmp2; @@ -373,8 +372,7 @@ static int __init lance_probe( struct net_device *dev) dev->irq); /* copy in the ethernet address from the prom */ - for(i = 0; i < 6 ; i++) - dev->dev_addr[i] = idprom->id_ethaddr[i]; + eth_hw_addr_set(dev, idprom->id_ethaddr); /* tell the card it's ether address, bytes swapped */ MEM->init.hwaddr[0] = dev->dev_addr[1]; diff --git a/drivers/net/ethernet/amd/sunlance.c b/drivers/net/ethernet/amd/sunlance.c index ddece276ae23..22d609563af8 100644 --- a/drivers/net/ethernet/amd/sunlance.c +++ b/drivers/net/ethernet/amd/sunlance.c @@ -1301,7 +1301,6 @@ static int sparc_lance_probe_one(struct platform_device *op, struct device_node *dp = op->dev.of_node; struct lance_private *lp; struct net_device *dev; - int i; dev = alloc_etherdev(sizeof(struct lance_private) + 8); if (!dev) @@ -1315,8 +1314,7 @@ static int sparc_lance_probe_one(struct platform_device *op, * will copy the address in the device structure to the lance * initialization block. */ - for (i = 0; i < 6; i++) - dev->dev_addr[i] = idprom->id_ethaddr[i]; + eth_hw_addr_set(dev, idprom->id_ethaddr); /* Get the IO region */ lp->lregs = of_ioremap(&op->resource[0], 0, diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c index d5fd49dd25f3..3936543a74d8 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c @@ -1080,7 +1080,7 @@ static int xgbe_add_mac_addresses(struct xgbe_prv_data *pdata) return 0; } -static int xgbe_set_mac_address(struct xgbe_prv_data *pdata, u8 *addr) +static int xgbe_set_mac_address(struct xgbe_prv_data *pdata, const u8 *addr) { unsigned int mac_addr_hi, mac_addr_lo; diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c index b5bf5af8db5f..30d24d19f40d 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c @@ -1912,10 +1912,8 @@ static int xgbe_close(struct net_device *netdev) clk_disable_unprepare(pdata->ptpclk); clk_disable_unprepare(pdata->sysclk); - flush_workqueue(pdata->an_workqueue); destroy_workqueue(pdata->an_workqueue); - flush_workqueue(pdata->dev_workqueue); destroy_workqueue(pdata->dev_workqueue); set_bit(XGBE_DOWN, &pdata->dev_state); diff --git a/drivers/net/ethernet/amd/xgbe/xgbe.h b/drivers/net/ethernet/amd/xgbe/xgbe.h index 3305979a9f7c..607a2c90513b 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe.h +++ b/drivers/net/ethernet/amd/xgbe/xgbe.h @@ -729,7 +729,7 @@ struct xgbe_ext_stats { struct xgbe_hw_if { int (*tx_complete)(struct xgbe_ring_desc *); - int (*set_mac_address)(struct xgbe_prv_data *, u8 *addr); + int (*set_mac_address)(struct xgbe_prv_data *, const u8 *addr); int (*config_rx_mode)(struct xgbe_prv_data *); int (*enable_rx_csum)(struct xgbe_prv_data *); diff --git a/drivers/net/ethernet/apm/xgene-v2/mac.c b/drivers/net/ethernet/apm/xgene-v2/mac.c index 2da979e4fad1..6423e22e05b2 100644 --- a/drivers/net/ethernet/apm/xgene-v2/mac.c +++ b/drivers/net/ethernet/apm/xgene-v2/mac.c @@ -65,7 +65,7 @@ void xge_mac_set_speed(struct xge_pdata *pdata) void xge_mac_set_station_addr(struct xge_pdata *pdata) { - u8 *dev_addr = pdata->ndev->dev_addr; + const u8 *dev_addr = pdata->ndev->dev_addr; u32 addr0, addr1; addr0 = (dev_addr[3] << 24) | (dev_addr[2] << 16) | diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c index 5f657879134e..e641dbbea1e2 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c @@ -378,8 +378,8 @@ u32 xgene_enet_rd_stat(struct xgene_enet_pdata *pdata, u32 rd_addr) static void xgene_gmac_set_mac_addr(struct xgene_enet_pdata *pdata) { + const u8 *dev_addr = pdata->ndev->dev_addr; u32 addr0, addr1; - u8 *dev_addr = pdata->ndev->dev_addr; addr0 = (dev_addr[3] << 24) | (dev_addr[2] << 16) | (dev_addr[1] << 8) | dev_addr[0]; diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_sgmac.c b/drivers/net/ethernet/apm/xgene/xgene_enet_sgmac.c index f482ced2cadd..72b5e8eb0ec7 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_sgmac.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_sgmac.c @@ -165,8 +165,8 @@ static void xgene_sgmac_reset(struct xgene_enet_pdata *p) static void xgene_sgmac_set_mac_addr(struct xgene_enet_pdata *p) { + const u8 *dev_addr = p->ndev->dev_addr; u32 addr0, addr1; - u8 *dev_addr = p->ndev->dev_addr; addr0 = (dev_addr[3] << 24) | (dev_addr[2] << 16) | (dev_addr[1] << 8) | dev_addr[0]; diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.c b/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.c index 304b5d43f236..86607b79c09f 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.c @@ -207,8 +207,8 @@ static void xgene_pcs_reset(struct xgene_enet_pdata *pdata) static void xgene_xgmac_set_mac_addr(struct xgene_enet_pdata *pdata) { + const u8 *dev_addr = pdata->ndev->dev_addr; u32 addr0, addr1; - u8 *dev_addr = pdata->ndev->dev_addr; addr0 = (dev_addr[3] << 24) | (dev_addr[2] << 16) | (dev_addr[1] << 8) | dev_addr[0]; diff --git a/drivers/net/ethernet/apple/bmac.c b/drivers/net/ethernet/apple/bmac.c index a989d2df59ad..9a650d1c1bdd 100644 --- a/drivers/net/ethernet/apple/bmac.c +++ b/drivers/net/ethernet/apple/bmac.c @@ -308,7 +308,7 @@ bmac_init_registers(struct net_device *dev) { struct bmac_data *bp = netdev_priv(dev); volatile unsigned short regValue; - unsigned short *pWord16; + const unsigned short *pWord16; int i; /* XXDEBUG(("bmac: enter init_registers\n")); */ @@ -371,7 +371,7 @@ bmac_init_registers(struct net_device *dev) bmwrite(dev, BHASH1, bp->hash_table_mask[2]); /* bits 47 - 32 */ bmwrite(dev, BHASH0, bp->hash_table_mask[3]); /* bits 63 - 48 */ - pWord16 = (unsigned short *)dev->dev_addr; + pWord16 = (const unsigned short *)dev->dev_addr; bmwrite(dev, MADD0, *pWord16++); bmwrite(dev, MADD1, *pWord16++); bmwrite(dev, MADD2, *pWord16); @@ -521,19 +521,16 @@ static int bmac_resume(struct macio_dev *mdev) static int bmac_set_address(struct net_device *dev, void *addr) { struct bmac_data *bp = netdev_priv(dev); - unsigned char *p = addr; - unsigned short *pWord16; + const unsigned short *pWord16; unsigned long flags; - int i; XXDEBUG(("bmac: enter set_address\n")); spin_lock_irqsave(&bp->lock, flags); - for (i = 0; i < 6; ++i) { - dev->dev_addr[i] = p[i]; - } + eth_hw_addr_set(dev, addr); + /* load up the hardware address */ - pWord16 = (unsigned short *)dev->dev_addr; + pWord16 = (const unsigned short *)dev->dev_addr; bmwrite(dev, MADD0, *pWord16++); bmwrite(dev, MADD1, *pWord16++); bmwrite(dev, MADD2, *pWord16); diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h index bed481816ea3..062a300a566a 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h @@ -217,7 +217,7 @@ struct aq_hw_ops { int (*hw_ring_tx_head_update)(struct aq_hw_s *self, struct aq_ring_s *aq_ring); - int (*hw_set_mac_address)(struct aq_hw_s *self, u8 *mac_addr); + int (*hw_set_mac_address)(struct aq_hw_s *self, const u8 *mac_addr); int (*hw_soft_reset)(struct aq_hw_s *self); @@ -226,7 +226,7 @@ struct aq_hw_ops { int (*hw_reset)(struct aq_hw_s *self); - int (*hw_init)(struct aq_hw_s *self, u8 *mac_addr); + int (*hw_init)(struct aq_hw_s *self, const u8 *mac_addr); int (*hw_start)(struct aq_hw_s *self); @@ -373,7 +373,7 @@ struct aq_fw_ops { int (*set_phyloopback)(struct aq_hw_s *self, u32 mode, bool enable); int (*set_power)(struct aq_hw_s *self, unsigned int power_state, - u8 *mac); + const u8 *mac); int (*send_fw_request)(struct aq_hw_s *self, const struct hw_fw_request_iface *fw_req, diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_macsec.c b/drivers/net/ethernet/aquantia/atlantic/aq_macsec.c index 4a6dfac857ca..02058fe79f52 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_macsec.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_macsec.c @@ -35,7 +35,7 @@ static int aq_apply_macsec_cfg(struct aq_nic_s *nic); static int aq_apply_secy_cfg(struct aq_nic_s *nic, const struct macsec_secy *secy); -static void aq_ether_addr_to_mac(u32 mac[2], unsigned char *emac) +static void aq_ether_addr_to_mac(u32 mac[2], const unsigned char *emac) { u32 tmp[2] = { 0 }; diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c index 694aa70bcafe..1acf544afeb4 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c @@ -300,6 +300,7 @@ static bool aq_nic_is_valid_ether_addr(const u8 *addr) int aq_nic_ndev_register(struct aq_nic_s *self) { + u8 addr[ETH_ALEN]; int err = 0; if (!self->ndev) { @@ -316,12 +317,13 @@ int aq_nic_ndev_register(struct aq_nic_s *self) #endif mutex_lock(&self->fwreq_mutex); - err = self->aq_fw_ops->get_mac_permanent(self->aq_hw, - self->ndev->dev_addr); + err = self->aq_fw_ops->get_mac_permanent(self->aq_hw, addr); mutex_unlock(&self->fwreq_mutex); if (err) goto err_exit; + eth_hw_addr_set(self->ndev, addr); + if (!is_valid_ether_addr(self->ndev->dev_addr) || !aq_nic_is_valid_ether_addr(self->ndev->dev_addr)) { netdev_warn(self->ndev, "MAC is invalid, will use random."); diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c index 611875ef2cd1..4625ccb79499 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c @@ -322,7 +322,7 @@ static int hw_atl_a0_hw_init_rx_path(struct aq_hw_s *self) return aq_hw_err_from_flags(self); } -static int hw_atl_a0_hw_mac_addr_set(struct aq_hw_s *self, u8 *mac_addr) +static int hw_atl_a0_hw_mac_addr_set(struct aq_hw_s *self, const u8 *mac_addr) { unsigned int h = 0U; unsigned int l = 0U; @@ -348,7 +348,7 @@ err_exit: return err; } -static int hw_atl_a0_hw_init(struct aq_hw_s *self, u8 *mac_addr) +static int hw_atl_a0_hw_init(struct aq_hw_s *self, const u8 *mac_addr) { static u32 aq_hw_atl_igcr_table_[4][2] = { [AQ_HW_IRQ_INVALID] = { 0x20000000U, 0x20000000U }, diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c index 9f1b15077e7d..d875ce3ec759 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c @@ -533,7 +533,7 @@ static int hw_atl_b0_hw_init_rx_path(struct aq_hw_s *self) return aq_hw_err_from_flags(self); } -int hw_atl_b0_hw_mac_addr_set(struct aq_hw_s *self, u8 *mac_addr) +int hw_atl_b0_hw_mac_addr_set(struct aq_hw_s *self, const u8 *mac_addr) { unsigned int h = 0U; unsigned int l = 0U; @@ -558,7 +558,7 @@ err_exit: return err; } -static int hw_atl_b0_hw_init(struct aq_hw_s *self, u8 *mac_addr) +static int hw_atl_b0_hw_init(struct aq_hw_s *self, const u8 *mac_addr) { static u32 aq_hw_atl_igcr_table_[4][2] = { [AQ_HW_IRQ_INVALID] = { 0x20000000U, 0x20000000U }, diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.h index d8db972113ec..5298846dd9f7 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.h +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.h @@ -58,7 +58,7 @@ int hw_atl_b0_hw_ring_rx_stop(struct aq_hw_s *self, struct aq_ring_s *ring); void hw_atl_b0_hw_init_rx_rss_ctrl1(struct aq_hw_s *self); -int hw_atl_b0_hw_mac_addr_set(struct aq_hw_s *self, u8 *mac_addr); +int hw_atl_b0_hw_mac_addr_set(struct aq_hw_s *self, const u8 *mac_addr); int hw_atl_b0_set_fc(struct aq_hw_s *self, u32 fc, u32 tc); int hw_atl_b0_set_loopback(struct aq_hw_s *self, u32 mode, bool enable); diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c index 404cbf60d3f2..fc0e66006644 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c @@ -944,7 +944,7 @@ u32 hw_atl_utils_get_fw_version(struct aq_hw_s *self) } static int aq_fw1x_set_wake_magic(struct aq_hw_s *self, bool wol_enabled, - u8 *mac) + const u8 *mac) { struct hw_atl_utils_fw_rpc *prpc = NULL; unsigned int rpc_size = 0U; @@ -987,7 +987,7 @@ err_exit: } static int aq_fw1x_set_power(struct aq_hw_s *self, unsigned int power_state, - u8 *mac) + const u8 *mac) { struct hw_atl_utils_fw_rpc *prpc = NULL; unsigned int rpc_size = 0U; diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c index ee0c22d04935..eac631c45c56 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c @@ -358,7 +358,7 @@ static int aq_fw2x_get_phy_temp(struct aq_hw_s *self, int *temp) return 0; } -static int aq_fw2x_set_wol(struct aq_hw_s *self, u8 *mac) +static int aq_fw2x_set_wol(struct aq_hw_s *self, const u8 *mac) { struct hw_atl_utils_fw_rpc *rpc = NULL; struct offload_info *info = NULL; @@ -404,7 +404,7 @@ err_exit: } static int aq_fw2x_set_power(struct aq_hw_s *self, unsigned int power_state, - u8 *mac) + const u8 *mac) { int err = 0; diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c index 92f64048bf69..c98708bb044c 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c @@ -516,7 +516,7 @@ static int hw_atl2_hw_init_rx_path(struct aq_hw_s *self) return aq_hw_err_from_flags(self); } -static int hw_atl2_hw_init(struct aq_hw_s *self, u8 *mac_addr) +static int hw_atl2_hw_init(struct aq_hw_s *self, const u8 *mac_addr) { static u32 aq_hw_atl2_igcr_table_[4][2] = { [AQ_HW_IRQ_INVALID] = { 0x20000000U, 0x20000000U }, diff --git a/drivers/net/ethernet/asix/Kconfig b/drivers/net/ethernet/asix/Kconfig new file mode 100644 index 000000000000..eed02453314c --- /dev/null +++ b/drivers/net/ethernet/asix/Kconfig @@ -0,0 +1,35 @@ +# +# Asix network device configuration +# + +config NET_VENDOR_ASIX + bool "Asix devices" + default y + help + If you have a network (Ethernet, non-USB, not NE2000 compatible) + interface based on a chip from ASIX, say Y. + +if NET_VENDOR_ASIX + +config SPI_AX88796C + tristate "Asix AX88796C-SPI support" + select PHYLIB + depends on SPI + depends on GPIOLIB + help + Say Y here if you intend to use ASIX AX88796C attached in SPI mode. + +config SPI_AX88796C_COMPRESSION + bool "SPI transfer compression" + default n + depends on SPI_AX88796C + help + Say Y here to enable SPI transfer compression. It saves up + to 24 dummy cycles during each transfer which may noticeably + speed up short transfers. This sets the default value that is + inherited by network interfaces during probe. It can be + changed at run time via spi-compression ethtool tunable. + + If unsure say N. + +endif # NET_VENDOR_ASIX diff --git a/drivers/net/ethernet/asix/Makefile b/drivers/net/ethernet/asix/Makefile new file mode 100644 index 000000000000..0bfbbb042634 --- /dev/null +++ b/drivers/net/ethernet/asix/Makefile @@ -0,0 +1,6 @@ +# +# Makefile for the Asix network device drivers. +# + +obj-$(CONFIG_SPI_AX88796C) += ax88796c.o +ax88796c-y := ax88796c_main.o ax88796c_ioctl.o ax88796c_spi.o diff --git a/drivers/net/ethernet/asix/ax88796c_ioctl.c b/drivers/net/ethernet/asix/ax88796c_ioctl.c new file mode 100644 index 000000000000..916ae380a004 --- /dev/null +++ b/drivers/net/ethernet/asix/ax88796c_ioctl.c @@ -0,0 +1,239 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2010 ASIX Electronics Corporation + * Copyright (c) 2020 Samsung Electronics Co., Ltd. + * + * ASIX AX88796C SPI Fast Ethernet Linux driver + */ + +#define pr_fmt(fmt) "ax88796c: " fmt + +#include +#include +#include +#include + +#include "ax88796c_main.h" +#include "ax88796c_ioctl.h" + +static const char ax88796c_priv_flag_names[][ETH_GSTRING_LEN] = { + "SPICompression", +}; + +static void +ax88796c_get_drvinfo(struct net_device *ndev, struct ethtool_drvinfo *info) +{ + /* Inherit standard device info */ + strncpy(info->driver, DRV_NAME, sizeof(info->driver)); +} + +static u32 ax88796c_get_msglevel(struct net_device *ndev) +{ + struct ax88796c_device *ax_local = to_ax88796c_device(ndev); + + return ax_local->msg_enable; +} + +static void ax88796c_set_msglevel(struct net_device *ndev, u32 level) +{ + struct ax88796c_device *ax_local = to_ax88796c_device(ndev); + + ax_local->msg_enable = level; +} + +static void +ax88796c_get_pauseparam(struct net_device *ndev, struct ethtool_pauseparam *pause) +{ + struct ax88796c_device *ax_local = to_ax88796c_device(ndev); + + pause->tx_pause = !!(ax_local->flowctrl & AX_FC_TX); + pause->rx_pause = !!(ax_local->flowctrl & AX_FC_RX); + pause->autoneg = (ax_local->flowctrl & AX_FC_ANEG) ? + AUTONEG_ENABLE : + AUTONEG_DISABLE; +} + +static int +ax88796c_set_pauseparam(struct net_device *ndev, struct ethtool_pauseparam *pause) +{ + struct ax88796c_device *ax_local = to_ax88796c_device(ndev); + int fc; + + /* The following logic comes from phylink_ethtool_set_pauseparam() */ + fc = pause->tx_pause ? AX_FC_TX : 0; + fc |= pause->rx_pause ? AX_FC_RX : 0; + fc |= pause->autoneg ? AX_FC_ANEG : 0; + + ax_local->flowctrl = fc; + + if (pause->autoneg) { + phy_set_asym_pause(ax_local->phydev, pause->tx_pause, + pause->rx_pause); + } else { + int maccr = 0; + + phy_set_asym_pause(ax_local->phydev, 0, 0); + maccr |= (ax_local->flowctrl & AX_FC_RX) ? MACCR_RXFC_ENABLE : 0; + maccr |= (ax_local->flowctrl & AX_FC_TX) ? MACCR_TXFC_ENABLE : 0; + + mutex_lock(&ax_local->spi_lock); + + maccr |= AX_READ(&ax_local->ax_spi, P0_MACCR) & + ~(MACCR_TXFC_ENABLE | MACCR_RXFC_ENABLE); + AX_WRITE(&ax_local->ax_spi, maccr, P0_MACCR); + + mutex_unlock(&ax_local->spi_lock); + } + + return 0; +} + +static int ax88796c_get_regs_len(struct net_device *ndev) +{ + return AX88796C_REGDUMP_LEN + AX88796C_PHY_REGDUMP_LEN; +} + +static void +ax88796c_get_regs(struct net_device *ndev, struct ethtool_regs *regs, void *_p) +{ + struct ax88796c_device *ax_local = to_ax88796c_device(ndev); + int offset, i; + u16 *p = _p; + + memset(p, 0, ax88796c_get_regs_len(ndev)); + + mutex_lock(&ax_local->spi_lock); + + for (offset = 0; offset < AX88796C_REGDUMP_LEN; offset += 2) { + if (!test_bit(offset / 2, ax88796c_no_regs_mask)) + *p = AX_READ(&ax_local->ax_spi, offset); + p++; + } + + mutex_unlock(&ax_local->spi_lock); + + for (i = 0; i < AX88796C_PHY_REGDUMP_LEN / 2; i++) { + *p = phy_read(ax_local->phydev, i); + p++; + } +} + +static void +ax88796c_get_strings(struct net_device *ndev, u32 stringset, u8 *data) +{ + switch (stringset) { + case ETH_SS_PRIV_FLAGS: + memcpy(data, ax88796c_priv_flag_names, + sizeof(ax88796c_priv_flag_names)); + break; + } +} + +static int +ax88796c_get_sset_count(struct net_device *ndev, int stringset) +{ + int ret = 0; + + switch (stringset) { + case ETH_SS_PRIV_FLAGS: + ret = ARRAY_SIZE(ax88796c_priv_flag_names); + break; + default: + ret = -EOPNOTSUPP; + } + + return ret; +} + +static int ax88796c_set_priv_flags(struct net_device *ndev, u32 flags) +{ + struct ax88796c_device *ax_local = to_ax88796c_device(ndev); + + if (flags & ~AX_PRIV_FLAGS_MASK) + return -EOPNOTSUPP; + + if ((ax_local->priv_flags ^ flags) & AX_CAP_COMP) + if (netif_running(ndev)) + return -EBUSY; + + ax_local->priv_flags = flags; + + return 0; +} + +static u32 ax88796c_get_priv_flags(struct net_device *ndev) +{ + struct ax88796c_device *ax_local = to_ax88796c_device(ndev); + + return ax_local->priv_flags; +} + +int ax88796c_mdio_read(struct mii_bus *mdiobus, int phy_id, int loc) +{ + struct ax88796c_device *ax_local = mdiobus->priv; + int ret; + + mutex_lock(&ax_local->spi_lock); + AX_WRITE(&ax_local->ax_spi, MDIOCR_RADDR(loc) + | MDIOCR_FADDR(phy_id) | MDIOCR_READ, P2_MDIOCR); + + ret = read_poll_timeout(AX_READ, ret, + (ret != 0), + 0, jiffies_to_usecs(HZ / 100), false, + &ax_local->ax_spi, P2_MDIOCR); + if (!ret) + ret = AX_READ(&ax_local->ax_spi, P2_MDIODR); + + mutex_unlock(&ax_local->spi_lock); + + return ret; +} + +int +ax88796c_mdio_write(struct mii_bus *mdiobus, int phy_id, int loc, u16 val) +{ + struct ax88796c_device *ax_local = mdiobus->priv; + int ret; + + mutex_lock(&ax_local->spi_lock); + AX_WRITE(&ax_local->ax_spi, val, P2_MDIODR); + + AX_WRITE(&ax_local->ax_spi, + MDIOCR_RADDR(loc) | MDIOCR_FADDR(phy_id) + | MDIOCR_WRITE, P2_MDIOCR); + + ret = read_poll_timeout(AX_READ, ret, + ((ret & MDIOCR_VALID) != 0), 0, + jiffies_to_usecs(HZ / 100), false, + &ax_local->ax_spi, P2_MDIOCR); + mutex_unlock(&ax_local->spi_lock); + + return ret; +} + +const struct ethtool_ops ax88796c_ethtool_ops = { + .get_drvinfo = ax88796c_get_drvinfo, + .get_link = ethtool_op_get_link, + .get_msglevel = ax88796c_get_msglevel, + .set_msglevel = ax88796c_set_msglevel, + .get_link_ksettings = phy_ethtool_get_link_ksettings, + .set_link_ksettings = phy_ethtool_set_link_ksettings, + .nway_reset = phy_ethtool_nway_reset, + .get_pauseparam = ax88796c_get_pauseparam, + .set_pauseparam = ax88796c_set_pauseparam, + .get_regs_len = ax88796c_get_regs_len, + .get_regs = ax88796c_get_regs, + .get_strings = ax88796c_get_strings, + .get_sset_count = ax88796c_get_sset_count, + .get_priv_flags = ax88796c_get_priv_flags, + .set_priv_flags = ax88796c_set_priv_flags, +}; + +int ax88796c_ioctl(struct net_device *ndev, struct ifreq *ifr, int cmd) +{ + int ret; + + ret = phy_mii_ioctl(ndev->phydev, ifr, cmd); + + return ret; +} diff --git a/drivers/net/ethernet/asix/ax88796c_ioctl.h b/drivers/net/ethernet/asix/ax88796c_ioctl.h new file mode 100644 index 000000000000..34d2a7dcc5ef --- /dev/null +++ b/drivers/net/ethernet/asix/ax88796c_ioctl.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2010 ASIX Electronics Corporation + * Copyright (c) 2020 Samsung Electronics Co., Ltd. + * + * ASIX AX88796C SPI Fast Ethernet Linux driver + */ + +#ifndef _AX88796C_IOCTL_H +#define _AX88796C_IOCTL_H + +#include +#include + +#include "ax88796c_main.h" + +extern const struct ethtool_ops ax88796c_ethtool_ops; + +bool ax88796c_check_power(const struct ax88796c_device *ax_local); +bool ax88796c_check_power_and_wake(struct ax88796c_device *ax_local); +void ax88796c_set_power_saving(struct ax88796c_device *ax_local, u8 ps_level); +int ax88796c_mdio_read(struct mii_bus *mdiobus, int phy_id, int loc); +int ax88796c_mdio_write(struct mii_bus *mdiobus, int phy_id, int loc, u16 val); +int ax88796c_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd); + +#endif diff --git a/drivers/net/ethernet/asix/ax88796c_main.c b/drivers/net/ethernet/asix/ax88796c_main.c new file mode 100644 index 000000000000..cfc597f72e3d --- /dev/null +++ b/drivers/net/ethernet/asix/ax88796c_main.c @@ -0,0 +1,1163 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2010 ASIX Electronics Corporation + * Copyright (c) 2020 Samsung Electronics Co., Ltd. + * + * ASIX AX88796C SPI Fast Ethernet Linux driver + */ + +#define pr_fmt(fmt) "ax88796c: " fmt + +#include "ax88796c_main.h" +#include "ax88796c_ioctl.h" + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static int comp = IS_ENABLED(CONFIG_SPI_AX88796C_COMPRESSION); +static int msg_enable = NETIF_MSG_PROBE | + NETIF_MSG_LINK | + NETIF_MSG_RX_ERR | + NETIF_MSG_TX_ERR; + +static const char *no_regs_list = "80018001,e1918001,8001a001,fc0d0000"; +unsigned long ax88796c_no_regs_mask[AX88796C_REGDUMP_LEN / (sizeof(unsigned long) * 8)]; + +module_param(msg_enable, int, 0444); +MODULE_PARM_DESC(msg_enable, "Message mask (see linux/netdevice.h for bitmap)"); + +static int ax88796c_soft_reset(struct ax88796c_device *ax_local) +{ + u16 temp; + int ret; + + lockdep_assert_held(&ax_local->spi_lock); + + AX_WRITE(&ax_local->ax_spi, PSR_RESET, P0_PSR); + AX_WRITE(&ax_local->ax_spi, PSR_RESET_CLR, P0_PSR); + + ret = read_poll_timeout(AX_READ, ret, + (ret & PSR_DEV_READY), + 0, jiffies_to_usecs(160 * HZ / 1000), false, + &ax_local->ax_spi, P0_PSR); + if (ret) + return ret; + + temp = AX_READ(&ax_local->ax_spi, P4_SPICR); + if (ax_local->priv_flags & AX_CAP_COMP) { + AX_WRITE(&ax_local->ax_spi, + (temp | SPICR_RCEN | SPICR_QCEN), P4_SPICR); + ax_local->ax_spi.comp = 1; + } else { + AX_WRITE(&ax_local->ax_spi, + (temp & ~(SPICR_RCEN | SPICR_QCEN)), P4_SPICR); + ax_local->ax_spi.comp = 0; + } + + return 0; +} + +static int ax88796c_reload_eeprom(struct ax88796c_device *ax_local) +{ + int ret; + + lockdep_assert_held(&ax_local->spi_lock); + + AX_WRITE(&ax_local->ax_spi, EECR_RELOAD, P3_EECR); + + ret = read_poll_timeout(AX_READ, ret, + (ret & PSR_DEV_READY), + 0, jiffies_to_usecs(2 * HZ / 1000), false, + &ax_local->ax_spi, P0_PSR); + if (ret) { + dev_err(&ax_local->spi->dev, + "timeout waiting for reload eeprom\n"); + return ret; + } + + return 0; +} + +static void ax88796c_set_hw_multicast(struct net_device *ndev) +{ + struct ax88796c_device *ax_local = to_ax88796c_device(ndev); + int mc_count = netdev_mc_count(ndev); + u16 rx_ctl = RXCR_AB; + + lockdep_assert_held(&ax_local->spi_lock); + + memset(ax_local->multi_filter, 0, AX_MCAST_FILTER_SIZE); + + if (ndev->flags & IFF_PROMISC) { + rx_ctl |= RXCR_PRO; + + } else if (ndev->flags & IFF_ALLMULTI || mc_count > AX_MAX_MCAST) { + rx_ctl |= RXCR_AMALL; + + } else if (mc_count == 0) { + /* just broadcast and directed */ + } else { + u32 crc_bits; + int i; + struct netdev_hw_addr *ha; + + netdev_for_each_mc_addr(ha, ndev) { + crc_bits = ether_crc(ETH_ALEN, ha->addr); + ax_local->multi_filter[crc_bits >> 29] |= + (1 << ((crc_bits >> 26) & 7)); + } + + for (i = 0; i < 4; i++) { + AX_WRITE(&ax_local->ax_spi, + ((ax_local->multi_filter[i * 2 + 1] << 8) | + ax_local->multi_filter[i * 2]), P3_MFAR(i)); + } + } + + AX_WRITE(&ax_local->ax_spi, rx_ctl, P2_RXCR); +} + +static void ax88796c_set_mac_addr(struct net_device *ndev) +{ + struct ax88796c_device *ax_local = to_ax88796c_device(ndev); + + lockdep_assert_held(&ax_local->spi_lock); + + AX_WRITE(&ax_local->ax_spi, ((u16)(ndev->dev_addr[4] << 8) | + (u16)ndev->dev_addr[5]), P3_MACASR0); + AX_WRITE(&ax_local->ax_spi, ((u16)(ndev->dev_addr[2] << 8) | + (u16)ndev->dev_addr[3]), P3_MACASR1); + AX_WRITE(&ax_local->ax_spi, ((u16)(ndev->dev_addr[0] << 8) | + (u16)ndev->dev_addr[1]), P3_MACASR2); +} + +static void ax88796c_load_mac_addr(struct net_device *ndev) +{ + struct ax88796c_device *ax_local = to_ax88796c_device(ndev); + u16 temp; + + lockdep_assert_held(&ax_local->spi_lock); + + /* Try the device tree first */ + if (!eth_platform_get_mac_address(&ax_local->spi->dev, ndev->dev_addr) && + is_valid_ether_addr(ndev->dev_addr)) { + if (netif_msg_probe(ax_local)) + dev_info(&ax_local->spi->dev, + "MAC address read from device tree\n"); + return; + } + + /* Read the MAC address from AX88796C */ + temp = AX_READ(&ax_local->ax_spi, P3_MACASR0); + ndev->dev_addr[5] = (u8)temp; + ndev->dev_addr[4] = (u8)(temp >> 8); + + temp = AX_READ(&ax_local->ax_spi, P3_MACASR1); + ndev->dev_addr[3] = (u8)temp; + ndev->dev_addr[2] = (u8)(temp >> 8); + + temp = AX_READ(&ax_local->ax_spi, P3_MACASR2); + ndev->dev_addr[1] = (u8)temp; + ndev->dev_addr[0] = (u8)(temp >> 8); + + if (is_valid_ether_addr(ndev->dev_addr)) { + if (netif_msg_probe(ax_local)) + dev_info(&ax_local->spi->dev, + "MAC address read from ASIX chip\n"); + return; + } + + /* Use random address if none found */ + if (netif_msg_probe(ax_local)) + dev_info(&ax_local->spi->dev, "Use random MAC address\n"); + eth_hw_addr_random(ndev); +} + +static void ax88796c_proc_tx_hdr(struct tx_pkt_info *info, u8 ip_summed) +{ + u16 pkt_len_bar = (~info->pkt_len & TX_HDR_SOP_PKTLENBAR); + + /* Prepare SOP header */ + info->sop.flags_len = info->pkt_len | + ((ip_summed == CHECKSUM_NONE) || + (ip_summed == CHECKSUM_UNNECESSARY) ? TX_HDR_SOP_DICF : 0); + + info->sop.seq_lenbar = ((info->seq_num << 11) & TX_HDR_SOP_SEQNUM) + | pkt_len_bar; + cpu_to_be16s(&info->sop.flags_len); + cpu_to_be16s(&info->sop.seq_lenbar); + + /* Prepare Segment header */ + info->seg.flags_seqnum_seglen = TX_HDR_SEG_FS | TX_HDR_SEG_LS + | info->pkt_len; + + info->seg.eo_so_seglenbar = pkt_len_bar; + + cpu_to_be16s(&info->seg.flags_seqnum_seglen); + cpu_to_be16s(&info->seg.eo_so_seglenbar); + + /* Prepare EOP header */ + info->eop.seq_len = ((info->seq_num << 11) & + TX_HDR_EOP_SEQNUM) | info->pkt_len; + info->eop.seqbar_lenbar = ((~info->seq_num << 11) & + TX_HDR_EOP_SEQNUMBAR) | pkt_len_bar; + + cpu_to_be16s(&info->eop.seq_len); + cpu_to_be16s(&info->eop.seqbar_lenbar); +} + +static int +ax88796c_check_free_pages(struct ax88796c_device *ax_local, u8 need_pages) +{ + u8 free_pages; + u16 tmp; + + lockdep_assert_held(&ax_local->spi_lock); + + free_pages = AX_READ(&ax_local->ax_spi, P0_TFBFCR) & TX_FREEBUF_MASK; + if (free_pages < need_pages) { + /* schedule free page interrupt */ + tmp = AX_READ(&ax_local->ax_spi, P0_TFBFCR) + & TFBFCR_SCHE_FREE_PAGE; + AX_WRITE(&ax_local->ax_spi, tmp | TFBFCR_TX_PAGE_SET | + TFBFCR_SET_FREE_PAGE(need_pages), + P0_TFBFCR); + return -ENOMEM; + } + + return 0; +} + +static struct sk_buff * +ax88796c_tx_fixup(struct net_device *ndev, struct sk_buff_head *q) +{ + struct ax88796c_device *ax_local = to_ax88796c_device(ndev); + u8 spi_len = ax_local->ax_spi.comp ? 1 : 4; + struct sk_buff *skb; + struct tx_pkt_info info; + struct skb_data *entry; + u16 pkt_len; + u8 padlen, seq_num; + u8 need_pages; + int headroom; + int tailroom; + + if (skb_queue_empty(q)) + return NULL; + + skb = skb_peek(q); + pkt_len = skb->len; + need_pages = (pkt_len + TX_OVERHEAD + 127) >> 7; + if (ax88796c_check_free_pages(ax_local, need_pages) != 0) + return NULL; + + headroom = skb_headroom(skb); + tailroom = skb_tailroom(skb); + padlen = round_up(pkt_len, 4) - pkt_len; + seq_num = ++ax_local->seq_num & 0x1F; + + info.pkt_len = pkt_len; + + if (skb_cloned(skb) || + (headroom < (TX_OVERHEAD + spi_len)) || + (tailroom < (padlen + TX_EOP_SIZE))) { + size_t h = max((TX_OVERHEAD + spi_len) - headroom, 0); + size_t t = max((padlen + TX_EOP_SIZE) - tailroom, 0); + + if (pskb_expand_head(skb, h, t, GFP_KERNEL)) + return NULL; + } + + info.seq_num = seq_num; + ax88796c_proc_tx_hdr(&info, skb->ip_summed); + + /* SOP and SEG header */ + memcpy(skb_push(skb, TX_OVERHEAD), &info.sop, TX_OVERHEAD); + + /* Write SPI TXQ header */ + memcpy(skb_push(skb, spi_len), ax88796c_tx_cmd_buf, spi_len); + + /* Make 32-bit alignment */ + skb_put(skb, padlen); + + /* EOP header */ + memcpy(skb_put(skb, TX_EOP_SIZE), &info.eop, TX_EOP_SIZE); + + skb_unlink(skb, q); + + entry = (struct skb_data *)skb->cb; + memset(entry, 0, sizeof(*entry)); + entry->len = pkt_len; + + if (netif_msg_pktdata(ax_local)) { + char pfx[IFNAMSIZ + 7]; + + snprintf(pfx, sizeof(pfx), "%s: ", ndev->name); + + netdev_info(ndev, "TX packet len %d, total len %d, seq %d\n", + pkt_len, skb->len, seq_num); + + netdev_info(ndev, " SPI Header:\n"); + print_hex_dump(KERN_INFO, pfx, DUMP_PREFIX_OFFSET, 16, 1, + skb->data, 4, 0); + + netdev_info(ndev, " TX SOP:\n"); + print_hex_dump(KERN_INFO, pfx, DUMP_PREFIX_OFFSET, 16, 1, + skb->data + 4, TX_OVERHEAD, 0); + + netdev_info(ndev, " TX packet:\n"); + print_hex_dump(KERN_INFO, pfx, DUMP_PREFIX_OFFSET, 16, 1, + skb->data + 4 + TX_OVERHEAD, + skb->len - TX_EOP_SIZE - 4 - TX_OVERHEAD, 0); + + netdev_info(ndev, " TX EOP:\n"); + print_hex_dump(KERN_INFO, pfx, DUMP_PREFIX_OFFSET, 16, 1, + skb->data + skb->len - 4, 4, 0); + } + + return skb; +} + +static int ax88796c_hard_xmit(struct ax88796c_device *ax_local) +{ + struct ax88796c_pcpu_stats *stats; + struct sk_buff *tx_skb; + struct skb_data *entry; + unsigned long flags; + + lockdep_assert_held(&ax_local->spi_lock); + + stats = this_cpu_ptr(ax_local->stats); + tx_skb = ax88796c_tx_fixup(ax_local->ndev, &ax_local->tx_wait_q); + + if (!tx_skb) { + this_cpu_inc(ax_local->stats->tx_dropped); + return 0; + } + entry = (struct skb_data *)tx_skb->cb; + + AX_WRITE(&ax_local->ax_spi, + (TSNR_TXB_START | TSNR_PKT_CNT(1)), P0_TSNR); + + axspi_write_txq(&ax_local->ax_spi, tx_skb->data, tx_skb->len); + + if (((AX_READ(&ax_local->ax_spi, P0_TSNR) & TXNR_TXB_IDLE) == 0) || + ((ISR_TXERR & AX_READ(&ax_local->ax_spi, P0_ISR)) != 0)) { + /* Ack tx error int */ + AX_WRITE(&ax_local->ax_spi, ISR_TXERR, P0_ISR); + + this_cpu_inc(ax_local->stats->tx_dropped); + + if (net_ratelimit()) + netif_err(ax_local, tx_err, ax_local->ndev, + "TX FIFO error, re-initialize the TX bridge\n"); + + /* Reinitial tx bridge */ + AX_WRITE(&ax_local->ax_spi, TXNR_TXB_REINIT | + AX_READ(&ax_local->ax_spi, P0_TSNR), P0_TSNR); + ax_local->seq_num = 0; + } else { + flags = u64_stats_update_begin_irqsave(&stats->syncp); + u64_stats_inc(&stats->tx_packets); + u64_stats_add(&stats->tx_bytes, entry->len); + u64_stats_update_end_irqrestore(&stats->syncp, flags); + } + + entry->state = tx_done; + dev_kfree_skb(tx_skb); + + return 1; +} + +static int +ax88796c_start_xmit(struct sk_buff *skb, struct net_device *ndev) +{ + struct ax88796c_device *ax_local = to_ax88796c_device(ndev); + + skb_queue_tail(&ax_local->tx_wait_q, skb); + if (skb_queue_len(&ax_local->tx_wait_q) > TX_QUEUE_HIGH_WATER) + netif_stop_queue(ndev); + + set_bit(EVENT_TX, &ax_local->flags); + schedule_work(&ax_local->ax_work); + + return NETDEV_TX_OK; +} + +static void +ax88796c_skb_return(struct ax88796c_device *ax_local, + struct sk_buff *skb, struct rx_header *rxhdr) +{ + struct net_device *ndev = ax_local->ndev; + struct ax88796c_pcpu_stats *stats; + unsigned long flags; + int status; + + stats = this_cpu_ptr(ax_local->stats); + + do { + if (!(ndev->features & NETIF_F_RXCSUM)) + break; + + /* checksum error bit is set */ + if ((rxhdr->flags & RX_HDR3_L3_ERR) || + (rxhdr->flags & RX_HDR3_L4_ERR)) + break; + + /* Other types may be indicated by more than one bit. */ + if ((rxhdr->flags & RX_HDR3_L4_TYPE_TCP) || + (rxhdr->flags & RX_HDR3_L4_TYPE_UDP)) + skb->ip_summed = CHECKSUM_UNNECESSARY; + } while (0); + + flags = u64_stats_update_begin_irqsave(&stats->syncp); + u64_stats_inc(&stats->rx_packets); + u64_stats_add(&stats->rx_bytes, skb->len); + u64_stats_update_end_irqrestore(&stats->syncp, flags); + + skb->dev = ndev; + skb->protocol = eth_type_trans(skb, ax_local->ndev); + + netif_info(ax_local, rx_status, ndev, "< rx, len %zu, type 0x%x\n", + skb->len + sizeof(struct ethhdr), skb->protocol); + + status = netif_rx_ni(skb); + if (status != NET_RX_SUCCESS && net_ratelimit()) + netif_info(ax_local, rx_err, ndev, + "netif_rx status %d\n", status); +} + +static void +ax88796c_rx_fixup(struct ax88796c_device *ax_local, struct sk_buff *rx_skb) +{ + struct rx_header *rxhdr = (struct rx_header *)rx_skb->data; + struct net_device *ndev = ax_local->ndev; + u16 len; + + be16_to_cpus(&rxhdr->flags_len); + be16_to_cpus(&rxhdr->seq_lenbar); + be16_to_cpus(&rxhdr->flags); + + if ((rxhdr->flags_len & RX_HDR1_PKT_LEN) != + (~rxhdr->seq_lenbar & 0x7FF)) { + netif_err(ax_local, rx_err, ndev, "Header error\n"); + + this_cpu_inc(ax_local->stats->rx_frame_errors); + kfree_skb(rx_skb); + return; + } + + if ((rxhdr->flags_len & RX_HDR1_MII_ERR) || + (rxhdr->flags_len & RX_HDR1_CRC_ERR)) { + netif_err(ax_local, rx_err, ndev, "CRC or MII error\n"); + + this_cpu_inc(ax_local->stats->rx_crc_errors); + kfree_skb(rx_skb); + return; + } + + len = rxhdr->flags_len & RX_HDR1_PKT_LEN; + if (netif_msg_pktdata(ax_local)) { + char pfx[IFNAMSIZ + 7]; + + snprintf(pfx, sizeof(pfx), "%s: ", ndev->name); + netdev_info(ndev, "RX data, total len %d, packet len %d\n", + rx_skb->len, len); + + netdev_info(ndev, " Dump RX packet header:"); + print_hex_dump(KERN_INFO, pfx, DUMP_PREFIX_OFFSET, 16, 1, + rx_skb->data, sizeof(*rxhdr), 0); + + netdev_info(ndev, " Dump RX packet:"); + print_hex_dump(KERN_INFO, pfx, DUMP_PREFIX_OFFSET, 16, 1, + rx_skb->data + sizeof(*rxhdr), len, 0); + } + + skb_pull(rx_skb, sizeof(*rxhdr)); + pskb_trim(rx_skb, len); + + ax88796c_skb_return(ax_local, rx_skb, rxhdr); +} + +static int ax88796c_receive(struct net_device *ndev) +{ + struct ax88796c_device *ax_local = to_ax88796c_device(ndev); + struct skb_data *entry; + u16 w_count, pkt_len; + struct sk_buff *skb; + u8 pkt_cnt; + + lockdep_assert_held(&ax_local->spi_lock); + + /* check rx packet and total word count */ + AX_WRITE(&ax_local->ax_spi, AX_READ(&ax_local->ax_spi, P0_RTWCR) + | RTWCR_RX_LATCH, P0_RTWCR); + + pkt_cnt = AX_READ(&ax_local->ax_spi, P0_RXBCR2) & RXBCR2_PKT_MASK; + if (!pkt_cnt) + return 0; + + pkt_len = AX_READ(&ax_local->ax_spi, P0_RCPHR) & 0x7FF; + + w_count = round_up(pkt_len + 6, 4) >> 1; + + skb = netdev_alloc_skb(ndev, w_count * 2); + if (!skb) { + AX_WRITE(&ax_local->ax_spi, RXBCR1_RXB_DISCARD, P0_RXBCR1); + this_cpu_inc(ax_local->stats->rx_dropped); + return 0; + } + entry = (struct skb_data *)skb->cb; + + AX_WRITE(&ax_local->ax_spi, RXBCR1_RXB_START | w_count, P0_RXBCR1); + + axspi_read_rxq(&ax_local->ax_spi, + skb_put(skb, w_count * 2), skb->len); + + /* Check if rx bridge is idle */ + if ((AX_READ(&ax_local->ax_spi, P0_RXBCR2) & RXBCR2_RXB_IDLE) == 0) { + if (net_ratelimit()) + netif_err(ax_local, rx_err, ndev, + "Rx Bridge is not idle\n"); + AX_WRITE(&ax_local->ax_spi, RXBCR2_RXB_REINIT, P0_RXBCR2); + + entry->state = rx_err; + } else { + entry->state = rx_done; + } + + AX_WRITE(&ax_local->ax_spi, ISR_RXPKT, P0_ISR); + + ax88796c_rx_fixup(ax_local, skb); + + return 1; +} + +static int ax88796c_process_isr(struct ax88796c_device *ax_local) +{ + struct net_device *ndev = ax_local->ndev; + int todo = 0; + u16 isr; + + lockdep_assert_held(&ax_local->spi_lock); + + isr = AX_READ(&ax_local->ax_spi, P0_ISR); + AX_WRITE(&ax_local->ax_spi, isr, P0_ISR); + + netif_dbg(ax_local, intr, ndev, " ISR 0x%04x\n", isr); + + if (isr & ISR_TXERR) { + netif_dbg(ax_local, intr, ndev, " TXERR interrupt\n"); + AX_WRITE(&ax_local->ax_spi, TXNR_TXB_REINIT, P0_TSNR); + ax_local->seq_num = 0x1f; + } + + if (isr & ISR_TXPAGES) { + netif_dbg(ax_local, intr, ndev, " TXPAGES interrupt\n"); + set_bit(EVENT_TX, &ax_local->flags); + } + + if (isr & ISR_LINK) { + netif_dbg(ax_local, intr, ndev, " Link change interrupt\n"); + phy_mac_interrupt(ax_local->ndev->phydev); + } + + if (isr & ISR_RXPKT) { + netif_dbg(ax_local, intr, ndev, " RX interrupt\n"); + todo = ax88796c_receive(ax_local->ndev); + } + + return todo; +} + +static irqreturn_t ax88796c_interrupt(int irq, void *dev_instance) +{ + struct ax88796c_device *ax_local; + struct net_device *ndev; + + ndev = dev_instance; + if (!ndev) { + pr_err("irq %d for unknown device.\n", irq); + return IRQ_RETVAL(0); + } + ax_local = to_ax88796c_device(ndev); + + disable_irq_nosync(irq); + + netif_dbg(ax_local, intr, ndev, "Interrupt occurred\n"); + + set_bit(EVENT_INTR, &ax_local->flags); + schedule_work(&ax_local->ax_work); + + return IRQ_HANDLED; +} + +static void ax88796c_work(struct work_struct *work) +{ + struct ax88796c_device *ax_local = + container_of(work, struct ax88796c_device, ax_work); + + mutex_lock(&ax_local->spi_lock); + + if (test_bit(EVENT_SET_MULTI, &ax_local->flags)) { + ax88796c_set_hw_multicast(ax_local->ndev); + clear_bit(EVENT_SET_MULTI, &ax_local->flags); + } + + if (test_bit(EVENT_INTR, &ax_local->flags)) { + AX_WRITE(&ax_local->ax_spi, IMR_MASKALL, P0_IMR); + + while (ax88796c_process_isr(ax_local)) + /* nothing */; + + clear_bit(EVENT_INTR, &ax_local->flags); + + AX_WRITE(&ax_local->ax_spi, IMR_DEFAULT, P0_IMR); + + enable_irq(ax_local->ndev->irq); + } + + if (test_bit(EVENT_TX, &ax_local->flags)) { + while (skb_queue_len(&ax_local->tx_wait_q)) { + if (!ax88796c_hard_xmit(ax_local)) + break; + } + + clear_bit(EVENT_TX, &ax_local->flags); + + if (netif_queue_stopped(ax_local->ndev) && + (skb_queue_len(&ax_local->tx_wait_q) < TX_QUEUE_LOW_WATER)) + netif_wake_queue(ax_local->ndev); + } + + mutex_unlock(&ax_local->spi_lock); +} + +static void ax88796c_get_stats64(struct net_device *ndev, + struct rtnl_link_stats64 *stats) +{ + struct ax88796c_device *ax_local = to_ax88796c_device(ndev); + u32 rx_frame_errors = 0, rx_crc_errors = 0; + u32 rx_dropped = 0, tx_dropped = 0; + unsigned int start; + int cpu; + + for_each_possible_cpu(cpu) { + struct ax88796c_pcpu_stats *s; + u64 rx_packets, rx_bytes; + u64 tx_packets, tx_bytes; + + s = per_cpu_ptr(ax_local->stats, cpu); + + do { + start = u64_stats_fetch_begin_irq(&s->syncp); + rx_packets = u64_stats_read(&s->rx_packets); + rx_bytes = u64_stats_read(&s->rx_bytes); + tx_packets = u64_stats_read(&s->tx_packets); + tx_bytes = u64_stats_read(&s->tx_bytes); + } while (u64_stats_fetch_retry_irq(&s->syncp, start)); + + stats->rx_packets += rx_packets; + stats->rx_bytes += rx_bytes; + stats->tx_packets += tx_packets; + stats->tx_bytes += tx_bytes; + + rx_dropped += stats->rx_dropped; + tx_dropped += stats->tx_dropped; + rx_frame_errors += stats->rx_frame_errors; + rx_crc_errors += stats->rx_crc_errors; + } + + stats->rx_dropped = rx_dropped; + stats->tx_dropped = tx_dropped; + stats->rx_frame_errors = rx_frame_errors; + stats->rx_crc_errors = rx_crc_errors; +} + +static void ax88796c_set_mac(struct ax88796c_device *ax_local) +{ + u16 maccr; + + maccr = (ax_local->link) ? MACCR_RXEN : 0; + + switch (ax_local->speed) { + case SPEED_100: + maccr |= MACCR_SPEED_100; + case SPEED_10: + case SPEED_UNKNOWN: + break; + default: + return; + } + + switch (ax_local->duplex) { + case DUPLEX_FULL: + maccr |= MACCR_SPEED_100; + case DUPLEX_HALF: + case DUPLEX_UNKNOWN: + break; + default: + return; + } + + if (ax_local->flowctrl & AX_FC_ANEG && + ax_local->phydev->autoneg) { + maccr |= ax_local->pause ? MACCR_RXFC_ENABLE : 0; + maccr |= !ax_local->pause != !ax_local->asym_pause ? + MACCR_TXFC_ENABLE : 0; + } else { + maccr |= (ax_local->flowctrl & AX_FC_RX) ? MACCR_RXFC_ENABLE : 0; + maccr |= (ax_local->flowctrl & AX_FC_TX) ? MACCR_TXFC_ENABLE : 0; + } + + mutex_lock(&ax_local->spi_lock); + + maccr |= AX_READ(&ax_local->ax_spi, P0_MACCR) & + ~(MACCR_DUPLEX_FULL | MACCR_SPEED_100 | + MACCR_TXFC_ENABLE | MACCR_RXFC_ENABLE); + AX_WRITE(&ax_local->ax_spi, maccr, P0_MACCR); + + mutex_unlock(&ax_local->spi_lock); +} + +static void ax88796c_handle_link_change(struct net_device *ndev) +{ + struct ax88796c_device *ax_local = to_ax88796c_device(ndev); + struct phy_device *phydev = ndev->phydev; + bool update = false; + + if (phydev->link && (ax_local->speed != phydev->speed || + ax_local->duplex != phydev->duplex || + ax_local->pause != phydev->pause || + ax_local->asym_pause != phydev->asym_pause)) { + ax_local->speed = phydev->speed; + ax_local->duplex = phydev->duplex; + ax_local->pause = phydev->pause; + ax_local->asym_pause = phydev->asym_pause; + update = true; + } + + if (phydev->link != ax_local->link) { + if (!phydev->link) { + ax_local->speed = SPEED_UNKNOWN; + ax_local->duplex = DUPLEX_UNKNOWN; + } + + ax_local->link = phydev->link; + update = true; + } + + if (update) + ax88796c_set_mac(ax_local); + + if (net_ratelimit()) + phy_print_status(ndev->phydev); +} + +static void ax88796c_set_csums(struct ax88796c_device *ax_local) +{ + struct net_device *ndev = ax_local->ndev; + + lockdep_assert_held(&ax_local->spi_lock); + + if (ndev->features & NETIF_F_RXCSUM) { + AX_WRITE(&ax_local->ax_spi, COERCR0_DEFAULT, P4_COERCR0); + AX_WRITE(&ax_local->ax_spi, COERCR1_DEFAULT, P4_COERCR1); + } else { + AX_WRITE(&ax_local->ax_spi, 0, P4_COERCR0); + AX_WRITE(&ax_local->ax_spi, 0, P4_COERCR1); + } + + if (ndev->features & NETIF_F_HW_CSUM) { + AX_WRITE(&ax_local->ax_spi, COETCR0_DEFAULT, P4_COETCR0); + AX_WRITE(&ax_local->ax_spi, COETCR1_TXPPPE, P4_COETCR1); + } else { + AX_WRITE(&ax_local->ax_spi, 0, P4_COETCR0); + AX_WRITE(&ax_local->ax_spi, 0, P4_COETCR1); + } +} + +static int +ax88796c_open(struct net_device *ndev) +{ + struct ax88796c_device *ax_local = to_ax88796c_device(ndev); + unsigned long irq_flag = 0; + int fc = AX_FC_NONE; + int ret; + u16 t; + + ret = request_irq(ndev->irq, ax88796c_interrupt, + irq_flag, ndev->name, ndev); + if (ret) { + netdev_err(ndev, "unable to get IRQ %d (errno=%d).\n", + ndev->irq, ret); + return ret; + } + + mutex_lock(&ax_local->spi_lock); + + ret = ax88796c_soft_reset(ax_local); + if (ret < 0) { + free_irq(ndev->irq, ndev); + mutex_unlock(&ax_local->spi_lock); + return ret; + } + ax_local->seq_num = 0x1f; + + ax88796c_set_mac_addr(ndev); + ax88796c_set_csums(ax_local); + + /* Disable stuffing packet */ + t = AX_READ(&ax_local->ax_spi, P1_RXBSPCR); + t &= ~RXBSPCR_STUF_ENABLE; + AX_WRITE(&ax_local->ax_spi, t, P1_RXBSPCR); + + /* Enable RX packet process */ + AX_WRITE(&ax_local->ax_spi, RPPER_RXEN, P1_RPPER); + + t = AX_READ(&ax_local->ax_spi, P0_FER); + t |= FER_RXEN | FER_TXEN | FER_BSWAP | FER_IRQ_PULL; + AX_WRITE(&ax_local->ax_spi, t, P0_FER); + + /* Setup LED mode */ + AX_WRITE(&ax_local->ax_spi, + (LCR_LED0_EN | LCR_LED0_DUPLEX | LCR_LED1_EN | + LCR_LED1_100MODE), P2_LCR0); + AX_WRITE(&ax_local->ax_spi, + (AX_READ(&ax_local->ax_spi, P2_LCR1) & LCR_LED2_MASK) | + LCR_LED2_EN | LCR_LED2_LINK, P2_LCR1); + + /* Disable PHY auto-polling */ + AX_WRITE(&ax_local->ax_spi, PCR_PHYID(AX88796C_PHY_ID), P2_PCR); + + /* Enable MAC interrupts */ + AX_WRITE(&ax_local->ax_spi, IMR_DEFAULT, P0_IMR); + + mutex_unlock(&ax_local->spi_lock); + + /* Setup flow-control configuration */ + phy_support_asym_pause(ax_local->phydev); + + if (ax_local->phydev->advertising && + (linkmode_test_bit(ETHTOOL_LINK_MODE_Pause_BIT, + ax_local->phydev->advertising) || + linkmode_test_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, + ax_local->phydev->advertising))) + fc |= AX_FC_ANEG; + + fc |= linkmode_test_bit(ETHTOOL_LINK_MODE_Pause_BIT, + ax_local->phydev->advertising) ? AX_FC_RX : 0; + fc |= (linkmode_test_bit(ETHTOOL_LINK_MODE_Pause_BIT, + ax_local->phydev->advertising) != + linkmode_test_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, + ax_local->phydev->advertising)) ? AX_FC_TX : 0; + ax_local->flowctrl = fc; + + phy_start(ax_local->ndev->phydev); + + netif_start_queue(ndev); + + spi_message_init(&ax_local->ax_spi.rx_msg); + + return 0; +} + +static int +ax88796c_close(struct net_device *ndev) +{ + struct ax88796c_device *ax_local = to_ax88796c_device(ndev); + + phy_stop(ndev->phydev); + + /* We lock the mutex early not only to protect the device + * against concurrent access, but also avoid waking up the + * queue in ax88796c_work(). phy_stop() needs to be called + * before because it locks the mutex to access SPI. + */ + mutex_lock(&ax_local->spi_lock); + + netif_stop_queue(ndev); + + /* No more work can be scheduled now. Make any pending work, + * including one already waiting for the mutex to be unlocked, + * NOP. + */ + netif_dbg(ax_local, ifdown, ndev, "clearing bits\n"); + clear_bit(EVENT_SET_MULTI, &ax_local->flags); + clear_bit(EVENT_INTR, &ax_local->flags); + clear_bit(EVENT_TX, &ax_local->flags); + + /* Disable MAC interrupts */ + AX_WRITE(&ax_local->ax_spi, IMR_MASKALL, P0_IMR); + __skb_queue_purge(&ax_local->tx_wait_q); + ax88796c_soft_reset(ax_local); + + mutex_unlock(&ax_local->spi_lock); + + cancel_work_sync(&ax_local->ax_work); + + free_irq(ndev->irq, ndev); + + return 0; +} + +static int +ax88796c_set_features(struct net_device *ndev, netdev_features_t features) +{ + struct ax88796c_device *ax_local = to_ax88796c_device(ndev); + netdev_features_t changed = features ^ ndev->features; + + if (!(changed & (NETIF_F_RXCSUM | NETIF_F_HW_CSUM))) + return 0; + + ndev->features = features; + + if (changed & (NETIF_F_RXCSUM | NETIF_F_HW_CSUM)) + ax88796c_set_csums(ax_local); + + return 0; +} + +static const struct net_device_ops ax88796c_netdev_ops = { + .ndo_open = ax88796c_open, + .ndo_stop = ax88796c_close, + .ndo_start_xmit = ax88796c_start_xmit, + .ndo_get_stats64 = ax88796c_get_stats64, + .ndo_do_ioctl = ax88796c_ioctl, + .ndo_set_mac_address = eth_mac_addr, + .ndo_set_features = ax88796c_set_features, +}; + +static int ax88796c_hard_reset(struct ax88796c_device *ax_local) +{ + struct device *dev = (struct device *)&ax_local->spi->dev; + struct gpio_desc *reset_gpio; + + /* reset info */ + reset_gpio = gpiod_get(dev, "reset", 0); + if (IS_ERR(reset_gpio)) { + dev_err(dev, "Could not get 'reset' GPIO: %ld", PTR_ERR(reset_gpio)); + return PTR_ERR(reset_gpio); + } + + /* set reset */ + gpiod_direction_output(reset_gpio, 1); + msleep(100); + gpiod_direction_output(reset_gpio, 0); + gpiod_put(reset_gpio); + msleep(20); + + return 0; +} + +static int ax88796c_probe(struct spi_device *spi) +{ + char phy_id[MII_BUS_ID_SIZE + 3]; + struct ax88796c_device *ax_local; + struct net_device *ndev; + u16 temp; + int ret; + + ndev = devm_alloc_etherdev(&spi->dev, sizeof(*ax_local)); + if (!ndev) + return -ENOMEM; + + SET_NETDEV_DEV(ndev, &spi->dev); + + ax_local = to_ax88796c_device(ndev); + + dev_set_drvdata(&spi->dev, ax_local); + ax_local->spi = spi; + ax_local->ax_spi.spi = spi; + + ax_local->stats = + devm_netdev_alloc_pcpu_stats(&spi->dev, + struct ax88796c_pcpu_stats); + if (!ax_local->stats) + return -ENOMEM; + + ax_local->ndev = ndev; + ax_local->priv_flags |= comp ? AX_CAP_COMP : 0; + ax_local->msg_enable = msg_enable; + mutex_init(&ax_local->spi_lock); + + ax_local->mdiobus = devm_mdiobus_alloc(&spi->dev); + if (!ax_local->mdiobus) + return -ENOMEM; + + ax_local->mdiobus->priv = ax_local; + ax_local->mdiobus->read = ax88796c_mdio_read; + ax_local->mdiobus->write = ax88796c_mdio_write; + ax_local->mdiobus->name = "ax88976c-mdiobus"; + ax_local->mdiobus->phy_mask = (u32)~BIT(AX88796C_PHY_ID); + ax_local->mdiobus->parent = &spi->dev; + + snprintf(ax_local->mdiobus->id, MII_BUS_ID_SIZE, + "ax88796c-%s.%u", dev_name(&spi->dev), spi->chip_select); + + ret = devm_mdiobus_register(&spi->dev, ax_local->mdiobus); + if (ret < 0) { + dev_err(&spi->dev, "Could not register MDIO bus\n"); + return ret; + } + + if (netif_msg_probe(ax_local)) { + dev_info(&spi->dev, "AX88796C-SPI Configuration:\n"); + dev_info(&spi->dev, " Compression : %s\n", + ax_local->priv_flags & AX_CAP_COMP ? "ON" : "OFF"); + } + + ndev->irq = spi->irq; + ndev->netdev_ops = &ax88796c_netdev_ops; + ndev->ethtool_ops = &ax88796c_ethtool_ops; + ndev->hw_features |= NETIF_F_HW_CSUM | NETIF_F_RXCSUM; + ndev->features |= NETIF_F_HW_CSUM | NETIF_F_RXCSUM; + ndev->needed_headroom = TX_OVERHEAD; + ndev->needed_tailroom = TX_EOP_SIZE; + + mutex_lock(&ax_local->spi_lock); + + /* ax88796c gpio reset */ + ax88796c_hard_reset(ax_local); + + /* Reset AX88796C */ + ret = ax88796c_soft_reset(ax_local); + if (ret < 0) { + ret = -ENODEV; + mutex_unlock(&ax_local->spi_lock); + goto err; + } + /* Check board revision */ + temp = AX_READ(&ax_local->ax_spi, P2_CRIR); + if ((temp & 0xF) != 0x0) { + dev_err(&spi->dev, "spi read failed: %d\n", temp); + ret = -ENODEV; + mutex_unlock(&ax_local->spi_lock); + goto err; + } + + /*Reload EEPROM*/ + ax88796c_reload_eeprom(ax_local); + + ax88796c_load_mac_addr(ndev); + + if (netif_msg_probe(ax_local)) + dev_info(&spi->dev, + "irq %d, MAC addr %02X:%02X:%02X:%02X:%02X:%02X\n", + ndev->irq, + ndev->dev_addr[0], ndev->dev_addr[1], + ndev->dev_addr[2], ndev->dev_addr[3], + ndev->dev_addr[4], ndev->dev_addr[5]); + + /* Disable power saving */ + AX_WRITE(&ax_local->ax_spi, (AX_READ(&ax_local->ax_spi, P0_PSCR) + & PSCR_PS_MASK) | PSCR_PS_D0, P0_PSCR); + + mutex_unlock(&ax_local->spi_lock); + + INIT_WORK(&ax_local->ax_work, ax88796c_work); + + skb_queue_head_init(&ax_local->tx_wait_q); + + snprintf(phy_id, MII_BUS_ID_SIZE + 3, PHY_ID_FMT, + ax_local->mdiobus->id, AX88796C_PHY_ID); + ax_local->phydev = phy_connect(ax_local->ndev, phy_id, + ax88796c_handle_link_change, + PHY_INTERFACE_MODE_MII); + if (IS_ERR(ax_local->phydev)) { + ret = PTR_ERR(ax_local->phydev); + goto err; + } + ax_local->phydev->irq = PHY_POLL; + + ret = devm_register_netdev(&spi->dev, ndev); + if (ret) { + dev_err(&spi->dev, "failed to register a network device\n"); + goto err_phy_dis; + } + + netif_info(ax_local, probe, ndev, "%s %s registered\n", + dev_driver_string(&spi->dev), + dev_name(&spi->dev)); + phy_attached_info(ax_local->phydev); + + return 0; + +err_phy_dis: + phy_disconnect(ax_local->phydev); +err: + return ret; +} + +static int ax88796c_remove(struct spi_device *spi) +{ + struct ax88796c_device *ax_local = dev_get_drvdata(&spi->dev); + struct net_device *ndev = ax_local->ndev; + + phy_disconnect(ndev->phydev); + + netif_info(ax_local, probe, ndev, "removing network device %s %s\n", + dev_driver_string(&spi->dev), + dev_name(&spi->dev)); + + return 0; +} + +static const struct of_device_id ax88796c_dt_ids[] = { + { .compatible = "asix,ax88796c" }, + {}, +}; +MODULE_DEVICE_TABLE(of, ax88796c_dt_ids); + +static const struct spi_device_id asix_id[] = { + { "ax88796c", 0 }, + { } +}; +MODULE_DEVICE_TABLE(spi, asix_id); + +static struct spi_driver ax88796c_spi_driver = { + .driver = { + .name = DRV_NAME, + .of_match_table = of_match_ptr(ax88796c_dt_ids), + }, + .probe = ax88796c_probe, + .remove = ax88796c_remove, + .id_table = asix_id, +}; + +static __init int ax88796c_spi_init(void) +{ + int ret; + + bitmap_zero(ax88796c_no_regs_mask, AX88796C_REGDUMP_LEN); + ret = bitmap_parse(no_regs_list, 35, + ax88796c_no_regs_mask, AX88796C_REGDUMP_LEN); + if (ret) { + bitmap_fill(ax88796c_no_regs_mask, AX88796C_REGDUMP_LEN); + pr_err("Invalid bitmap description, masking all registers\n"); + } + + return spi_register_driver(&ax88796c_spi_driver); +} + +static __exit void ax88796c_spi_exit(void) +{ + spi_unregister_driver(&ax88796c_spi_driver); +} + +module_init(ax88796c_spi_init); +module_exit(ax88796c_spi_exit); + +MODULE_AUTHOR("Łukasz Stelmach "); +MODULE_DESCRIPTION("ASIX AX88796C SPI Ethernet driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/ethernet/asix/ax88796c_main.h b/drivers/net/ethernet/asix/ax88796c_main.h new file mode 100644 index 000000000000..80263c3cef75 --- /dev/null +++ b/drivers/net/ethernet/asix/ax88796c_main.h @@ -0,0 +1,568 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2010 ASIX Electronics Corporation + * Copyright (c) 2020 Samsung Electronics + * + * ASIX AX88796C SPI Fast Ethernet Linux driver + */ + +#ifndef _AX88796C_MAIN_H +#define _AX88796C_MAIN_H + +#include +#include + +#include "ax88796c_spi.h" + +/* These identify the driver base version and may not be removed. */ +#define DRV_NAME "ax88796c" +#define ADP_NAME "ASIX AX88796C SPI Ethernet Adapter" + +#define TX_QUEUE_HIGH_WATER 45 /* Tx queue high water mark */ +#define TX_QUEUE_LOW_WATER 20 /* Tx queue low water mark */ + +#define AX88796C_REGDUMP_LEN 256 +#define AX88796C_PHY_REGDUMP_LEN 14 +#define AX88796C_PHY_ID 0x10 + +#define TX_OVERHEAD 8 +#define TX_EOP_SIZE 4 + +#define AX_MCAST_FILTER_SIZE 8 +#define AX_MAX_MCAST 64 +#define AX_MAX_CLK 80000000 +#define TX_HDR_SOP_DICF 0x8000 +#define TX_HDR_SOP_CPHI 0x4000 +#define TX_HDR_SOP_INT 0x2000 +#define TX_HDR_SOP_MDEQ 0x1000 +#define TX_HDR_SOP_PKTLEN 0x07FF +#define TX_HDR_SOP_SEQNUM 0xF800 +#define TX_HDR_SOP_PKTLENBAR 0x07FF + +#define TX_HDR_SEG_FS 0x8000 +#define TX_HDR_SEG_LS 0x4000 +#define TX_HDR_SEG_SEGNUM 0x3800 +#define TX_HDR_SEG_SEGLEN 0x0700 +#define TX_HDR_SEG_EOFST 0xC000 +#define TX_HDR_SEG_SOFST 0x3800 +#define TX_HDR_SEG_SEGLENBAR 0x07FF + +#define TX_HDR_EOP_SEQNUM 0xF800 +#define TX_HDR_EOP_PKTLEN 0x07FF +#define TX_HDR_EOP_SEQNUMBAR 0xF800 +#define TX_HDR_EOP_PKTLENBAR 0x07FF + +/* Rx header fields mask */ +#define RX_HDR1_MCBC 0x8000 +#define RX_HDR1_STUFF_PKT 0x4000 +#define RX_HDR1_MII_ERR 0x2000 +#define RX_HDR1_CRC_ERR 0x1000 +#define RX_HDR1_PKT_LEN 0x07FF + +#define RX_HDR2_SEQ_NUM 0xF800 +#define RX_HDR2_PKT_LEN_BAR 0x7FFF + +#define RX_HDR3_PE 0x8000 +#define RX_HDR3_L3_TYPE_IPV4V6 0x6000 +#define RX_HDR3_L3_TYPE_IP 0x4000 +#define RX_HDR3_L3_TYPE_IPV6 0x2000 +#define RX_HDR3_L4_TYPE_ICMPV6 0x1400 +#define RX_HDR3_L4_TYPE_TCP 0x1000 +#define RX_HDR3_L4_TYPE_IGMP 0x0c00 +#define RX_HDR3_L4_TYPE_ICMP 0x0800 +#define RX_HDR3_L4_TYPE_UDP 0x0400 +#define RX_HDR3_L3_ERR 0x0200 +#define RX_HDR3_L4_ERR 0x0100 +#define RX_HDR3_PRIORITY(x) ((x) << 4) +#define RX_HDR3_STRIP 0x0008 +#define RX_HDR3_VLAN_ID 0x0007 + +struct ax88796c_pcpu_stats { + u64_stats_t rx_packets; + u64_stats_t rx_bytes; + u64_stats_t tx_packets; + u64_stats_t tx_bytes; + struct u64_stats_sync syncp; + u32 rx_dropped; + u32 tx_dropped; + u32 rx_frame_errors; + u32 rx_crc_errors; +}; + +struct ax88796c_device { + struct spi_device *spi; + struct net_device *ndev; + struct ax88796c_pcpu_stats __percpu *stats; + + struct work_struct ax_work; + + struct mutex spi_lock; /* device access */ + + struct sk_buff_head tx_wait_q; + + struct axspi_data ax_spi; + + struct mii_bus *mdiobus; + struct phy_device *phydev; + + int msg_enable; + + u16 seq_num; + + u8 multi_filter[AX_MCAST_FILTER_SIZE]; + + int link; + int speed; + int duplex; + int pause; + int asym_pause; + int flowctrl; + #define AX_FC_NONE 0 + #define AX_FC_RX BIT(0) + #define AX_FC_TX BIT(1) + #define AX_FC_ANEG BIT(2) + + u32 priv_flags; + #define AX_CAP_COMP BIT(0) + #define AX_PRIV_FLAGS_MASK (AX_CAP_COMP) + + unsigned long flags; + #define EVENT_INTR BIT(0) + #define EVENT_TX BIT(1) + #define EVENT_SET_MULTI BIT(2) + +}; + +#define to_ax88796c_device(ndev) ((struct ax88796c_device *)netdev_priv(ndev)) + +enum skb_state { + illegal = 0, + tx_done, + rx_done, + rx_err, +}; + +struct skb_data { + enum skb_state state; + size_t len; +}; + +/* A88796C register definition */ + /* Definition of PAGE0 */ +#define P0_PSR (0x00) + #define PSR_DEV_READY BIT(7) + #define PSR_RESET (0 << 15) + #define PSR_RESET_CLR BIT(15) +#define P0_BOR (0x02) +#define P0_FER (0x04) + #define FER_IPALM BIT(0) + #define FER_DCRC BIT(1) + #define FER_RH3M BIT(2) + #define FER_HEADERSWAP BIT(7) + #define FER_WSWAP BIT(8) + #define FER_BSWAP BIT(9) + #define FER_INTHI BIT(10) + #define FER_INTLO (0 << 10) + #define FER_IRQ_PULL BIT(11) + #define FER_RXEN BIT(14) + #define FER_TXEN BIT(15) +#define P0_ISR (0x06) + #define ISR_RXPKT BIT(0) + #define ISR_MDQ BIT(4) + #define ISR_TXT BIT(5) + #define ISR_TXPAGES BIT(6) + #define ISR_TXERR BIT(8) + #define ISR_LINK BIT(9) +#define P0_IMR (0x08) + #define IMR_RXPKT BIT(0) + #define IMR_MDQ BIT(4) + #define IMR_TXT BIT(5) + #define IMR_TXPAGES BIT(6) + #define IMR_TXERR BIT(8) + #define IMR_LINK BIT(9) + #define IMR_MASKALL (0xFFFF) + #define IMR_DEFAULT (IMR_TXERR) +#define P0_WFCR (0x0A) + #define WFCR_PMEIND BIT(0) /* PME indication */ + #define WFCR_PMETYPE BIT(1) /* PME I/O type */ + #define WFCR_PMEPOL BIT(2) /* PME polarity */ + #define WFCR_PMERST BIT(3) /* Reset PME */ + #define WFCR_SLEEP BIT(4) /* Enable sleep mode */ + #define WFCR_WAKEUP BIT(5) /* Enable wakeup mode */ + #define WFCR_WAITEVENT BIT(6) /* Reserved */ + #define WFCR_CLRWAKE BIT(7) /* Clear wakeup */ + #define WFCR_LINKCH BIT(8) /* Enable link change */ + #define WFCR_MAGICP BIT(9) /* Enable magic packet */ + #define WFCR_WAKEF BIT(10) /* Enable wakeup frame */ + #define WFCR_PMEEN BIT(11) /* Enable PME pin */ + #define WFCR_LINKCHS BIT(12) /* Link change status */ + #define WFCR_MAGICPS BIT(13) /* Magic packet status */ + #define WFCR_WAKEFS BIT(14) /* Wakeup frame status */ + #define WFCR_PMES BIT(15) /* PME pin status */ +#define P0_PSCR (0x0C) + #define PSCR_PS_MASK (0xFFF0) + #define PSCR_PS_D0 (0) + #define PSCR_PS_D1 BIT(0) + #define PSCR_PS_D2 BIT(1) + #define PSCR_FPS BIT(3) /* Enable fiber mode PS */ + #define PSCR_SWPS BIT(4) /* Enable software */ + /* PS control */ + #define PSCR_WOLPS BIT(5) /* Enable WOL PS */ + #define PSCR_SWWOL BIT(6) /* Enable software select */ + /* WOL PS */ + #define PSCR_PHYOSC BIT(7) /* Internal PHY OSC control */ + #define PSCR_FOFEF BIT(8) /* Force PHY generate FEF */ + #define PSCR_FOF BIT(9) /* Force PHY in fiber mode */ + #define PSCR_PHYPD BIT(10) /* PHY power down. */ + /* Active high */ + #define PSCR_PHYRST BIT(11) /* PHY reset signal. */ + /* Active low */ + #define PSCR_PHYCSIL BIT(12) /* PHY cable energy detect */ + #define PSCR_PHYCOFF BIT(13) /* PHY cable off */ + #define PSCR_PHYLINK BIT(14) /* PHY link status */ + #define PSCR_EEPOK BIT(15) /* EEPROM load complete */ +#define P0_MACCR (0x0E) + #define MACCR_RXEN BIT(0) /* Enable RX */ + #define MACCR_DUPLEX_FULL BIT(1) /* 1: Full, 0: Half */ + #define MACCR_SPEED_100 BIT(2) /* 1: 100Mbps, 0: 10Mbps */ + #define MACCR_RXFC_ENABLE BIT(3) + #define MACCR_RXFC_MASK 0xFFF7 + #define MACCR_TXFC_ENABLE BIT(4) + #define MACCR_TXFC_MASK 0xFFEF + #define MACCR_PSI BIT(6) /* Software Cable-Off */ + /* Power Saving Interrupt */ + #define MACCR_PF BIT(7) + #define MACCR_PMM_BITS 8 + #define MACCR_PMM_MASK (0x1F00) + #define MACCR_PMM_RESET BIT(8) + #define MACCR_PMM_WAIT (2 << 8) + #define MACCR_PMM_READY (3 << 8) + #define MACCR_PMM_D1 (4 << 8) + #define MACCR_PMM_D2 (5 << 8) + #define MACCR_PMM_WAKE (7 << 8) + #define MACCR_PMM_D1_WAKE (8 << 8) + #define MACCR_PMM_D2_WAKE (9 << 8) + #define MACCR_PMM_SLEEP (10 << 8) + #define MACCR_PMM_PHY_RESET (11 << 8) + #define MACCR_PMM_SOFT_D1 (16 << 8) + #define MACCR_PMM_SOFT_D2 (17 << 8) +#define P0_TFBFCR (0x10) + #define TFBFCR_SCHE_FREE_PAGE 0xE07F + #define TFBFCR_FREE_PAGE_BITS 0x07 + #define TFBFCR_FREE_PAGE_LATCH BIT(6) + #define TFBFCR_SET_FREE_PAGE(x) (((x) & 0x3F) << TFBFCR_FREE_PAGE_BITS) + #define TFBFCR_TX_PAGE_SET BIT(13) + #define TFBFCR_MANU_ENTX BIT(15) + #define TX_FREEBUF_MASK 0x003F + #define TX_DPTSTART 0x4000 + +#define P0_TSNR (0x12) + #define TXNR_TXB_ERR BIT(5) + #define TXNR_TXB_IDLE BIT(6) + #define TSNR_PKT_CNT(x) (((x) & 0x3F) << 8) + #define TXNR_TXB_REINIT BIT(14) + #define TSNR_TXB_START BIT(15) +#define P0_RTDPR (0x14) +#define P0_RXBCR1 (0x16) + #define RXBCR1_RXB_DISCARD BIT(14) + #define RXBCR1_RXB_START BIT(15) +#define P0_RXBCR2 (0x18) + #define RXBCR2_PKT_MASK (0xFF) + #define RXBCR2_RXPC_MASK (0x7F) + #define RXBCR2_RXB_READY BIT(13) + #define RXBCR2_RXB_IDLE BIT(14) + #define RXBCR2_RXB_REINIT BIT(15) +#define P0_RTWCR (0x1A) + #define RTWCR_RXWC_MASK (0x3FFF) + #define RTWCR_RX_LATCH BIT(15) +#define P0_RCPHR (0x1C) + + /* Definition of PAGE1 */ +#define P1_RPPER (0x22) + #define RPPER_RXEN BIT(0) +#define P1_MRCR (0x28) +#define P1_MDR (0x2A) +#define P1_RMPR (0x2C) +#define P1_TMPR (0x2E) +#define P1_RXBSPCR (0x30) + #define RXBSPCR_STUF_WORD_CNT(x) (((x) & 0x7000) >> 12) + #define RXBSPCR_STUF_ENABLE BIT(15) +#define P1_MCR (0x32) + #define MCR_SBP BIT(8) + #define MCR_SM BIT(9) + #define MCR_CRCENLAN BIT(11) + #define MCR_STP BIT(12) + /* Definition of PAGE2 */ +#define P2_CIR (0x42) +#define P2_PCR (0x44) + #define PCR_POLL_EN BIT(0) + #define PCR_POLL_FLOWCTRL BIT(1) + #define PCR_POLL_BMCR BIT(2) + #define PCR_PHYID(x) ((x) << 8) +#define P2_PHYSR (0x46) +#define P2_MDIODR (0x48) +#define P2_MDIOCR (0x4A) + #define MDIOCR_RADDR(x) ((x) & 0x1F) + #define MDIOCR_FADDR(x) (((x) & 0x1F) << 8) + #define MDIOCR_VALID BIT(13) + #define MDIOCR_READ BIT(14) + #define MDIOCR_WRITE BIT(15) +#define P2_LCR0 (0x4C) + #define LCR_LED0_EN BIT(0) + #define LCR_LED0_100MODE BIT(1) + #define LCR_LED0_DUPLEX BIT(2) + #define LCR_LED0_LINK BIT(3) + #define LCR_LED0_ACT BIT(4) + #define LCR_LED0_COL BIT(5) + #define LCR_LED0_10MODE BIT(6) + #define LCR_LED0_DUPCOL BIT(7) + #define LCR_LED1_EN BIT(8) + #define LCR_LED1_100MODE BIT(9) + #define LCR_LED1_DUPLEX BIT(10) + #define LCR_LED1_LINK BIT(11) + #define LCR_LED1_ACT BIT(12) + #define LCR_LED1_COL BIT(13) + #define LCR_LED1_10MODE BIT(14) + #define LCR_LED1_DUPCOL BIT(15) +#define P2_LCR1 (0x4E) + #define LCR_LED2_MASK (0xFF00) + #define LCR_LED2_EN BIT(0) + #define LCR_LED2_100MODE BIT(1) + #define LCR_LED2_DUPLEX BIT(2) + #define LCR_LED2_LINK BIT(3) + #define LCR_LED2_ACT BIT(4) + #define LCR_LED2_COL BIT(5) + #define LCR_LED2_10MODE BIT(6) + #define LCR_LED2_DUPCOL BIT(7) +#define P2_IPGCR (0x50) +#define P2_CRIR (0x52) +#define P2_FLHWCR (0x54) +#define P2_RXCR (0x56) + #define RXCR_PRO BIT(0) + #define RXCR_AMALL BIT(1) + #define RXCR_SEP BIT(2) + #define RXCR_AB BIT(3) + #define RXCR_AM BIT(4) + #define RXCR_AP BIT(5) + #define RXCR_ARP BIT(6) +#define P2_JLCR (0x58) +#define P2_MPLR (0x5C) + + /* Definition of PAGE3 */ +#define P3_MACASR0 (0x62) + #define P3_MACASR(x) (P3_MACASR0 + 2 * (x)) + #define MACASR_LOWBYTE_MASK 0x00FF + #define MACASR_HIGH_BITS 0x08 +#define P3_MACASR1 (0x64) +#define P3_MACASR2 (0x66) +#define P3_MFAR01 (0x68) +#define P3_MFAR_BASE (0x68) + #define P3_MFAR(x) (P3_MFAR_BASE + 2 * (x)) + +#define P3_MFAR23 (0x6A) +#define P3_MFAR45 (0x6C) +#define P3_MFAR67 (0x6E) +#define P3_VID0FR (0x70) +#define P3_VID1FR (0x72) +#define P3_EECSR (0x74) +#define P3_EEDR (0x76) +#define P3_EECR (0x78) + #define EECR_ADDR_MASK (0x00FF) + #define EECR_READ_ACT BIT(8) + #define EECR_WRITE_ACT BIT(9) + #define EECR_WRITE_DISABLE BIT(10) + #define EECR_WRITE_ENABLE BIT(11) + #define EECR_EE_READY BIT(13) + #define EECR_RELOAD BIT(14) + #define EECR_RESET BIT(15) +#define P3_TPCR (0x7A) + #define TPCR_PATT_MASK (0xFF) + #define TPCR_RAND_PKT_EN BIT(14) + #define TPCR_FIXED_PKT_EN BIT(15) +#define P3_TPLR (0x7C) + /* Definition of PAGE4 */ +#define P4_SPICR (0x8A) + #define SPICR_RCEN BIT(0) + #define SPICR_QCEN BIT(1) + #define SPICR_RBRE BIT(3) + #define SPICR_PMM BIT(4) + #define SPICR_LOOPBACK BIT(8) + #define SPICR_CORE_RES_CLR BIT(10) + #define SPICR_SPI_RES_CLR BIT(11) +#define P4_SPIISMR (0x8C) + +#define P4_COERCR0 (0x92) + #define COERCR0_RXIPCE BIT(0) + #define COERCR0_RXIPVE BIT(1) + #define COERCR0_RXV6PE BIT(2) + #define COERCR0_RXTCPE BIT(3) + #define COERCR0_RXUDPE BIT(4) + #define COERCR0_RXICMP BIT(5) + #define COERCR0_RXIGMP BIT(6) + #define COERCR0_RXICV6 BIT(7) + + #define COERCR0_RXTCPV6 BIT(8) + #define COERCR0_RXUDPV6 BIT(9) + #define COERCR0_RXICMV6 BIT(10) + #define COERCR0_RXIGMV6 BIT(11) + #define COERCR0_RXICV6V6 BIT(12) + + #define COERCR0_DEFAULT (COERCR0_RXIPCE | COERCR0_RXV6PE | \ + COERCR0_RXTCPE | COERCR0_RXUDPE | \ + COERCR0_RXTCPV6 | COERCR0_RXUDPV6) +#define P4_COERCR1 (0x94) + #define COERCR1_IPCEDP BIT(0) + #define COERCR1_IPVEDP BIT(1) + #define COERCR1_V6VEDP BIT(2) + #define COERCR1_TCPEDP BIT(3) + #define COERCR1_UDPEDP BIT(4) + #define COERCR1_ICMPDP BIT(5) + #define COERCR1_IGMPDP BIT(6) + #define COERCR1_ICV6DP BIT(7) + #define COERCR1_RX64TE BIT(8) + #define COERCR1_RXPPPE BIT(9) + #define COERCR1_TCP6DP BIT(10) + #define COERCR1_UDP6DP BIT(11) + #define COERCR1_IC6DP BIT(12) + #define COERCR1_IG6DP BIT(13) + #define COERCR1_ICV66DP BIT(14) + #define COERCR1_RPCE BIT(15) + + #define COERCR1_DEFAULT (COERCR1_RXPPPE) + +#define P4_COETCR0 (0x96) + #define COETCR0_TXIP BIT(0) + #define COETCR0_TXTCP BIT(1) + #define COETCR0_TXUDP BIT(2) + #define COETCR0_TXICMP BIT(3) + #define COETCR0_TXIGMP BIT(4) + #define COETCR0_TXICV6 BIT(5) + #define COETCR0_TXTCPV6 BIT(8) + #define COETCR0_TXUDPV6 BIT(9) + #define COETCR0_TXICMV6 BIT(10) + #define COETCR0_TXIGMV6 BIT(11) + #define COETCR0_TXICV6V6 BIT(12) + + #define COETCR0_DEFAULT (COETCR0_TXIP | COETCR0_TXTCP | \ + COETCR0_TXUDP | COETCR0_TXTCPV6 | \ + COETCR0_TXUDPV6) +#define P4_COETCR1 (0x98) + #define COETCR1_TX64TE BIT(0) + #define COETCR1_TXPPPE BIT(1) + +#define P4_COECEDR (0x9A) +#define P4_L2CECR (0x9C) + + /* Definition of PAGE5 */ +#define P5_WFTR (0xA2) + #define WFTR_2MS (0x01) + #define WFTR_4MS (0x02) + #define WFTR_8MS (0x03) + #define WFTR_16MS (0x04) + #define WFTR_32MS (0x05) + #define WFTR_64MS (0x06) + #define WFTR_128MS (0x07) + #define WFTR_256MS (0x08) + #define WFTR_512MS (0x09) + #define WFTR_1024MS (0x0A) + #define WFTR_2048MS (0x0B) + #define WFTR_4096MS (0x0C) + #define WFTR_8192MS (0x0D) + #define WFTR_16384MS (0x0E) + #define WFTR_32768MS (0x0F) +#define P5_WFCCR (0xA4) +#define P5_WFCR03 (0xA6) + #define WFCR03_F0_EN BIT(0) + #define WFCR03_F1_EN BIT(4) + #define WFCR03_F2_EN BIT(8) + #define WFCR03_F3_EN BIT(12) +#define P5_WFCR47 (0xA8) + #define WFCR47_F4_EN BIT(0) + #define WFCR47_F5_EN BIT(4) + #define WFCR47_F6_EN BIT(8) + #define WFCR47_F7_EN BIT(12) +#define P5_WF0BMR0 (0xAA) +#define P5_WF0BMR1 (0xAC) +#define P5_WF0CR (0xAE) +#define P5_WF0OBR (0xB0) +#define P5_WF1BMR0 (0xB2) +#define P5_WF1BMR1 (0xB4) +#define P5_WF1CR (0xB6) +#define P5_WF1OBR (0xB8) +#define P5_WF2BMR0 (0xBA) +#define P5_WF2BMR1 (0xBC) + + /* Definition of PAGE6 */ +#define P6_WF2CR (0xC2) +#define P6_WF2OBR (0xC4) +#define P6_WF3BMR0 (0xC6) +#define P6_WF3BMR1 (0xC8) +#define P6_WF3CR (0xCA) +#define P6_WF3OBR (0xCC) +#define P6_WF4BMR0 (0xCE) +#define P6_WF4BMR1 (0xD0) +#define P6_WF4CR (0xD2) +#define P6_WF4OBR (0xD4) +#define P6_WF5BMR0 (0xD6) +#define P6_WF5BMR1 (0xD8) +#define P6_WF5CR (0xDA) +#define P6_WF5OBR (0xDC) + +/* Definition of PAGE7 */ +#define P7_WF6BMR0 (0xE2) +#define P7_WF6BMR1 (0xE4) +#define P7_WF6CR (0xE6) +#define P7_WF6OBR (0xE8) +#define P7_WF7BMR0 (0xEA) +#define P7_WF7BMR1 (0xEC) +#define P7_WF7CR (0xEE) +#define P7_WF7OBR (0xF0) +#define P7_WFR01 (0xF2) +#define P7_WFR23 (0xF4) +#define P7_WFR45 (0xF6) +#define P7_WFR67 (0xF8) +#define P7_WFPC0 (0xFA) +#define P7_WFPC1 (0xFC) + +/* Tx headers structure */ +struct tx_sop_header { + /* bit 15-11: flags, bit 10-0: packet length */ + u16 flags_len; + /* bit 15-11: sequence number, bit 11-0: packet length bar */ + u16 seq_lenbar; +}; + +struct tx_segment_header { + /* bit 15-14: flags, bit 13-11: segment number */ + /* bit 10-0: segment length */ + u16 flags_seqnum_seglen; + /* bit 15-14: end offset, bit 13-11: start offset */ + /* bit 10-0: segment length bar */ + u16 eo_so_seglenbar; +}; + +struct tx_eop_header { + /* bit 15-11: sequence number, bit 10-0: packet length */ + u16 seq_len; + /* bit 15-11: sequence number bar, bit 10-0: packet length bar */ + u16 seqbar_lenbar; +}; + +struct tx_pkt_info { + struct tx_sop_header sop; + struct tx_segment_header seg; + struct tx_eop_header eop; + u16 pkt_len; + u16 seq_num; +}; + +/* Rx headers structure */ +struct rx_header { + u16 flags_len; + u16 seq_lenbar; + u16 flags; +}; + +extern unsigned long ax88796c_no_regs_mask[]; + +#endif /* #ifndef _AX88796C_MAIN_H */ diff --git a/drivers/net/ethernet/asix/ax88796c_spi.c b/drivers/net/ethernet/asix/ax88796c_spi.c new file mode 100644 index 000000000000..94df4f96d2be --- /dev/null +++ b/drivers/net/ethernet/asix/ax88796c_spi.c @@ -0,0 +1,115 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2010 ASIX Electronics Corporation + * Copyright (c) 2020 Samsung Electronics Co., Ltd. + * + * ASIX AX88796C SPI Fast Ethernet Linux driver + */ + +#define pr_fmt(fmt) "ax88796c: " fmt + +#include +#include + +#include "ax88796c_spi.h" + +const u8 ax88796c_rx_cmd_buf[5] = {AX_SPICMD_READ_RXQ, 0xFF, 0xFF, 0xFF, 0xFF}; +const u8 ax88796c_tx_cmd_buf[4] = {AX_SPICMD_WRITE_TXQ, 0xFF, 0xFF, 0xFF}; + +/* driver bus management functions */ +int axspi_wakeup(struct axspi_data *ax_spi) +{ + int ret; + + ax_spi->cmd_buf[0] = AX_SPICMD_EXIT_PWD; /* OP */ + ret = spi_write(ax_spi->spi, ax_spi->cmd_buf, 1); + if (ret) + dev_err(&ax_spi->spi->dev, "%s() failed: ret = %d\n", __func__, ret); + return ret; +} + +int axspi_read_status(struct axspi_data *ax_spi, struct spi_status *status) +{ + int ret; + + /* OP */ + ax_spi->cmd_buf[0] = AX_SPICMD_READ_STATUS; + ret = spi_write_then_read(ax_spi->spi, ax_spi->cmd_buf, 1, (u8 *)&status, 3); + if (ret) + dev_err(&ax_spi->spi->dev, "%s() failed: ret = %d\n", __func__, ret); + else + le16_to_cpus(&status->isr); + + return ret; +} + +int axspi_read_rxq(struct axspi_data *ax_spi, void *data, int len) +{ + struct spi_transfer *xfer = ax_spi->spi_rx_xfer; + int ret; + + memcpy(ax_spi->cmd_buf, ax88796c_rx_cmd_buf, 5); + + xfer->tx_buf = ax_spi->cmd_buf; + xfer->rx_buf = NULL; + xfer->len = ax_spi->comp ? 2 : 5; + xfer->bits_per_word = 8; + spi_message_add_tail(xfer, &ax_spi->rx_msg); + + xfer++; + xfer->rx_buf = data; + xfer->tx_buf = NULL; + xfer->len = len; + xfer->bits_per_word = 8; + spi_message_add_tail(xfer, &ax_spi->rx_msg); + ret = spi_sync(ax_spi->spi, &ax_spi->rx_msg); + if (ret) + dev_err(&ax_spi->spi->dev, "%s() failed: ret = %d\n", __func__, ret); + + return ret; +} + +int axspi_write_txq(const struct axspi_data *ax_spi, void *data, int len) +{ + return spi_write(ax_spi->spi, data, len); +} + +u16 axspi_read_reg(struct axspi_data *ax_spi, u8 reg) +{ + int ret; + int len = ax_spi->comp ? 3 : 4; + + ax_spi->cmd_buf[0] = 0x03; /* OP code read register */ + ax_spi->cmd_buf[1] = reg; /* register address */ + ax_spi->cmd_buf[2] = 0xFF; /* dumy cycle */ + ax_spi->cmd_buf[3] = 0xFF; /* dumy cycle */ + ret = spi_write_then_read(ax_spi->spi, + ax_spi->cmd_buf, len, + ax_spi->rx_buf, 2); + if (ret) { + dev_err(&ax_spi->spi->dev, + "%s() failed: ret = %d\n", __func__, ret); + return 0xFFFF; + } + + le16_to_cpus((u16 *)ax_spi->rx_buf); + + return *(u16 *)ax_spi->rx_buf; +} + +int axspi_write_reg(struct axspi_data *ax_spi, u8 reg, u16 value) +{ + int ret; + + memset(ax_spi->cmd_buf, 0, sizeof(ax_spi->cmd_buf)); + ax_spi->cmd_buf[0] = AX_SPICMD_WRITE_REG; /* OP code read register */ + ax_spi->cmd_buf[1] = reg; /* register address */ + ax_spi->cmd_buf[2] = value; + ax_spi->cmd_buf[3] = value >> 8; + + ret = spi_write(ax_spi->spi, ax_spi->cmd_buf, 4); + if (ret) + dev_err(&ax_spi->spi->dev, "%s() failed: ret = %d\n", __func__, ret); + return ret; +} + diff --git a/drivers/net/ethernet/asix/ax88796c_spi.h b/drivers/net/ethernet/asix/ax88796c_spi.h new file mode 100644 index 000000000000..5bcf91f603fb --- /dev/null +++ b/drivers/net/ethernet/asix/ax88796c_spi.h @@ -0,0 +1,69 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2010 ASIX Electronics Corporation + * Copyright (c) 2020 Samsung Electronics Co., Ltd. + * + * ASIX AX88796C SPI Fast Ethernet Linux driver + */ + +#ifndef _AX88796C_SPI_H +#define _AX88796C_SPI_H + +#include +#include + +/* Definition of SPI command */ +#define AX_SPICMD_WRITE_TXQ 0x02 +#define AX_SPICMD_READ_REG 0x03 +#define AX_SPICMD_READ_STATUS 0x05 +#define AX_SPICMD_READ_RXQ 0x0B +#define AX_SPICMD_BIDIR_WRQ 0xB2 +#define AX_SPICMD_WRITE_REG 0xD8 +#define AX_SPICMD_EXIT_PWD 0xAB + +extern const u8 ax88796c_rx_cmd_buf[]; +extern const u8 ax88796c_tx_cmd_buf[]; + +struct axspi_data { + struct spi_device *spi; + struct spi_message rx_msg; + struct spi_transfer spi_rx_xfer[2]; + u8 cmd_buf[6]; + u8 rx_buf[6]; + u8 comp; +}; + +struct spi_status { + u16 isr; + u8 status; +# define AX_STATUS_READY 0x80 +}; + +int axspi_read_rxq(struct axspi_data *ax_spi, void *data, int len); +int axspi_write_txq(const struct axspi_data *ax_spi, void *data, int len); +u16 axspi_read_reg(struct axspi_data *ax_spi, u8 reg); +int axspi_write_reg(struct axspi_data *ax_spi, u8 reg, u16 value); +int axspi_read_status(struct axspi_data *ax_spi, struct spi_status *status); +int axspi_wakeup(struct axspi_data *ax_spi); + +static inline u16 AX_READ(struct axspi_data *ax_spi, u8 offset) +{ + return axspi_read_reg(ax_spi, offset); +} + +static inline int AX_WRITE(struct axspi_data *ax_spi, u16 value, u8 offset) +{ + return axspi_write_reg(ax_spi, offset, value); +} + +static inline int AX_READ_STATUS(struct axspi_data *ax_spi, + struct spi_status *status) +{ + return axspi_read_status(ax_spi, status); +} + +static inline int AX_WAKEUP(struct axspi_data *ax_spi) +{ + return axspi_wakeup(ax_spi); +} +#endif diff --git a/drivers/net/ethernet/atheros/ag71xx.c b/drivers/net/ethernet/atheros/ag71xx.c index 1aaaf8a4e7c5..ada3a9f0c8c8 100644 --- a/drivers/net/ethernet/atheros/ag71xx.c +++ b/drivers/net/ethernet/atheros/ag71xx.c @@ -1971,7 +1971,7 @@ static int ag71xx_probe(struct platform_device *pdev) err = of_get_ethdev_address(np, ndev); if (err) { netif_err(ag, probe, ndev, "invalid MAC address, using random address\n"); - eth_random_addr(ndev->dev_addr); + eth_hw_addr_random(ndev); } err = of_get_phy_mode(np, &ag->phy_if_mode); diff --git a/drivers/net/ethernet/broadcom/b44.c b/drivers/net/ethernet/broadcom/b44.c index 55c9e6fcb471..969591bbc066 100644 --- a/drivers/net/ethernet/broadcom/b44.c +++ b/drivers/net/ethernet/broadcom/b44.c @@ -218,7 +218,8 @@ static inline void __b44_cam_read(struct b44 *bp, unsigned char *data, int index data[1] = (val >> 0) & 0xFF; } -static inline void __b44_cam_write(struct b44 *bp, unsigned char *data, int index) +static inline void __b44_cam_write(struct b44 *bp, + const unsigned char *data, int index) { u32 val; @@ -1507,7 +1508,8 @@ static void bwfilter_table(struct b44 *bp, u8 *pp, u32 bytes, u32 table_offset) } } -static int b44_magic_pattern(u8 *macaddr, u8 *ppattern, u8 *pmask, int offset) +static int b44_magic_pattern(const u8 *macaddr, u8 *ppattern, u8 *pmask, + int offset) { int magicsync = 6; int k, j, len = offset; diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index b813745e8de3..40933bf5a710 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -1818,7 +1818,7 @@ static inline void umac_reset(struct bcm_sysport_priv *priv) } static void umac_set_hw_addr(struct bcm_sysport_priv *priv, - unsigned char *addr) + const unsigned char *addr) { u32 mac0 = (addr[0] << 24) | (addr[1] << 16) | (addr[2] << 8) | addr[3]; diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c index d2c7834850cc..7b525c65bacb 100644 --- a/drivers/net/ethernet/broadcom/bgmac.c +++ b/drivers/net/ethernet/broadcom/bgmac.c @@ -768,7 +768,7 @@ static void bgmac_umac_cmd_maskset(struct bgmac *bgmac, u32 mask, u32 set, udelay(2); } -static void bgmac_write_mac_address(struct bgmac *bgmac, u8 *addr) +static void bgmac_write_mac_address(struct bgmac *bgmac, const u8 *addr) { u32 tmp; diff --git a/drivers/net/ethernet/broadcom/bnx2.c b/drivers/net/ethernet/broadcom/bnx2.c index 248b81249cb0..babc955ba64e 100644 --- a/drivers/net/ethernet/broadcom/bnx2.c +++ b/drivers/net/ethernet/broadcom/bnx2.c @@ -2704,7 +2704,7 @@ bnx2_alloc_bad_rbuf(struct bnx2 *bp) } static void -bnx2_set_mac_addr(struct bnx2 *bp, u8 *mac_addr, u32 pos) +bnx2_set_mac_addr(struct bnx2 *bp, const u8 *mac_addr, u32 pos) { u32 val; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h index e789430f407c..2b06d78baa08 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h @@ -1994,7 +1994,7 @@ int bnx2x_idle_chk(struct bnx2x *bp); * operation has been successfully scheduled and a negative - if a requested * operations has failed. */ -int bnx2x_set_mac_one(struct bnx2x *bp, u8 *mac, +int bnx2x_set_mac_one(struct bnx2x *bp, const u8 *mac, struct bnx2x_vlan_mac_obj *obj, bool set, int mac_type, unsigned long *ramrod_flags); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index ef49e38ae027..aec666e97683 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -8417,7 +8417,7 @@ alloc_mem_err: * Init service functions */ -int bnx2x_set_mac_one(struct bnx2x *bp, u8 *mac, +int bnx2x_set_mac_one(struct bnx2x *bp, const u8 *mac, struct bnx2x_vlan_mac_obj *obj, bool set, int mac_type, unsigned long *ramrod_flags) { @@ -9146,7 +9146,7 @@ u32 bnx2x_send_unload_req(struct bnx2x *bp, int unload_mode) else if (bp->wol) { u32 emac_base = port ? GRCBASE_EMAC1 : GRCBASE_EMAC0; - u8 *mac_addr = bp->dev->dev_addr; + const u8 *mac_addr = bp->dev->dev_addr; struct pci_dev *pdev = bp->pdev; u32 val; u16 pmc; @@ -11823,9 +11823,10 @@ static void bnx2x_get_mac_hwinfo(struct bnx2x *bp) u32 val, val2; int func = BP_ABS_FUNC(bp); int port = BP_PORT(bp); + u8 addr[ETH_ALEN] = {}; /* Zero primary MAC configuration */ - eth_zero_addr(bp->dev->dev_addr); + eth_hw_addr_set(bp->dev, addr); if (BP_NOMCP(bp)) { BNX2X_ERROR("warning: random MAC workaround active\n"); @@ -11834,8 +11835,10 @@ static void bnx2x_get_mac_hwinfo(struct bnx2x *bp) val2 = MF_CFG_RD(bp, func_mf_config[func].mac_upper); val = MF_CFG_RD(bp, func_mf_config[func].mac_lower); if ((val2 != FUNC_MF_CFG_UPPERMAC_DEFAULT) && - (val != FUNC_MF_CFG_LOWERMAC_DEFAULT)) - bnx2x_set_mac_buf(bp->dev->dev_addr, val, val2); + (val != FUNC_MF_CFG_LOWERMAC_DEFAULT)) { + bnx2x_set_mac_buf(addr, val, val2); + eth_hw_addr_set(bp->dev, addr); + } if (CNIC_SUPPORT(bp)) bnx2x_get_cnic_mac_hwinfo(bp); @@ -11843,7 +11846,8 @@ static void bnx2x_get_mac_hwinfo(struct bnx2x *bp) /* in SF read MACs from port configuration */ val2 = SHMEM_RD(bp, dev_info.port_hw_config[port].mac_upper); val = SHMEM_RD(bp, dev_info.port_hw_config[port].mac_lower); - bnx2x_set_mac_buf(bp->dev->dev_addr, val, val2); + bnx2x_set_mac_buf(addr, val, val2); + eth_hw_addr_set(bp->dev, addr); if (CNIC_SUPPORT(bp)) bnx2x_get_cnic_mac_hwinfo(bp); @@ -12291,7 +12295,9 @@ static int bnx2x_init_bp(struct bnx2x *bp) if (rc) return rc; } else { - eth_zero_addr(bp->dev->dev_addr); + static const u8 zero_addr[ETH_ALEN] = {}; + + eth_hw_addr_set(bp->dev, zero_addr); } bnx2x_set_modes_bitmap(bp); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h index 966d5722c5e2..8c2cf5519787 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h @@ -508,7 +508,8 @@ int bnx2x_vfpf_init(struct bnx2x *bp); void bnx2x_vfpf_close_vf(struct bnx2x *bp); int bnx2x_vfpf_setup_q(struct bnx2x *bp, struct bnx2x_fastpath *fp, bool is_leading); -int bnx2x_vfpf_config_mac(struct bnx2x *bp, u8 *addr, u8 vf_qid, bool set); +int bnx2x_vfpf_config_mac(struct bnx2x *bp, const u8 *addr, u8 vf_qid, + bool set); int bnx2x_vfpf_config_rss(struct bnx2x *bp, struct bnx2x_config_rss_params *params); int bnx2x_vfpf_set_mcast(struct net_device *dev); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c index 7c96f943c6f3..c9129b9ba446 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c @@ -721,7 +721,7 @@ out: } /* request pf to add a mac for the vf */ -int bnx2x_vfpf_config_mac(struct bnx2x *bp, u8 *addr, u8 vf_qid, bool set) +int bnx2x_vfpf_config_mac(struct bnx2x *bp, const u8 *addr, u8 vf_qid, bool set) { struct vfpf_set_q_filters_tlv *req = &bp->vf2pf_mbox->req.set_q_filters; struct pfvf_general_resp_tlv *resp = &bp->vf2pf_mbox->resp.general_resp; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index f05f4271d4c1..66263aa0d96b 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -4869,7 +4869,7 @@ static int bnxt_hwrm_cfa_ntuple_filter_alloc(struct bnxt *bp, #endif static int bnxt_hwrm_set_vnic_filter(struct bnxt *bp, u16 vnic_id, u16 idx, - u8 *mac_addr) + const u8 *mac_addr) { struct hwrm_cfa_l2_filter_alloc_output *resp; struct hwrm_cfa_l2_filter_alloc_input *req; @@ -6366,7 +6366,7 @@ static int __bnxt_reserve_rings(struct bnxt *bp) if (rx_rings != bp->rx_nr_rings) { netdev_warn(bp->dev, "Able to reserve only %d out of %d requested RX rings\n", rx_rings, bp->rx_nr_rings); - if ((bp->dev->priv_flags & IFF_RXFH_CONFIGURED) && + if (netif_is_rxfh_configured(bp->dev) && (bnxt_get_nr_rss_ctxs(bp, bp->rx_nr_rings) != bnxt_get_nr_rss_ctxs(bp, rx_rings) || bnxt_get_max_rss_ring(bp) >= rx_rings)) { diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index 7260910e75fb..fbb56b1f70fd 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -909,7 +909,7 @@ static int bnxt_set_channels(struct net_device *dev, if (bnxt_get_nr_rss_ctxs(bp, req_rx_rings) != bnxt_get_nr_rss_ctxs(bp, bp->rx_nr_rings) && - (dev->priv_flags & IFF_RXFH_CONFIGURED)) { + netif_is_rxfh_configured(dev)) { netdev_warn(dev, "RSS table size change required, RSS table entries must be default to proceed\n"); return -EINVAL; } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c index d4ebc5d710ba..1d177fed44a6 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c @@ -1151,7 +1151,7 @@ void bnxt_hwrm_exec_fwd_req(struct bnxt *bp) } } -int bnxt_approve_mac(struct bnxt *bp, u8 *mac, bool strict) +int bnxt_approve_mac(struct bnxt *bp, const u8 *mac, bool strict) { struct hwrm_func_vf_cfg_input *req; int rc = 0; @@ -1246,7 +1246,7 @@ void bnxt_update_vf_mac(struct bnxt *bp) { } -int bnxt_approve_mac(struct bnxt *bp, u8 *mac, bool strict) +int bnxt_approve_mac(struct bnxt *bp, const u8 *mac, bool strict) { return 0; } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h index 995535e4c11b..9a4bacba477b 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h @@ -41,5 +41,5 @@ int bnxt_cfg_hw_sriov(struct bnxt *bp, int *num_vfs, bool reset); void bnxt_sriov_disable(struct bnxt *); void bnxt_hwrm_exec_fwd_req(struct bnxt *); void bnxt_update_vf_mac(struct bnxt *); -int bnxt_approve_mac(struct bnxt *, u8 *, bool); +int bnxt_approve_mac(struct bnxt *, const u8 *, bool); #endif diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 83c55e7b099f..5da9c00b43b1 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -3266,7 +3266,7 @@ static void bcmgenet_umac_reset(struct bcmgenet_priv *priv) } static void bcmgenet_set_hw_addr(struct bcmgenet_priv *priv, - unsigned char *addr) + const unsigned char *addr) { bcmgenet_umac_writel(priv, get_unaligned_be32(&addr[0]), UMAC_MAC0); bcmgenet_umac_writel(priv, get_unaligned_be16(&addr[4]), UMAC_MAC1); @@ -3560,7 +3560,7 @@ static void bcmgenet_timeout(struct net_device *dev, unsigned int txqueue) #define MAX_MDF_FILTER 17 static inline void bcmgenet_set_mdf_addr(struct bcmgenet_priv *priv, - unsigned char *addr, + const unsigned char *addr, int *i) { bcmgenet_umac_writel(priv, addr[0] << 8 | addr[1], @@ -4085,8 +4085,12 @@ static int bcmgenet_probe(struct platform_device *pdev) eth_hw_addr_set(dev, pd->mac_address); else if (device_get_ethdev_address(&pdev->dev, dev)) - if (has_acpi_companion(&pdev->dev)) - bcmgenet_get_hw_addr(priv, dev->dev_addr); + if (has_acpi_companion(&pdev->dev)) { + u8 addr[ETH_ALEN]; + + bcmgenet_get_hw_addr(priv, addr); + eth_hw_addr_set(dev, addr); + } if (!is_valid_ether_addr(dev->dev_addr)) { dev_warn(&pdev->dev, "using random Ethernet MAC\n"); diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index 5a50ea75094f..b1328c5524b5 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -3942,7 +3942,8 @@ static int tg3_load_tso_firmware(struct tg3 *tp) } /* tp->lock is held. */ -static void __tg3_set_one_mac_addr(struct tg3 *tp, u8 *mac_addr, int index) +static void __tg3_set_one_mac_addr(struct tg3 *tp, const u8 *mac_addr, + int index) { u32 addr_high, addr_low; @@ -5746,7 +5747,6 @@ static int tg3_setup_fiber_phy(struct tg3 *tp, bool force_reset) tw32_f(MAC_EVENT, MAC_EVENT_LNKSTATE_CHANGED); udelay(40); - current_link_up = false; tp->link_config.rmt_adv = 0; mac_status = tr32(MAC_STATUS); @@ -10273,8 +10273,7 @@ static int tg3_reset_hw(struct tg3 *tp, bool reset_phy) if (tg3_asic_rev(tp) == ASIC_REV_5705 && tg3_chip_rev_id(tp) != CHIPREV_ID_5705_A0) { - if (tg3_flag(tp, TSO_CAPABLE) && - tg3_asic_rev(tp) == ASIC_REV_5705) { + if (tg3_flag(tp, TSO_CAPABLE)) { rdmac_mode |= RDMAC_MODE_FIFO_SIZE_128; } else if (!(tr32(TG3PCI_PCISTATE) & PCISTATE_BUS_SPEED_HIGH) && !tg3_flag(tp, IS_5788)) { @@ -16911,19 +16910,18 @@ static int tg3_get_invariants(struct tg3 *tp, const struct pci_device_id *ent) return err; } -static int tg3_get_device_address(struct tg3 *tp) +static int tg3_get_device_address(struct tg3 *tp, u8 *addr) { - struct net_device *dev = tp->dev; u32 hi, lo, mac_offset; int addr_ok = 0; int err; - if (!eth_platform_get_mac_address(&tp->pdev->dev, dev->dev_addr)) + if (!eth_platform_get_mac_address(&tp->pdev->dev, addr)) return 0; if (tg3_flag(tp, IS_SSB_CORE)) { - err = ssb_gige_get_macaddr(tp->pdev, &dev->dev_addr[0]); - if (!err && is_valid_ether_addr(&dev->dev_addr[0])) + err = ssb_gige_get_macaddr(tp->pdev, addr); + if (!err && is_valid_ether_addr(addr)) return 0; } @@ -16947,41 +16945,41 @@ static int tg3_get_device_address(struct tg3 *tp) /* First try to get it from MAC address mailbox. */ tg3_read_mem(tp, NIC_SRAM_MAC_ADDR_HIGH_MBOX, &hi); if ((hi >> 16) == 0x484b) { - dev->dev_addr[0] = (hi >> 8) & 0xff; - dev->dev_addr[1] = (hi >> 0) & 0xff; + addr[0] = (hi >> 8) & 0xff; + addr[1] = (hi >> 0) & 0xff; tg3_read_mem(tp, NIC_SRAM_MAC_ADDR_LOW_MBOX, &lo); - dev->dev_addr[2] = (lo >> 24) & 0xff; - dev->dev_addr[3] = (lo >> 16) & 0xff; - dev->dev_addr[4] = (lo >> 8) & 0xff; - dev->dev_addr[5] = (lo >> 0) & 0xff; + addr[2] = (lo >> 24) & 0xff; + addr[3] = (lo >> 16) & 0xff; + addr[4] = (lo >> 8) & 0xff; + addr[5] = (lo >> 0) & 0xff; /* Some old bootcode may report a 0 MAC address in SRAM */ - addr_ok = is_valid_ether_addr(&dev->dev_addr[0]); + addr_ok = is_valid_ether_addr(addr); } if (!addr_ok) { /* Next, try NVRAM. */ if (!tg3_flag(tp, NO_NVRAM) && !tg3_nvram_read_be32(tp, mac_offset + 0, &hi) && !tg3_nvram_read_be32(tp, mac_offset + 4, &lo)) { - memcpy(&dev->dev_addr[0], ((char *)&hi) + 2, 2); - memcpy(&dev->dev_addr[2], (char *)&lo, sizeof(lo)); + memcpy(&addr[0], ((char *)&hi) + 2, 2); + memcpy(&addr[2], (char *)&lo, sizeof(lo)); } /* Finally just fetch it out of the MAC control regs. */ else { hi = tr32(MAC_ADDR_0_HIGH); lo = tr32(MAC_ADDR_0_LOW); - dev->dev_addr[5] = lo & 0xff; - dev->dev_addr[4] = (lo >> 8) & 0xff; - dev->dev_addr[3] = (lo >> 16) & 0xff; - dev->dev_addr[2] = (lo >> 24) & 0xff; - dev->dev_addr[1] = hi & 0xff; - dev->dev_addr[0] = (hi >> 8) & 0xff; + addr[5] = lo & 0xff; + addr[4] = (lo >> 8) & 0xff; + addr[3] = (lo >> 16) & 0xff; + addr[2] = (lo >> 24) & 0xff; + addr[1] = hi & 0xff; + addr[0] = (hi >> 8) & 0xff; } } - if (!is_valid_ether_addr(&dev->dev_addr[0])) + if (!is_valid_ether_addr(addr)) return -EINVAL; return 0; } @@ -17557,6 +17555,7 @@ static int tg3_init_one(struct pci_dev *pdev, char str[40]; u64 dma_mask, persist_dma_mask; netdev_features_t features = 0; + u8 addr[ETH_ALEN] __aligned(2); err = pci_enable_device(pdev); if (err) { @@ -17779,12 +17778,13 @@ static int tg3_init_one(struct pci_dev *pdev, tp->rx_pending = 63; } - err = tg3_get_device_address(tp); + err = tg3_get_device_address(tp, addr); if (err) { dev_err(&pdev->dev, "Could not obtain valid ethernet address, aborting\n"); goto err_out_apeunmap; } + eth_hw_addr_set(dev, addr); intmbx = MAILBOX_INTERRUPT_0 + TG3_64BIT_REG_LOW; rcvmbx = MAILBOX_RCVRET_CON_IDX_0 + TG3_64BIT_REG_LOW; diff --git a/drivers/net/ethernet/brocade/bna/bnad.c b/drivers/net/ethernet/brocade/bna/bnad.c index b1947fd9a07c..bbdc829c3524 100644 --- a/drivers/net/ethernet/brocade/bna/bnad.c +++ b/drivers/net/ethernet/brocade/bna/bnad.c @@ -3515,7 +3515,6 @@ static void bnad_uninit(struct bnad *bnad) { if (bnad->work_q) { - flush_workqueue(bnad->work_q); destroy_workqueue(bnad->work_q); bnad->work_q = NULL; } diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 683f14665c2c..029dea2873e3 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -313,7 +313,7 @@ static void macb_get_hwaddr(struct macb *bp) addr[5] = (top >> 8) & 0xff; if (is_valid_ether_addr(addr)) { - memcpy(bp->dev->dev_addr, addr, sizeof(addr)); + eth_hw_addr_set(bp->dev, addr); return; } } diff --git a/drivers/net/ethernet/calxeda/xgmac.c b/drivers/net/ethernet/calxeda/xgmac.c index dc51f36fdf2a..457cb7121000 100644 --- a/drivers/net/ethernet/calxeda/xgmac.c +++ b/drivers/net/ethernet/calxeda/xgmac.c @@ -607,7 +607,7 @@ static inline void xgmac_mac_disable(void __iomem *ioaddr) writel(value, ioaddr + XGMAC_CONTROL); } -static void xgmac_set_mac_addr(void __iomem *ioaddr, unsigned char *addr, +static void xgmac_set_mac_addr(void __iomem *ioaddr, const unsigned char *addr, int num) { u32 data; @@ -1693,6 +1693,7 @@ static int xgmac_probe(struct platform_device *pdev) struct resource *res; struct net_device *ndev = NULL; struct xgmac_priv *priv = NULL; + u8 addr[ETH_ALEN]; u32 uid; res = platform_get_resource(pdev, IORESOURCE_MEM, 0); @@ -1785,7 +1786,8 @@ static int xgmac_probe(struct platform_device *pdev) ndev->max_mtu = XGMAC_MAX_MTU; /* Get the MAC address */ - xgmac_get_mac_addr(priv->base, ndev->dev_addr, 0); + xgmac_get_mac_addr(priv->base, addr, 0); + eth_hw_addr_set(ndev, addr); if (!is_valid_ether_addr(ndev->dev_addr)) netdev_warn(ndev, "MAC address %pM not valid", ndev->dev_addr); diff --git a/drivers/net/ethernet/cavium/liquidio/lio_core.c b/drivers/net/ethernet/cavium/liquidio/lio_core.c index ec7928b54e4a..73cb03266549 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_core.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_core.c @@ -490,7 +490,6 @@ void cleanup_rx_oom_poll_fn(struct net_device *netdev) wq = &lio->rxq_status_wq[q_no]; if (wq->wq) { cancel_delayed_work_sync(&wq->wk.work); - flush_workqueue(wq->wq); destroy_workqueue(wq->wq); wq->wq = NULL; } diff --git a/drivers/net/ethernet/chelsio/cxgb/gmac.h b/drivers/net/ethernet/chelsio/cxgb/gmac.h index dfa77491a910..5913eaf442b5 100644 --- a/drivers/net/ethernet/chelsio/cxgb/gmac.h +++ b/drivers/net/ethernet/chelsio/cxgb/gmac.h @@ -117,7 +117,7 @@ struct cmac_ops { const struct cmac_statistics *(*statistics_update)(struct cmac *, int); int (*macaddress_get)(struct cmac *, u8 mac_addr[6]); - int (*macaddress_set)(struct cmac *, u8 mac_addr[6]); + int (*macaddress_set)(struct cmac *, const u8 mac_addr[6]); }; typedef struct _cmac_instance cmac_instance; diff --git a/drivers/net/ethernet/chelsio/cxgb/pm3393.c b/drivers/net/ethernet/chelsio/cxgb/pm3393.c index c27908e66f5e..0bb37e4680c7 100644 --- a/drivers/net/ethernet/chelsio/cxgb/pm3393.c +++ b/drivers/net/ethernet/chelsio/cxgb/pm3393.c @@ -496,7 +496,7 @@ static int pm3393_macaddress_get(struct cmac *cmac, u8 mac_addr[6]) return 0; } -static int pm3393_macaddress_set(struct cmac *cmac, u8 ma[6]) +static int pm3393_macaddress_set(struct cmac *cmac, const u8 ma[6]) { u32 val, lo, mid, hi, enabled = cmac->instance->enabled; diff --git a/drivers/net/ethernet/chelsio/cxgb/vsc7326.c b/drivers/net/ethernet/chelsio/cxgb/vsc7326.c index a19284bdb80e..2ad3efb550c2 100644 --- a/drivers/net/ethernet/chelsio/cxgb/vsc7326.c +++ b/drivers/net/ethernet/chelsio/cxgb/vsc7326.c @@ -379,7 +379,7 @@ static int mac_intr_clear(struct cmac *mac) } /* Expect MAC address to be in network byte order. */ -static int mac_set_address(struct cmac* mac, u8 addr[6]) +static int mac_set_address(struct cmac* mac, const u8 addr[6]) { u32 val; int port = mac->instance->index; diff --git a/drivers/net/ethernet/chelsio/cxgb3/common.h b/drivers/net/ethernet/chelsio/cxgb3/common.h index b706f2fbe4f4..a309016f7f8c 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/common.h +++ b/drivers/net/ethernet/chelsio/cxgb3/common.h @@ -710,7 +710,7 @@ int t3_mac_enable(struct cmac *mac, int which); int t3_mac_disable(struct cmac *mac, int which); int t3_mac_set_mtu(struct cmac *mac, unsigned int mtu); int t3_mac_set_rx_mode(struct cmac *mac, struct net_device *dev); -int t3_mac_set_address(struct cmac *mac, unsigned int idx, u8 addr[6]); +int t3_mac_set_address(struct cmac *mac, unsigned int idx, const u8 addr[6]); int t3_mac_set_num_ucast(struct cmac *mac, int n); const struct mac_stats *t3_mac_update_stats(struct cmac *mac); int t3_mac_set_speed_duplex_fc(struct cmac *mac, int speed, int duplex, int fc); diff --git a/drivers/net/ethernet/chelsio/cxgb3/xgmac.c b/drivers/net/ethernet/chelsio/cxgb3/xgmac.c index 3af19a550372..1bdc6cad1e49 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/xgmac.c +++ b/drivers/net/ethernet/chelsio/cxgb3/xgmac.c @@ -240,7 +240,7 @@ static void set_addr_filter(struct cmac *mac, int idx, const u8 * addr) } /* Set one of the station's unicast MAC addresses. */ -int t3_mac_set_address(struct cmac *mac, unsigned int idx, u8 addr[6]) +int t3_mac_set_address(struct cmac *mac, unsigned int idx, const u8 addr[6]) { if (idx >= mac->nucast) return -EINVAL; diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c index bcad69c48074..4af5561cbfc5 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c +++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c @@ -870,7 +870,7 @@ static void do_abort_syn_rcv(struct sock *child, struct sock *parent) * created only after 3 way handshake is done. */ sock_orphan(child); - percpu_counter_inc((child)->sk_prot->orphan_count); + INC_ORPHAN_COUNT(child); chtls_release_resources(child); chtls_conn_done(child); } else { diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.h b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.h index b1161bdeda4d..f61ca657601c 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.h +++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.h @@ -95,7 +95,7 @@ struct deferred_skb_cb { #define WSCALE_OK(tp) ((tp)->rx_opt.wscale_ok) #define TSTAMP_OK(tp) ((tp)->rx_opt.tstamp_ok) #define SACK_OK(tp) ((tp)->rx_opt.sack_ok) -#define INC_ORPHAN_COUNT(sk) percpu_counter_inc((sk)->sk_prot->orphan_count) +#define INC_ORPHAN_COUNT(sk) this_cpu_inc(*(sk)->sk_prot->orphan_count) /* TLS SKB */ #define skb_ulp_tls_inline(skb) (ULP_SKB_CB(skb)->ulp.tls.ofld) diff --git a/drivers/net/ethernet/cirrus/cs89x0.c b/drivers/net/ethernet/cirrus/cs89x0.c index bd7920ab166f..4a97aa8e1387 100644 --- a/drivers/net/ethernet/cirrus/cs89x0.c +++ b/drivers/net/ethernet/cirrus/cs89x0.c @@ -1314,6 +1314,7 @@ cs89x0_probe1(struct net_device *dev, void __iomem *ioaddr, int modular) int tmp; unsigned rev_type = 0; int eeprom_buff[CHKSUM_LEN]; + u8 addr[ETH_ALEN]; int retval; /* Initialize the device structure. */ @@ -1387,9 +1388,10 @@ cs89x0_probe1(struct net_device *dev, void __iomem *ioaddr, int modular) for (i = 0; i < ETH_ALEN / 2; i++) { unsigned int Addr; Addr = readreg(dev, PP_IA + i * 2); - dev->dev_addr[i * 2] = Addr & 0xFF; - dev->dev_addr[i * 2 + 1] = Addr >> 8; + addr[i * 2] = Addr & 0xFF; + addr[i * 2 + 1] = Addr >> 8; } + eth_hw_addr_set(dev, addr); /* Load the Adapter Configuration. * Note: Barring any more specific information from some @@ -1464,9 +1466,10 @@ cs89x0_probe1(struct net_device *dev, void __iomem *ioaddr, int modular) /* eeprom_buff has 32-bit ints, so we can't just memcpy it */ /* store the initial memory base address */ for (i = 0; i < ETH_ALEN / 2; i++) { - dev->dev_addr[i * 2] = eeprom_buff[i]; - dev->dev_addr[i * 2 + 1] = eeprom_buff[i] >> 8; + addr[i * 2] = eeprom_buff[i]; + addr[i * 2 + 1] = eeprom_buff[i] >> 8; } + eth_hw_addr_set(dev, addr); cs89_dbg(1, debug, "%s: new adapter_cnf: 0x%x\n", dev->name, lp->adapter_cnf); } diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c index 66348cc3aaaf..aacf141986d5 100644 --- a/drivers/net/ethernet/cisco/enic/enic_main.c +++ b/drivers/net/ethernet/cisco/enic/enic_main.c @@ -1098,6 +1098,7 @@ static int enic_set_vf_mac(struct net_device *netdev, int vf, u8 *mac) static int enic_set_vf_port(struct net_device *netdev, int vf, struct nlattr *port[]) { + static const u8 zero_addr[ETH_ALEN] = {}; struct enic *enic = netdev_priv(netdev); struct enic_port_profile prev_pp; struct enic_port_profile *pp; @@ -1162,7 +1163,7 @@ static int enic_set_vf_port(struct net_device *netdev, int vf, } else { memset(pp, 0, sizeof(*pp)); if (vf == PORT_SELF_VF) - eth_zero_addr(netdev->dev_addr); + eth_hw_addr_set(netdev, zero_addr); } } else { /* Set flag to indicate that the port assoc/disassoc @@ -1174,7 +1175,7 @@ static int enic_set_vf_port(struct net_device *netdev, int vf, if (pp->request == PORT_REQUEST_DISASSOCIATE) { eth_zero_addr(pp->mac_addr); if (vf == PORT_SELF_VF) - eth_zero_addr(netdev->dev_addr); + eth_hw_addr_set(netdev, zero_addr); } } diff --git a/drivers/net/ethernet/cisco/enic/enic_pp.c b/drivers/net/ethernet/cisco/enic/enic_pp.c index e6a83198c3dd..80f46dbd5117 100644 --- a/drivers/net/ethernet/cisco/enic/enic_pp.c +++ b/drivers/net/ethernet/cisco/enic/enic_pp.c @@ -73,9 +73,9 @@ static int enic_set_port_profile(struct enic *enic, int vf) struct vic_provinfo *vp; const u8 oui[3] = VIC_PROVINFO_CISCO_OUI; const __be16 os_type = htons(VIC_GENERIC_PROV_OS_TYPE_LINUX); + const u8 *client_mac; char uuid_str[38]; char client_mac_str[18]; - u8 *client_mac; int err; ENIC_PP_BY_INDEX(enic, vf, pp, &err); diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c index 82d32caf1374..941f175fb911 100644 --- a/drivers/net/ethernet/cortina/gemini.c +++ b/drivers/net/ethernet/cortina/gemini.c @@ -2473,7 +2473,7 @@ static int gemini_ethernet_port_probe(struct platform_device *pdev) port->mac_addr[0], port->mac_addr[1], port->mac_addr[2]); dev_info(dev, "using a random ethernet address\n"); - eth_random_addr(netdev->dev_addr); + eth_hw_addr_random(netdev); } gmac_write_mac_address(netdev); diff --git a/drivers/net/ethernet/davicom/dm9000.c b/drivers/net/ethernet/davicom/dm9000.c index e13dd53a8b3b..0985ab216566 100644 --- a/drivers/net/ethernet/davicom/dm9000.c +++ b/drivers/net/ethernet/davicom/dm9000.c @@ -1425,6 +1425,7 @@ dm9000_probe(struct platform_device *pdev) enum of_gpio_flags flags; struct regulator *power; bool inv_mac_addr = false; + u8 addr[ETH_ALEN]; power = devm_regulator_get(dev, "vcc"); if (IS_ERR(power)) { @@ -1666,7 +1667,8 @@ dm9000_probe(struct platform_device *pdev) /* try reading the node address from the attached EEPROM */ for (i = 0; i < 6; i += 2) - dm9000_read_eeprom(db, i / 2, ndev->dev_addr+i); + dm9000_read_eeprom(db, i / 2, addr + i); + eth_hw_addr_set(ndev, addr); if (!is_valid_ether_addr(ndev->dev_addr) && pdata != NULL) { mac_src = "platform data"; @@ -1678,7 +1680,8 @@ dm9000_probe(struct platform_device *pdev) mac_src = "chip"; for (i = 0; i < 6; i++) - ndev->dev_addr[i] = ior(db, i+DM9000_PAR); + addr[i] = ior(db, i + DM9000_PAR); + eth_hw_addr_set(ndev, pdata->dev_addr); } if (!is_valid_ether_addr(ndev->dev_addr)) { diff --git a/drivers/net/ethernet/dec/tulip/de2104x.c b/drivers/net/ethernet/dec/tulip/de2104x.c index 117c26fa5909..d51b3d24a0c8 100644 --- a/drivers/net/ethernet/dec/tulip/de2104x.c +++ b/drivers/net/ethernet/dec/tulip/de2104x.c @@ -666,8 +666,8 @@ static void build_setup_frame_hash(u16 *setup_frm, struct net_device *dev) struct de_private *de = netdev_priv(dev); u16 hash_table[32]; struct netdev_hw_addr *ha; + const u16 *eaddrs; int i; - u16 *eaddrs; memset(hash_table, 0, sizeof(hash_table)); __set_bit_le(255, hash_table); /* Broadcast entry */ @@ -685,7 +685,7 @@ static void build_setup_frame_hash(u16 *setup_frm, struct net_device *dev) setup_frm = &de->setup_frame[13*6]; /* Fill the final entry with our physical address. */ - eaddrs = (u16 *)dev->dev_addr; + eaddrs = (const u16 *)dev->dev_addr; *setup_frm++ = eaddrs[0]; *setup_frm++ = eaddrs[0]; *setup_frm++ = eaddrs[1]; *setup_frm++ = eaddrs[1]; *setup_frm++ = eaddrs[2]; *setup_frm++ = eaddrs[2]; @@ -695,7 +695,7 @@ static void build_setup_frame_perfect(u16 *setup_frm, struct net_device *dev) { struct de_private *de = netdev_priv(dev); struct netdev_hw_addr *ha; - u16 *eaddrs; + const u16 *eaddrs; /* We have <= 14 addresses so we can use the wonderful 16 address perfect filtering of the Tulip. */ @@ -710,7 +710,7 @@ static void build_setup_frame_perfect(u16 *setup_frm, struct net_device *dev) setup_frm = &de->setup_frame[15*6]; /* Fill the final entry with our physical address. */ - eaddrs = (u16 *)dev->dev_addr; + eaddrs = (const u16 *)dev->dev_addr; *setup_frm++ = eaddrs[0]; *setup_frm++ = eaddrs[0]; *setup_frm++ = eaddrs[1]; *setup_frm++ = eaddrs[1]; *setup_frm++ = eaddrs[2]; *setup_frm++ = eaddrs[2]; @@ -1713,6 +1713,7 @@ static const struct ethtool_ops de_ethtool_ops = { static void de21040_get_mac_address(struct de_private *de) { + u8 addr[ETH_ALEN]; unsigned i; dw32 (ROMCmd, 0); /* Reset the pointer with a dummy write. */ @@ -1724,12 +1725,13 @@ static void de21040_get_mac_address(struct de_private *de) value = dr32(ROMCmd); rmb(); } while (value < 0 && --boguscnt > 0); - de->dev->dev_addr[i] = value; + addr[i] = value; udelay(1); if (boguscnt <= 0) pr_warn("timeout reading 21040 MAC address byte %u\n", i); } + eth_hw_addr_set(de->dev, addr); } static void de21040_get_media_info(struct de_private *de) @@ -1821,8 +1823,7 @@ static void de21041_get_srom_info(struct de_private *de) #endif /* store MAC address */ - for (i = 0; i < 6; i ++) - de->dev->dev_addr[i] = ee_data[i + sa_offset]; + eth_hw_addr_set(de->dev, &ee_data[sa_offset]); /* get offset of controller 0 info leaf. ignore 2nd byte. */ ofs = ee_data[SROMC0InfoLeaf]; diff --git a/drivers/net/ethernet/dec/tulip/de4x5.c b/drivers/net/ethernet/dec/tulip/de4x5.c index 36ab4cbf2ad0..13121c4dcfe6 100644 --- a/drivers/net/ethernet/dec/tulip/de4x5.c +++ b/drivers/net/ethernet/dec/tulip/de4x5.c @@ -4031,6 +4031,7 @@ get_hw_addr(struct net_device *dev) int broken, i, k, tmp, status = 0; u_short j,chksum; struct de4x5_private *lp = netdev_priv(dev); + u8 addr[ETH_ALEN]; broken = de4x5_bad_srom(lp); @@ -4042,28 +4043,30 @@ get_hw_addr(struct net_device *dev) if (lp->chipset == DC21040) { while ((tmp = inl(DE4X5_APROM)) < 0); k += (u_char) tmp; - dev->dev_addr[i++] = (u_char) tmp; + addr[i++] = (u_char) tmp; while ((tmp = inl(DE4X5_APROM)) < 0); k += (u_short) (tmp << 8); - dev->dev_addr[i++] = (u_char) tmp; + addr[i++] = (u_char) tmp; } else if (!broken) { - dev->dev_addr[i] = (u_char) lp->srom.ieee_addr[i]; i++; - dev->dev_addr[i] = (u_char) lp->srom.ieee_addr[i]; i++; + addr[i] = (u_char) lp->srom.ieee_addr[i]; i++; + addr[i] = (u_char) lp->srom.ieee_addr[i]; i++; } else if ((broken == SMC) || (broken == ACCTON)) { - dev->dev_addr[i] = *((u_char *)&lp->srom + i); i++; - dev->dev_addr[i] = *((u_char *)&lp->srom + i); i++; + addr[i] = *((u_char *)&lp->srom + i); i++; + addr[i] = *((u_char *)&lp->srom + i); i++; } } else { k += (u_char) (tmp = inb(EISA_APROM)); - dev->dev_addr[i++] = (u_char) tmp; + addr[i++] = (u_char) tmp; k += (u_short) ((tmp = inb(EISA_APROM)) << 8); - dev->dev_addr[i++] = (u_char) tmp; + addr[i++] = (u_char) tmp; } if (k > 0xffff) k-=0xffff; } if (k == 0xffff) k=0; + eth_hw_addr_set(dev, addr); + if (lp->bus == PCI) { if (lp->chipset == DC21040) { while ((tmp = inl(DE4X5_APROM)) < 0); @@ -4095,8 +4098,9 @@ get_hw_addr(struct net_device *dev) int x = dev->dev_addr[i]; x = ((x & 0xf) << 4) + ((x & 0xf0) >> 4); x = ((x & 0x33) << 2) + ((x & 0xcc) >> 2); - dev->dev_addr[i] = ((x & 0x55) << 1) + ((x & 0xaa) >> 1); + addr[i] = ((x & 0x55) << 1) + ((x & 0xaa) >> 1); } + eth_hw_addr_set(dev, addr); } #endif /* CONFIG_PPC_PMAC */ @@ -4158,12 +4162,9 @@ test_bad_enet(struct net_device *dev, int status) if ((tmp == 0) || (tmp == 0x5fa)) { if ((lp->chipset == last.chipset) && (lp->bus_num == last.bus) && (lp->bus_num > 0)) { - for (i=0; idev_addr[i] = last.addr[i]; - for (i=ETH_ALEN-1; i>2; --i) { - dev->dev_addr[i] += 1; - if (dev->dev_addr[i] != 0) break; - } - for (i=0; idev_addr[i]; + eth_addr_inc(last.addr); + eth_hw_addr_set(dev, last.addr); + if (!an_exception(lp)) { dev->irq = last.irq; } @@ -5391,9 +5392,7 @@ de4x5_siocdevprivate(struct net_device *dev, struct ifreq *rq, void __user *data if (netif_queue_stopped(dev)) return -EBUSY; netif_stop_queue(dev); - for (i=0; idev_addr[i] = tmp.addr[i]; - } + eth_hw_addr_set(dev, tmp.addr); build_setup_frame(dev, PHYS_ADDR_ONLY); /* Set up the descriptor and give ownership to the card */ load_packet(dev, lp->setup_frame, TD_IC | PERFECT_F | TD_SET | diff --git a/drivers/net/ethernet/dec/tulip/dmfe.c b/drivers/net/ethernet/dec/tulip/dmfe.c index c763b692e164..83f1727d1423 100644 --- a/drivers/net/ethernet/dec/tulip/dmfe.c +++ b/drivers/net/ethernet/dec/tulip/dmfe.c @@ -476,8 +476,7 @@ static int dmfe_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) } /* Set Node address */ - for (i = 0; i < 6; i++) - dev->dev_addr[i] = db->srom[20 + i]; + eth_hw_addr_set(dev, &db->srom[20]); err = register_netdev (dev); if (err) @@ -1436,9 +1435,9 @@ static void update_cr6(u32 cr6_data, void __iomem *ioaddr) static void dm9132_id_table(struct net_device *dev) { + const u16 *addrptr = (const u16 *)dev->dev_addr; struct dmfe_board_info *db = netdev_priv(dev); void __iomem *ioaddr = db->ioaddr + 0xc0; - u16 *addrptr = (u16 *)dev->dev_addr; struct netdev_hw_addr *ha; u16 i, hash_table[4]; @@ -1477,7 +1476,7 @@ static void send_filter_frame(struct net_device *dev) struct dmfe_board_info *db = netdev_priv(dev); struct netdev_hw_addr *ha; struct tx_desc *txptr; - u16 * addrptr; + const u16 * addrptr; u32 * suptr; int i; @@ -1487,7 +1486,7 @@ static void send_filter_frame(struct net_device *dev) suptr = (u32 *) txptr->tx_buf_ptr; /* Node address */ - addrptr = (u16 *) dev->dev_addr; + addrptr = (const u16 *) dev->dev_addr; *suptr++ = addrptr[0]; *suptr++ = addrptr[1]; *suptr++ = addrptr[2]; diff --git a/drivers/net/ethernet/dec/tulip/tulip_core.c b/drivers/net/ethernet/dec/tulip/tulip_core.c index 1ba6452c0683..79df5a72877b 100644 --- a/drivers/net/ethernet/dec/tulip/tulip_core.c +++ b/drivers/net/ethernet/dec/tulip/tulip_core.c @@ -339,7 +339,7 @@ static void tulip_up(struct net_device *dev) } } else { /* This is set_rx_mode(), but without starting the transmitter. */ - u16 *eaddrs = (u16 *)dev->dev_addr; + const u16 *eaddrs = (const u16 *)dev->dev_addr; u16 *setup_frm = &tp->setup_frame[15*6]; dma_addr_t mapping; @@ -1001,8 +1001,8 @@ static void build_setup_frame_hash(u16 *setup_frm, struct net_device *dev) struct tulip_private *tp = netdev_priv(dev); u16 hash_table[32]; struct netdev_hw_addr *ha; + const u16 *eaddrs; int i; - u16 *eaddrs; memset(hash_table, 0, sizeof(hash_table)); __set_bit_le(255, hash_table); /* Broadcast entry */ @@ -1019,7 +1019,7 @@ static void build_setup_frame_hash(u16 *setup_frm, struct net_device *dev) setup_frm = &tp->setup_frame[13*6]; /* Fill the final entry with our physical address. */ - eaddrs = (u16 *)dev->dev_addr; + eaddrs = (const u16 *)dev->dev_addr; *setup_frm++ = eaddrs[0]; *setup_frm++ = eaddrs[0]; *setup_frm++ = eaddrs[1]; *setup_frm++ = eaddrs[1]; *setup_frm++ = eaddrs[2]; *setup_frm++ = eaddrs[2]; @@ -1029,7 +1029,7 @@ static void build_setup_frame_perfect(u16 *setup_frm, struct net_device *dev) { struct tulip_private *tp = netdev_priv(dev); struct netdev_hw_addr *ha; - u16 *eaddrs; + const u16 *eaddrs; /* We have <= 14 addresses so we can use the wonderful 16 address perfect filtering of the Tulip. */ @@ -1044,7 +1044,7 @@ static void build_setup_frame_perfect(u16 *setup_frm, struct net_device *dev) setup_frm = &tp->setup_frame[15*6]; /* Fill the final entry with our physical address. */ - eaddrs = (u16 *)dev->dev_addr; + eaddrs = (const u16 *)dev->dev_addr; *setup_frm++ = eaddrs[0]; *setup_frm++ = eaddrs[0]; *setup_frm++ = eaddrs[1]; *setup_frm++ = eaddrs[1]; *setup_frm++ = eaddrs[2]; *setup_frm++ = eaddrs[2]; @@ -1305,6 +1305,7 @@ static int tulip_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) int chip_idx = ent->driver_data; const char *chip_name = tulip_tbl[chip_idx].chip_name; unsigned int eeprom_missing = 0; + u8 addr[ETH_ALEN] __aligned(2); unsigned int force_csr0 = 0; board_idx++; @@ -1506,13 +1507,15 @@ static int tulip_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) do { value = ioread32(ioaddr + CSR9); } while (value < 0 && --boguscnt > 0); - put_unaligned_le16(value, ((__le16 *)dev->dev_addr) + i); + put_unaligned_le16(value, ((__le16 *)addr) + i); sum += value & 0xffff; } + eth_hw_addr_set(dev, addr); } else if (chip_idx == COMET) { /* No need to read the EEPROM. */ - put_unaligned_le32(ioread32(ioaddr + 0xA4), dev->dev_addr); - put_unaligned_le16(ioread32(ioaddr + 0xA8), dev->dev_addr + 4); + put_unaligned_le32(ioread32(ioaddr + 0xA4), addr); + put_unaligned_le16(ioread32(ioaddr + 0xA8), addr + 4); + eth_hw_addr_set(dev, addr); for (i = 0; i < 6; i ++) sum += dev->dev_addr[i]; } else { @@ -1575,20 +1578,23 @@ static int tulip_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) #endif for (i = 0; i < 6; i ++) { - dev->dev_addr[i] = ee_data[i + sa_offset]; + addr[i] = ee_data[i + sa_offset]; sum += ee_data[i + sa_offset]; } + eth_hw_addr_set(dev, addr); } /* Lite-On boards have the address byte-swapped. */ if ((dev->dev_addr[0] == 0xA0 || dev->dev_addr[0] == 0xC0 || dev->dev_addr[0] == 0x02) && - dev->dev_addr[1] == 0x00) + dev->dev_addr[1] == 0x00) { for (i = 0; i < 6; i+=2) { - char tmp = dev->dev_addr[i]; - dev->dev_addr[i] = dev->dev_addr[i+1]; - dev->dev_addr[i+1] = tmp; + addr[i] = dev->dev_addr[i+1]; + addr[i+1] = dev->dev_addr[i]; } + eth_hw_addr_set(dev, addr); + } + /* On the Zynx 315 Etherarray and other multiport boards only the first Tulip has an EEPROM. On Sparc systems the mac address is held in the OBP property @@ -1599,17 +1605,18 @@ static int tulip_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) if (sum == 0 || sum == 6*0xff) { #if defined(CONFIG_SPARC) struct device_node *dp = pci_device_to_OF_node(pdev); - const unsigned char *addr; + const unsigned char *addr2; int len; #endif eeprom_missing = 1; for (i = 0; i < 5; i++) - dev->dev_addr[i] = last_phys_addr[i]; - dev->dev_addr[i] = last_phys_addr[i] + 1; + addr[i] = last_phys_addr[i]; + addr[i] = last_phys_addr[i] + 1; + eth_hw_addr_set(dev, addr); #if defined(CONFIG_SPARC) - addr = of_get_property(dp, "local-mac-address", &len); - if (addr && len == ETH_ALEN) - eth_hw_addr_set(dev, addr); + addr2 = of_get_property(dp, "local-mac-address", &len); + if (addr2 && len == ETH_ALEN) + eth_hw_addr_set(dev, addr2); #endif #if defined(__i386__) || defined(__x86_64__) /* Patch up x86 BIOS bug. */ if (last_irq) diff --git a/drivers/net/ethernet/dec/tulip/uli526x.c b/drivers/net/ethernet/dec/tulip/uli526x.c index d67ef7d02d6b..77d9058431e3 100644 --- a/drivers/net/ethernet/dec/tulip/uli526x.c +++ b/drivers/net/ethernet/dec/tulip/uli526x.c @@ -272,6 +272,7 @@ static int uli526x_init_one(struct pci_dev *pdev, struct uli526x_board_info *db; /* board information structure */ struct net_device *dev; void __iomem *ioaddr; + u8 addr[ETH_ALEN]; int i, err; ULI526X_DBUG(0, "uli526x_init_one()", 0); @@ -379,7 +380,7 @@ static int uli526x_init_one(struct pci_dev *pdev, uw32(DCR13, 0x1b0); //Select ID Table access port //Read MAC address from CR14 for (i = 0; i < 6; i++) - dev->dev_addr[i] = ur32(DCR14); + addr[i] = ur32(DCR14); //Read end uw32(DCR13, 0); //Clear CR13 uw32(DCR0, 0); //Clear CR0 @@ -388,8 +389,10 @@ static int uli526x_init_one(struct pci_dev *pdev, else /*Exist SROM*/ { for (i = 0; i < 6; i++) - dev->dev_addr[i] = db->srom[20 + i]; + addr[i] = db->srom[20 + i]; } + eth_hw_addr_set(dev, addr); + err = register_netdev (dev); if (err) goto err_out_unmap; @@ -1343,7 +1346,7 @@ static void send_filter_frame(struct net_device *dev, int mc_cnt) void __iomem *ioaddr = db->ioaddr; struct netdev_hw_addr *ha; struct tx_desc *txptr; - u16 * addrptr; + const u16 * addrptr; u32 * suptr; int i; @@ -1353,7 +1356,7 @@ static void send_filter_frame(struct net_device *dev, int mc_cnt) suptr = (u32 *) txptr->tx_buf_ptr; /* Node address */ - addrptr = (u16 *) dev->dev_addr; + addrptr = (const u16 *) dev->dev_addr; *suptr++ = addrptr[0] << FLT_SHIFT; *suptr++ = addrptr[1] << FLT_SHIFT; *suptr++ = addrptr[2] << FLT_SHIFT; diff --git a/drivers/net/ethernet/dec/tulip/winbond-840.c b/drivers/net/ethernet/dec/tulip/winbond-840.c index 85b99099c6b9..86b1d23eba83 100644 --- a/drivers/net/ethernet/dec/tulip/winbond-840.c +++ b/drivers/net/ethernet/dec/tulip/winbond-840.c @@ -355,6 +355,7 @@ static int w840_probe1(struct pci_dev *pdev, const struct pci_device_id *ent) int chip_idx = ent->driver_data; int irq; int i, option = find_cnt < MAX_UNITS ? options[find_cnt] : 0; + __le16 addr[ETH_ALEN / 2]; void __iomem *ioaddr; i = pcim_enable_device(pdev); @@ -382,7 +383,8 @@ static int w840_probe1(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_out_netdev; for (i = 0; i < 3; i++) - ((__le16 *)dev->dev_addr)[i] = cpu_to_le16(eeprom_read(ioaddr, i)); + addr[i] = cpu_to_le16(eeprom_read(ioaddr, i)); + eth_hw_addr_set(dev, (u8 *)addr); /* Reset the chip to erase previous misconfiguration. No hold time required! */ @@ -877,7 +879,7 @@ static void init_registers(struct net_device *dev) 8000 16 longwords 0200 2 longwords 2000 32 longwords C000 32 longwords 0400 4 longwords */ -#if defined (__i386__) && !defined(MODULE) +#if defined (__i386__) && !defined(MODULE) && !defined(CONFIG_UML) /* When not a module we can work around broken '486 PCI boards. */ if (boot_cpu_data.x86 <= 4) { i |= 0x4800; diff --git a/drivers/net/ethernet/dec/tulip/xircom_cb.c b/drivers/net/ethernet/dec/tulip/xircom_cb.c index a8de79355578..8759f9f76b62 100644 --- a/drivers/net/ethernet/dec/tulip/xircom_cb.c +++ b/drivers/net/ethernet/dec/tulip/xircom_cb.c @@ -1015,12 +1015,14 @@ static void read_mac_address(struct xircom_private *card) xw32(CSR10, i + 3); data_count = xr32(CSR9); if ((tuple == 0x22) && (data_id == 0x04) && (data_count == 0x06)) { + u8 addr[ETH_ALEN]; int j; for (j = 0; j < 6; j++) { xw32(CSR10, i + j + 4); - card->dev->dev_addr[j] = xr32(CSR9) & 0xff; + addr[j] = xr32(CSR9) & 0xff; } + eth_hw_addr_set(card->dev, addr); break; } else if (link == 0) { break; diff --git a/drivers/net/ethernet/dlink/dl2k.c b/drivers/net/ethernet/dlink/dl2k.c index 202ecb132053..a301f7e6a440 100644 --- a/drivers/net/ethernet/dlink/dl2k.c +++ b/drivers/net/ethernet/dlink/dl2k.c @@ -349,8 +349,7 @@ parse_eeprom (struct net_device *dev) } /* Set MAC address */ - for (i = 0; i < 6; i++) - dev->dev_addr[i] = psrom->mac_addr[i]; + eth_hw_addr_set(dev, psrom->mac_addr); if (np->chip_id == CHIP_IP1000A) { np->led_mode = psrom->led_mode; @@ -567,7 +566,7 @@ static void rio_hw_init(struct net_device *dev) */ for (i = 0; i < 3; i++) dw16(StationAddr0 + 2 * i, - cpu_to_le16(((u16 *)dev->dev_addr)[i])); + cpu_to_le16(((const u16 *)dev->dev_addr)[i])); set_multicast (dev); if (np->coalesce) { diff --git a/drivers/net/ethernet/dlink/sundance.c b/drivers/net/ethernet/dlink/sundance.c index 194b0812f7f6..c710dc17be90 100644 --- a/drivers/net/ethernet/dlink/sundance.c +++ b/drivers/net/ethernet/dlink/sundance.c @@ -508,6 +508,7 @@ static int sundance_probe1(struct pci_dev *pdev, int bar = 1; #endif int phy, phy_end, phy_idx = 0; + __le16 addr[ETH_ALEN / 2]; if (pci_enable_device(pdev)) return -EIO; @@ -528,8 +529,9 @@ static int sundance_probe1(struct pci_dev *pdev, goto err_out_res; for (i = 0; i < 3; i++) - ((__le16 *)dev->dev_addr)[i] = + addr[i] = cpu_to_le16(eeprom_read(ioaddr, i + EEPROM_SA_OFFSET)); + eth_hw_addr_set(dev, (u8 *)addr); np = netdev_priv(dev); np->ndev = dev; diff --git a/drivers/net/ethernet/dnet.c b/drivers/net/ethernet/dnet.c index 6c51cf991dad..92462ed87bc4 100644 --- a/drivers/net/ethernet/dnet.c +++ b/drivers/net/ethernet/dnet.c @@ -60,11 +60,11 @@ static void __dnet_set_hwaddr(struct dnet *bp) { u16 tmp; - tmp = be16_to_cpup((__be16 *)bp->dev->dev_addr); + tmp = be16_to_cpup((const __be16 *)bp->dev->dev_addr); dnet_writew_mac(bp, DNET_INTERNAL_MAC_ADDR_0_REG, tmp); - tmp = be16_to_cpup((__be16 *)(bp->dev->dev_addr + 2)); + tmp = be16_to_cpup((const __be16 *)(bp->dev->dev_addr + 2)); dnet_writew_mac(bp, DNET_INTERNAL_MAC_ADDR_1_REG, tmp); - tmp = be16_to_cpup((__be16 *)(bp->dev->dev_addr + 4)); + tmp = be16_to_cpup((const __be16 *)(bp->dev->dev_addr + 4)); dnet_writew_mac(bp, DNET_INTERNAL_MAC_ADDR_2_REG, tmp); } @@ -93,7 +93,7 @@ static void dnet_get_hwaddr(struct dnet *bp) *((__be16 *)(addr + 4)) = cpu_to_be16(tmp); if (is_valid_ether_addr(addr)) - memcpy(bp->dev->dev_addr, addr, sizeof(addr)); + eth_hw_addr_set(bp->dev, addr); } static int dnet_mdio_read(struct mii_bus *bus, int mii_id, int regnum) diff --git a/drivers/net/ethernet/ec_bhf.c b/drivers/net/ethernet/ec_bhf.c index b2d4fb3feb74..46e3a05e9582 100644 --- a/drivers/net/ethernet/ec_bhf.c +++ b/drivers/net/ethernet/ec_bhf.c @@ -479,6 +479,7 @@ static int ec_bhf_probe(struct pci_dev *dev, const struct pci_device_id *id) struct net_device *net_dev; struct ec_bhf_priv *priv; void __iomem *dma_io; + u8 addr[ETH_ALEN]; void __iomem *io; int err = 0; @@ -539,7 +540,8 @@ static int ec_bhf_probe(struct pci_dev *dev, const struct pci_device_id *id) if (err < 0) goto err_free_net_dev; - memcpy_fromio(net_dev->dev_addr, priv->mii_io + MII_MAC_ADDR, 6); + memcpy_fromio(addr, priv->mii_io + MII_MAC_ADDR, ETH_ALEN); + eth_hw_addr_set(net_dev, addr); err = register_netdev(net_dev); if (err < 0) diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c index 649c5c429bd7..528eb0f223b1 100644 --- a/drivers/net/ethernet/emulex/benet/be_cmds.c +++ b/drivers/net/ethernet/emulex/benet/be_cmds.c @@ -1080,7 +1080,7 @@ err: } /* Uses synchronous MCCQ */ -int be_cmd_pmac_add(struct be_adapter *adapter, u8 *mac_addr, +int be_cmd_pmac_add(struct be_adapter *adapter, const u8 *mac_addr, u32 if_id, u32 *pmac_id, u32 domain) { struct be_mcc_wrb *wrb; diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.h b/drivers/net/ethernet/emulex/benet/be_cmds.h index c30d6d6f0f3a..db1f3b908582 100644 --- a/drivers/net/ethernet/emulex/benet/be_cmds.h +++ b/drivers/net/ethernet/emulex/benet/be_cmds.h @@ -2385,7 +2385,7 @@ int be_pci_fnum_get(struct be_adapter *adapter); int be_fw_wait_ready(struct be_adapter *adapter); int be_cmd_mac_addr_query(struct be_adapter *adapter, u8 *mac_addr, bool permanent, u32 if_handle, u32 pmac_id); -int be_cmd_pmac_add(struct be_adapter *adapter, u8 *mac_addr, u32 if_id, +int be_cmd_pmac_add(struct be_adapter *adapter, const u8 *mac_addr, u32 if_id, u32 *pmac_id, u32 domain); int be_cmd_pmac_del(struct be_adapter *adapter, u32 if_id, int pmac_id, u32 domain); diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index ef60e2da05a4..d51f24c9e1b8 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -272,7 +272,7 @@ void be_cq_notify(struct be_adapter *adapter, u16 qid, bool arm, u16 num_popped) iowrite32(val, adapter->db + DB_CQ_OFFSET); } -static int be_dev_mac_add(struct be_adapter *adapter, u8 *mac) +static int be_dev_mac_add(struct be_adapter *adapter, const u8 *mac) { int i; @@ -4621,7 +4621,6 @@ static void be_destroy_err_recovery_workq(void) if (!be_err_recovery_workq) return; - flush_workqueue(be_err_recovery_workq); destroy_workqueue(be_err_recovery_workq); be_err_recovery_workq = NULL; } diff --git a/drivers/net/ethernet/ethoc.c b/drivers/net/ethernet/ethoc.c index cd3a3b8f23b6..b1c8ffea6ad2 100644 --- a/drivers/net/ethernet/ethoc.c +++ b/drivers/net/ethernet/ethoc.c @@ -802,8 +802,8 @@ static int ethoc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) static void ethoc_do_set_mac_address(struct net_device *dev) { + const unsigned char *mac = dev->dev_addr; struct ethoc *priv = netdev_priv(dev); - unsigned char *mac = dev->dev_addr; ethoc_write(priv, MAC_ADDR0, (mac[2] << 24) | (mac[3] << 16) | (mac[4] << 8) | (mac[5] << 0)); @@ -1154,8 +1154,12 @@ static int ethoc_probe(struct platform_device *pdev) /* Check that the given MAC address is valid. If it isn't, read the * current MAC from the controller. */ - if (!is_valid_ether_addr(netdev->dev_addr)) - ethoc_get_mac_address(netdev, netdev->dev_addr); + if (!is_valid_ether_addr(netdev->dev_addr)) { + u8 addr[ETH_ALEN]; + + ethoc_get_mac_address(netdev, addr); + eth_hw_addr_set(netdev, addr); + } /* Check the MAC again for validity, if it still isn't choose and * program a random one. diff --git a/drivers/net/ethernet/fealnx.c b/drivers/net/ethernet/fealnx.c index 25c91b3c5fd3..b3939a5f7b03 100644 --- a/drivers/net/ethernet/fealnx.c +++ b/drivers/net/ethernet/fealnx.c @@ -482,6 +482,7 @@ static int fealnx_init_one(struct pci_dev *pdev, struct net_device *dev; void *ring_space; dma_addr_t ring_dma; + u8 addr[ETH_ALEN]; #ifdef USE_IO_OPS int bar = 0; #else @@ -525,7 +526,8 @@ static int fealnx_init_one(struct pci_dev *pdev, /* read ethernet id */ for (i = 0; i < 6; ++i) - dev->dev_addr[i] = ioread8(ioaddr + PAR0 + i); + addr[i] = ioread8(ioaddr + PAR0 + i); + eth_hw_addr_set(dev, addr); /* Reset the chip to erase previous misconfiguration. */ iowrite32(0x00000001, ioaddr + BCR); @@ -827,7 +829,7 @@ static int netdev_open(struct net_device *dev) return -EAGAIN; for (i = 0; i < 3; i++) - iowrite16(((unsigned short*)dev->dev_addr)[i], + iowrite16(((const unsigned short *)dev->dev_addr)[i], ioaddr + PAR0 + i*2); init_ring(dev); @@ -857,7 +859,7 @@ static int netdev_open(struct net_device *dev) np->bcrvalue |= 0x04; /* big-endian */ #endif -#if defined(__i386__) && !defined(MODULE) +#if defined(__i386__) && !defined(MODULE) && !defined(CONFIG_UML) if (boot_cpu_data.x86 <= 4) np->crvalue = 0xa00; else diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index cd8a7d94f60c..6b2927d863e2 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -272,7 +272,7 @@ static int dpaa_netdev_init(struct net_device *net_dev, } else { eth_hw_addr_random(net_dev); err = priv->mac_dev->change_addr(priv->mac_dev->fman_mac, - (enet_addr_t *)net_dev->dev_addr); + (const enet_addr_t *)net_dev->dev_addr); if (err) { dev_err(dev, "Failed to set random MAC address\n"); return -EINVAL; @@ -452,7 +452,7 @@ static int dpaa_set_mac_address(struct net_device *net_dev, void *addr) mac_dev = priv->mac_dev; err = mac_dev->change_addr(mac_dev->fman_mac, - (enet_addr_t *)net_dev->dev_addr); + (const enet_addr_t *)net_dev->dev_addr); if (err < 0) { netif_err(priv, drv, net_dev, "mac_dev->change_addr() = %d\n", err); diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c index 34f189271ef2..714e961e7a77 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c @@ -533,6 +533,7 @@ static void dpaa2_eth_rx(struct dpaa2_eth_priv *priv, percpu_stats->rx_packets++; percpu_stats->rx_bytes += dpaa2_fd_get_len(fd); + ch->stats.bytes_per_cdan += dpaa2_fd_get_len(fd); list_add_tail(&skb->list, ch->rx_list); @@ -641,6 +642,7 @@ static int dpaa2_eth_consume_frames(struct dpaa2_eth_channel *ch, fq->stats.frames += cleaned; ch->stats.frames += cleaned; + ch->stats.frames_per_cdan += cleaned; /* A dequeue operation only pulls frames from a single queue * into the store. Return the frame queue as an out param. @@ -1264,7 +1266,7 @@ static netdev_tx_t dpaa2_eth_tx(struct sk_buff *skb, struct net_device *net_dev) /* Tx confirmation frame processing routine */ static void dpaa2_eth_tx_conf(struct dpaa2_eth_priv *priv, - struct dpaa2_eth_channel *ch __always_unused, + struct dpaa2_eth_channel *ch, const struct dpaa2_fd *fd, struct dpaa2_eth_fq *fq) { @@ -1279,6 +1281,7 @@ static void dpaa2_eth_tx_conf(struct dpaa2_eth_priv *priv, percpu_extras = this_cpu_ptr(priv->percpu_extras); percpu_extras->tx_conf_frames++; percpu_extras->tx_conf_bytes += fd_len; + ch->stats.bytes_per_cdan += fd_len; /* Check frame errors in the FD field */ fd_errors = dpaa2_fd_get_ctrl(fd) & DPAA2_FD_TX_ERR_MASK; @@ -1601,6 +1604,12 @@ static int dpaa2_eth_poll(struct napi_struct *napi, int budget) } } while (store_cleaned); + /* Update NET DIM with the values for this CDAN */ + dpaa2_io_update_net_dim(ch->dpio, ch->stats.frames_per_cdan, + ch->stats.bytes_per_cdan); + ch->stats.frames_per_cdan = 0; + ch->stats.bytes_per_cdan = 0; + /* We didn't consume the entire budget, so finish napi and * re-enable data availability notifications */ diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h index 628d2d45f045..2085844227fe 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h @@ -384,6 +384,8 @@ struct dpaa2_eth_ch_stats { __u64 xdp_redirect; /* Must be last, does not show up in ethtool stats */ __u64 frames; + __u64 frames_per_cdan; + __u64 bytes_per_cdan; }; /* Maximum number of queues associated with a DPNI */ diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c index 2da5f881f630..adb8ce5306ee 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c @@ -820,7 +820,63 @@ static int dpaa2_eth_set_tunable(struct net_device *net_dev, return err; } +static int dpaa2_eth_get_coalesce(struct net_device *dev, + struct ethtool_coalesce *ic, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) +{ + struct dpaa2_eth_priv *priv = netdev_priv(dev); + struct dpaa2_io *dpio = priv->channel[0]->dpio; + + dpaa2_io_get_irq_coalescing(dpio, &ic->rx_coalesce_usecs); + ic->use_adaptive_rx_coalesce = dpaa2_io_get_adaptive_coalescing(dpio); + + return 0; +} + +static int dpaa2_eth_set_coalesce(struct net_device *dev, + struct ethtool_coalesce *ic, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) +{ + struct dpaa2_eth_priv *priv = netdev_priv(dev); + struct dpaa2_io *dpio; + int prev_adaptive; + u32 prev_rx_usecs; + int i, j, err; + + /* Keep track of the previous value, just in case we fail */ + dpio = priv->channel[0]->dpio; + dpaa2_io_get_irq_coalescing(dpio, &prev_rx_usecs); + prev_adaptive = dpaa2_io_get_adaptive_coalescing(dpio); + + /* Setup new value for rx coalescing */ + for (i = 0; i < priv->num_channels; i++) { + dpio = priv->channel[i]->dpio; + + dpaa2_io_set_adaptive_coalescing(dpio, + ic->use_adaptive_rx_coalesce); + err = dpaa2_io_set_irq_coalescing(dpio, ic->rx_coalesce_usecs); + if (err) + goto restore_rx_usecs; + } + + return 0; + +restore_rx_usecs: + for (j = 0; j < i; j++) { + dpio = priv->channel[j]->dpio; + + dpaa2_io_set_irq_coalescing(dpio, prev_rx_usecs); + dpaa2_io_set_adaptive_coalescing(dpio, prev_adaptive); + } + + return err; +} + const struct ethtool_ops dpaa2_ethtool_ops = { + .supported_coalesce_params = ETHTOOL_COALESCE_RX_USECS | + ETHTOOL_COALESCE_USE_ADAPTIVE_RX, .get_drvinfo = dpaa2_eth_get_drvinfo, .nway_reset = dpaa2_eth_nway_reset, .get_link = ethtool_op_get_link, @@ -836,4 +892,6 @@ const struct ethtool_ops dpaa2_ethtool_ops = { .get_ts_info = dpaa2_eth_get_ts_info, .get_tunable = dpaa2_eth_get_tunable, .set_tunable = dpaa2_eth_set_tunable, + .get_coalesce = dpaa2_eth_get_coalesce, + .set_coalesce = dpaa2_eth_set_coalesce, }; diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index 3cbfa8b4e265..504e12554079 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -7,7 +7,9 @@ #include #include #include +#include #include +#include static int enetc_num_stack_tx_queues(struct enetc_ndev_priv *priv) { @@ -314,12 +316,261 @@ dma_err: return 0; } +static void enetc_map_tx_tso_hdr(struct enetc_bdr *tx_ring, struct sk_buff *skb, + struct enetc_tx_swbd *tx_swbd, + union enetc_tx_bd *txbd, int *i, int hdr_len, + int data_len) +{ + union enetc_tx_bd txbd_tmp; + u8 flags = 0, e_flags = 0; + dma_addr_t addr; + + enetc_clear_tx_bd(&txbd_tmp); + addr = tx_ring->tso_headers_dma + *i * TSO_HEADER_SIZE; + + if (skb_vlan_tag_present(skb)) + flags |= ENETC_TXBD_FLAGS_EX; + + txbd_tmp.addr = cpu_to_le64(addr); + txbd_tmp.buf_len = cpu_to_le16(hdr_len); + + /* first BD needs frm_len and offload flags set */ + txbd_tmp.frm_len = cpu_to_le16(hdr_len + data_len); + txbd_tmp.flags = flags; + + /* For the TSO header we do not set the dma address since we do not + * want it unmapped when we do cleanup. We still set len so that we + * count the bytes sent. + */ + tx_swbd->len = hdr_len; + tx_swbd->do_twostep_tstamp = false; + tx_swbd->check_wb = false; + + /* Actually write the header in the BD */ + *txbd = txbd_tmp; + + /* Add extension BD for VLAN */ + if (flags & ENETC_TXBD_FLAGS_EX) { + /* Get the next BD */ + enetc_bdr_idx_inc(tx_ring, i); + txbd = ENETC_TXBD(*tx_ring, *i); + tx_swbd = &tx_ring->tx_swbd[*i]; + prefetchw(txbd); + + /* Setup the VLAN fields */ + enetc_clear_tx_bd(&txbd_tmp); + txbd_tmp.ext.vid = cpu_to_le16(skb_vlan_tag_get(skb)); + txbd_tmp.ext.tpid = 0; /* < C-TAG */ + e_flags |= ENETC_TXBD_E_FLAGS_VLAN_INS; + + /* Write the BD */ + txbd_tmp.ext.e_flags = e_flags; + *txbd = txbd_tmp; + } +} + +static int enetc_map_tx_tso_data(struct enetc_bdr *tx_ring, struct sk_buff *skb, + struct enetc_tx_swbd *tx_swbd, + union enetc_tx_bd *txbd, char *data, + int size, bool last_bd) +{ + union enetc_tx_bd txbd_tmp; + dma_addr_t addr; + u8 flags = 0; + + enetc_clear_tx_bd(&txbd_tmp); + + addr = dma_map_single(tx_ring->dev, data, size, DMA_TO_DEVICE); + if (unlikely(dma_mapping_error(tx_ring->dev, addr))) { + netdev_err(tx_ring->ndev, "DMA map error\n"); + return -ENOMEM; + } + + if (last_bd) { + flags |= ENETC_TXBD_FLAGS_F; + tx_swbd->is_eof = 1; + } + + txbd_tmp.addr = cpu_to_le64(addr); + txbd_tmp.buf_len = cpu_to_le16(size); + txbd_tmp.flags = flags; + + tx_swbd->dma = addr; + tx_swbd->len = size; + tx_swbd->dir = DMA_TO_DEVICE; + + *txbd = txbd_tmp; + + return 0; +} + +static __wsum enetc_tso_hdr_csum(struct tso_t *tso, struct sk_buff *skb, + char *hdr, int hdr_len, int *l4_hdr_len) +{ + char *l4_hdr = hdr + skb_transport_offset(skb); + int mac_hdr_len = skb_network_offset(skb); + + if (tso->tlen != sizeof(struct udphdr)) { + struct tcphdr *tcph = (struct tcphdr *)(l4_hdr); + + tcph->check = 0; + } else { + struct udphdr *udph = (struct udphdr *)(l4_hdr); + + udph->check = 0; + } + + /* Compute the IP checksum. This is necessary since tso_build_hdr() + * already incremented the IP ID field. + */ + if (!tso->ipv6) { + struct iphdr *iph = (void *)(hdr + mac_hdr_len); + + iph->check = 0; + iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl); + } + + /* Compute the checksum over the L4 header. */ + *l4_hdr_len = hdr_len - skb_transport_offset(skb); + return csum_partial(l4_hdr, *l4_hdr_len, 0); +} + +static void enetc_tso_complete_csum(struct enetc_bdr *tx_ring, struct tso_t *tso, + struct sk_buff *skb, char *hdr, int len, + __wsum sum) +{ + char *l4_hdr = hdr + skb_transport_offset(skb); + __sum16 csum_final; + + /* Complete the L4 checksum by appending the pseudo-header to the + * already computed checksum. + */ + if (!tso->ipv6) + csum_final = csum_tcpudp_magic(ip_hdr(skb)->saddr, + ip_hdr(skb)->daddr, + len, ip_hdr(skb)->protocol, sum); + else + csum_final = csum_ipv6_magic(&ipv6_hdr(skb)->saddr, + &ipv6_hdr(skb)->daddr, + len, ipv6_hdr(skb)->nexthdr, sum); + + if (tso->tlen != sizeof(struct udphdr)) { + struct tcphdr *tcph = (struct tcphdr *)(l4_hdr); + + tcph->check = csum_final; + } else { + struct udphdr *udph = (struct udphdr *)(l4_hdr); + + udph->check = csum_final; + } +} + +static int enetc_map_tx_tso_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb) +{ + int hdr_len, total_len, data_len; + struct enetc_tx_swbd *tx_swbd; + union enetc_tx_bd *txbd; + struct tso_t tso; + __wsum csum, csum2; + int count = 0, pos; + int err, i, bd_data_num; + + /* Initialize the TSO handler, and prepare the first payload */ + hdr_len = tso_start(skb, &tso); + total_len = skb->len - hdr_len; + i = tx_ring->next_to_use; + + while (total_len > 0) { + char *hdr; + + /* Get the BD */ + txbd = ENETC_TXBD(*tx_ring, i); + tx_swbd = &tx_ring->tx_swbd[i]; + prefetchw(txbd); + + /* Determine the length of this packet */ + data_len = min_t(int, skb_shinfo(skb)->gso_size, total_len); + total_len -= data_len; + + /* prepare packet headers: MAC + IP + TCP */ + hdr = tx_ring->tso_headers + i * TSO_HEADER_SIZE; + tso_build_hdr(skb, hdr, &tso, data_len, total_len == 0); + + /* compute the csum over the L4 header */ + csum = enetc_tso_hdr_csum(&tso, skb, hdr, hdr_len, &pos); + enetc_map_tx_tso_hdr(tx_ring, skb, tx_swbd, txbd, &i, hdr_len, data_len); + bd_data_num = 0; + count++; + + while (data_len > 0) { + int size; + + size = min_t(int, tso.size, data_len); + + /* Advance the index in the BDR */ + enetc_bdr_idx_inc(tx_ring, &i); + txbd = ENETC_TXBD(*tx_ring, i); + tx_swbd = &tx_ring->tx_swbd[i]; + prefetchw(txbd); + + /* Compute the checksum over this segment of data and + * add it to the csum already computed (over the L4 + * header and possible other data segments). + */ + csum2 = csum_partial(tso.data, size, 0); + csum = csum_block_add(csum, csum2, pos); + pos += size; + + err = enetc_map_tx_tso_data(tx_ring, skb, tx_swbd, txbd, + tso.data, size, + size == data_len); + if (err) + goto err_map_data; + + data_len -= size; + count++; + bd_data_num++; + tso_build_data(skb, &tso, size); + + if (unlikely(bd_data_num >= ENETC_MAX_SKB_FRAGS && data_len)) + goto err_chained_bd; + } + + enetc_tso_complete_csum(tx_ring, &tso, skb, hdr, pos, csum); + + if (total_len == 0) + tx_swbd->skb = skb; + + /* Go to the next BD */ + enetc_bdr_idx_inc(tx_ring, &i); + } + + tx_ring->next_to_use = i; + enetc_update_tx_ring_tail(tx_ring); + + return count; + +err_map_data: + dev_err(tx_ring->dev, "DMA map error"); + +err_chained_bd: + do { + tx_swbd = &tx_ring->tx_swbd[i]; + enetc_free_tx_frame(tx_ring, tx_swbd); + if (i == 0) + i = tx_ring->bd_count; + i--; + } while (count--); + + return 0; +} + static netdev_tx_t enetc_start_xmit(struct sk_buff *skb, struct net_device *ndev) { struct enetc_ndev_priv *priv = netdev_priv(ndev); struct enetc_bdr *tx_ring; - int count; + int count, err; /* Queue one-step Sync packet if already locked */ if (skb->cb[0] & ENETC_F_TX_ONESTEP_SYNC_TSTAMP) { @@ -332,20 +583,36 @@ static netdev_tx_t enetc_start_xmit(struct sk_buff *skb, tx_ring = priv->tx_ring[skb->queue_mapping]; - if (unlikely(skb_shinfo(skb)->nr_frags > ENETC_MAX_SKB_FRAGS)) - if (unlikely(skb_linearize(skb))) - goto drop_packet_err; + if (skb_is_gso(skb)) { + if (enetc_bd_unused(tx_ring) < tso_count_descs(skb)) { + netif_stop_subqueue(ndev, tx_ring->index); + return NETDEV_TX_BUSY; + } - count = skb_shinfo(skb)->nr_frags + 1; /* fragments + head */ - if (enetc_bd_unused(tx_ring) < ENETC_TXBDS_NEEDED(count)) { - netif_stop_subqueue(ndev, tx_ring->index); - return NETDEV_TX_BUSY; + enetc_lock_mdio(); + count = enetc_map_tx_tso_buffs(tx_ring, skb); + enetc_unlock_mdio(); + } else { + if (unlikely(skb_shinfo(skb)->nr_frags > ENETC_MAX_SKB_FRAGS)) + if (unlikely(skb_linearize(skb))) + goto drop_packet_err; + + count = skb_shinfo(skb)->nr_frags + 1; /* fragments + head */ + if (enetc_bd_unused(tx_ring) < ENETC_TXBDS_NEEDED(count)) { + netif_stop_subqueue(ndev, tx_ring->index); + return NETDEV_TX_BUSY; + } + + if (skb->ip_summed == CHECKSUM_PARTIAL) { + err = skb_checksum_help(skb); + if (err) + goto drop_packet_err; + } + enetc_lock_mdio(); + count = enetc_map_tx_buffs(tx_ring, skb); + enetc_unlock_mdio(); } - enetc_lock_mdio(); - count = enetc_map_tx_buffs(tx_ring, skb); - enetc_unlock_mdio(); - if (unlikely(!count)) goto drop_packet_err; @@ -546,10 +813,7 @@ static bool enetc_clean_tx_ring(struct enetc_bdr *tx_ring, int napi_budget) bool is_eof = tx_swbd->is_eof; if (unlikely(tx_swbd->check_wb)) { - struct enetc_ndev_priv *priv = netdev_priv(ndev); - union enetc_tx_bd *txbd; - - txbd = ENETC_TXBD(*tx_ring, i); + union enetc_tx_bd *txbd = ENETC_TXBD(*tx_ring, i); if (txbd->flags & ENETC_TXBD_FLAGS_W && tx_swbd->do_twostep_tstamp) { @@ -567,8 +831,7 @@ static bool enetc_clean_tx_ring(struct enetc_bdr *tx_ring, int napi_budget) if (xdp_frame) { xdp_return_frame(xdp_frame); } else if (skb) { - if (unlikely(tx_swbd->skb->cb[0] & - ENETC_F_TX_ONESTEP_SYNC_TSTAMP)) { + if (unlikely(skb->cb[0] & ENETC_F_TX_ONESTEP_SYNC_TSTAMP)) { /* Start work to release lock for next one-step * timestamping packet. And send one skb in * tx_skbs queue if has. @@ -1493,15 +1756,32 @@ static int enetc_alloc_txbdr(struct enetc_bdr *txr) return -ENOMEM; err = enetc_dma_alloc_bdr(txr, sizeof(union enetc_tx_bd)); - if (err) { - vfree(txr->tx_swbd); - return err; + if (err) + goto err_alloc_bdr; + + txr->tso_headers = dma_alloc_coherent(txr->dev, + txr->bd_count * TSO_HEADER_SIZE, + &txr->tso_headers_dma, + GFP_KERNEL); + if (!txr->tso_headers) { + err = -ENOMEM; + goto err_alloc_tso; } txr->next_to_clean = 0; txr->next_to_use = 0; return 0; + +err_alloc_tso: + dma_free_coherent(txr->dev, txr->bd_count * sizeof(union enetc_tx_bd), + txr->bd_base, txr->bd_dma_base); + txr->bd_base = NULL; +err_alloc_bdr: + vfree(txr->tx_swbd); + txr->tx_swbd = NULL; + + return err; } static void enetc_free_txbdr(struct enetc_bdr *txr) @@ -1513,6 +1793,10 @@ static void enetc_free_txbdr(struct enetc_bdr *txr) size = txr->bd_count * sizeof(union enetc_tx_bd); + dma_free_coherent(txr->dev, txr->bd_count * TSO_HEADER_SIZE, + txr->tso_headers, txr->tso_headers_dma); + txr->tso_headers = NULL; + dma_free_coherent(txr->dev, size, txr->bd_base, txr->bd_dma_base); txr->bd_base = NULL; diff --git a/drivers/net/ethernet/freescale/enetc/enetc.h b/drivers/net/ethernet/freescale/enetc/enetc.h index 08b283347d9c..fb39e406b7fc 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.h +++ b/drivers/net/ethernet/freescale/enetc/enetc.h @@ -112,6 +112,10 @@ struct enetc_bdr { dma_addr_t bd_dma_base; u8 tsd_enable; /* Time specific departure */ bool ext_en; /* enable h/w descriptor extensions */ + + /* DMA buffer for TSO headers */ + char *tso_headers; + dma_addr_t tso_headers_dma; } ____cacheline_aligned_in_smp; static inline void enetc_bdr_idx_inc(struct enetc_bdr *bdr, int *i) diff --git a/drivers/net/ethernet/freescale/enetc/enetc_hw.h b/drivers/net/ethernet/freescale/enetc/enetc_hw.h index 0f5f081a5baf..1514e6a4a3ff 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_hw.h +++ b/drivers/net/ethernet/freescale/enetc/enetc_hw.h @@ -635,10 +635,14 @@ struct enetc_cmd_rfse { #define ENETC_RFSE_EN BIT(15) #define ENETC_RFSE_MODE_BD 2 -static inline void enetc_get_primary_mac_addr(struct enetc_hw *hw, u8 *addr) +static inline void enetc_load_primary_mac_addr(struct enetc_hw *hw, + struct net_device *ndev) { + u8 addr[ETH_ALEN] __aligned(4); + *(u32 *)addr = __raw_readl(hw->reg + ENETC_SIPMAR0); *(u16 *)(addr + 4) = __raw_readw(hw->reg + ENETC_SIPMAR1); + eth_hw_addr_set(ndev, addr); } #define ENETC_SI_INT_IDX 0 diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c index 343f13666ce2..64f92770691f 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c @@ -762,10 +762,14 @@ static void enetc_pf_netdev_setup(struct enetc_si *si, struct net_device *ndev, ndev->hw_features = NETIF_F_SG | NETIF_F_RXCSUM | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX | - NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_LOOPBACK; + NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_LOOPBACK | + NETIF_F_HW_CSUM | NETIF_F_TSO | NETIF_F_TSO6; ndev->features = NETIF_F_HIGHDMA | NETIF_F_SG | NETIF_F_RXCSUM | NETIF_F_HW_VLAN_CTAG_TX | - NETIF_F_HW_VLAN_CTAG_RX; + NETIF_F_HW_VLAN_CTAG_RX | + NETIF_F_HW_CSUM | NETIF_F_TSO | NETIF_F_TSO6; + ndev->vlan_features = NETIF_F_SG | NETIF_F_HW_CSUM | + NETIF_F_TSO | NETIF_F_TSO6; if (si->num_rss) ndev->hw_features |= NETIF_F_RXHASH; @@ -782,7 +786,7 @@ static void enetc_pf_netdev_setup(struct enetc_si *si, struct net_device *ndev, } /* pick up primary MAC address from SI */ - enetc_get_primary_mac_addr(&si->hw, ndev->dev_addr); + enetc_load_primary_mac_addr(&si->hw, ndev); } static int enetc_mdio_probe(struct enetc_pf *pf, struct device_node *np) diff --git a/drivers/net/ethernet/freescale/enetc/enetc_qos.c b/drivers/net/ethernet/freescale/enetc/enetc_qos.c index 4577226d3c6a..0536d2c76fbc 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_qos.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_qos.c @@ -486,14 +486,16 @@ static int enetc_streamid_hw_set(struct enetc_ndev_priv *priv, data_size = sizeof(struct streamid_data); si_data = kzalloc(data_size, __GFP_DMA | GFP_KERNEL); + if (!si_data) + return -ENOMEM; cbd.length = cpu_to_le16(data_size); dma = dma_map_single(&priv->si->pdev->dev, si_data, data_size, DMA_FROM_DEVICE); if (dma_mapping_error(&priv->si->pdev->dev, dma)) { netdev_err(priv->si->ndev, "DMA mapping failed!\n"); - kfree(si_data); - return -ENOMEM; + err = -ENOMEM; + goto out; } cbd.addr[0] = cpu_to_le32(lower_32_bits(dma)); @@ -512,12 +514,10 @@ static int enetc_streamid_hw_set(struct enetc_ndev_priv *priv, err = enetc_send_cmd(priv->si, &cbd); if (err) - return -EINVAL; + goto out; - if (!enable) { - kfree(si_data); - return 0; - } + if (!enable) + goto out; /* Enable the entry overwrite again incase space flushed by hardware */ memset(&cbd, 0, sizeof(cbd)); @@ -560,6 +560,10 @@ static int enetc_streamid_hw_set(struct enetc_ndev_priv *priv, } err = enetc_send_cmd(priv->si, &cbd); +out: + if (!dma_mapping_error(&priv->si->pdev->dev, dma)) + dma_unmap_single(&priv->si->pdev->dev, dma, data_size, DMA_FROM_DEVICE); + kfree(si_data); return err; diff --git a/drivers/net/ethernet/freescale/enetc/enetc_vf.c b/drivers/net/ethernet/freescale/enetc/enetc_vf.c index 0704f6bf12fd..17924305afa2 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_vf.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_vf.c @@ -122,16 +122,20 @@ static void enetc_vf_netdev_setup(struct enetc_si *si, struct net_device *ndev, ndev->hw_features = NETIF_F_SG | NETIF_F_RXCSUM | NETIF_F_HW_VLAN_CTAG_TX | - NETIF_F_HW_VLAN_CTAG_RX; + NETIF_F_HW_VLAN_CTAG_RX | + NETIF_F_HW_CSUM | NETIF_F_TSO | NETIF_F_TSO6; ndev->features = NETIF_F_HIGHDMA | NETIF_F_SG | NETIF_F_RXCSUM | NETIF_F_HW_VLAN_CTAG_TX | - NETIF_F_HW_VLAN_CTAG_RX; + NETIF_F_HW_VLAN_CTAG_RX | + NETIF_F_HW_CSUM | NETIF_F_TSO | NETIF_F_TSO6; + ndev->vlan_features = NETIF_F_SG | NETIF_F_HW_CSUM | + NETIF_F_TSO | NETIF_F_TSO6; if (si->num_rss) ndev->hw_features |= NETIF_F_RXHASH; /* pick up primary MAC address from SI */ - enetc_get_primary_mac_addr(&si->hw, ndev->dev_addr); + enetc_load_primary_mac_addr(&si->hw, ndev); } static int enetc_vf_probe(struct pci_dev *pdev, diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 47a6fc702ac7..bc418b910999 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -1768,11 +1768,8 @@ static int fec_get_mac(struct net_device *ndev) return 0; } - eth_hw_addr_set(ndev, iap); - /* Adjust MAC if using macaddr */ - if (iap == macaddr) - ndev->dev_addr[ETH_ALEN-1] = macaddr[ETH_ALEN-1] + fep->dev_id; + eth_hw_addr_gen(ndev, iap, iap == macaddr ? fep->dev_id : 0); return 0; } diff --git a/drivers/net/ethernet/freescale/fman/fman_dtsec.c b/drivers/net/ethernet/freescale/fman/fman_dtsec.c index bce3c9398887..1950a8936bc0 100644 --- a/drivers/net/ethernet/freescale/fman/fman_dtsec.c +++ b/drivers/net/ethernet/freescale/fman/fman_dtsec.c @@ -366,7 +366,7 @@ static void set_dflts(struct dtsec_cfg *cfg) cfg->maximum_frame = DEFAULT_MAXIMUM_FRAME; } -static void set_mac_address(struct dtsec_regs __iomem *regs, u8 *adr) +static void set_mac_address(struct dtsec_regs __iomem *regs, const u8 *adr) { u32 tmp; @@ -516,7 +516,7 @@ static int init(struct dtsec_regs __iomem *regs, struct dtsec_cfg *cfg, if (addr) { MAKE_ENET_ADDR_FROM_UINT64(addr, eth_addr); - set_mac_address(regs, (u8 *)eth_addr); + set_mac_address(regs, (const u8 *)eth_addr); } /* HASH */ @@ -1022,7 +1022,7 @@ int dtsec_accept_rx_pause_frames(struct fman_mac *dtsec, bool en) return 0; } -int dtsec_modify_mac_address(struct fman_mac *dtsec, enet_addr_t *enet_addr) +int dtsec_modify_mac_address(struct fman_mac *dtsec, const enet_addr_t *enet_addr) { struct dtsec_regs __iomem *regs = dtsec->regs; enum comm_mode mode = COMM_MODE_NONE; @@ -1041,7 +1041,7 @@ int dtsec_modify_mac_address(struct fman_mac *dtsec, enet_addr_t *enet_addr) * Station address have to be swapped (big endian to little endian */ dtsec->addr = ENET_ADDR_TO_UINT64(*enet_addr); - set_mac_address(dtsec->regs, (u8 *)(*enet_addr)); + set_mac_address(dtsec->regs, (const u8 *)(*enet_addr)); graceful_start(dtsec, mode); diff --git a/drivers/net/ethernet/freescale/fman/fman_dtsec.h b/drivers/net/ethernet/freescale/fman/fman_dtsec.h index 5149d96ec2c1..68512c3bd6e5 100644 --- a/drivers/net/ethernet/freescale/fman/fman_dtsec.h +++ b/drivers/net/ethernet/freescale/fman/fman_dtsec.h @@ -37,7 +37,7 @@ struct fman_mac *dtsec_config(struct fman_mac_params *params); int dtsec_set_promiscuous(struct fman_mac *dtsec, bool new_val); -int dtsec_modify_mac_address(struct fman_mac *dtsec, enet_addr_t *enet_addr); +int dtsec_modify_mac_address(struct fman_mac *dtsec, const enet_addr_t *enet_addr); int dtsec_adjust_link(struct fman_mac *dtsec, u16 speed); int dtsec_restart_autoneg(struct fman_mac *dtsec); diff --git a/drivers/net/ethernet/freescale/fman/fman_memac.c b/drivers/net/ethernet/freescale/fman/fman_memac.c index 62f42921933d..2216b7f51d26 100644 --- a/drivers/net/ethernet/freescale/fman/fman_memac.c +++ b/drivers/net/ethernet/freescale/fman/fman_memac.c @@ -354,7 +354,7 @@ struct fman_mac { bool allmulti_enabled; }; -static void add_addr_in_paddr(struct memac_regs __iomem *regs, u8 *adr, +static void add_addr_in_paddr(struct memac_regs __iomem *regs, const u8 *adr, u8 paddr_num) { u32 tmp0, tmp1; @@ -897,12 +897,12 @@ int memac_accept_rx_pause_frames(struct fman_mac *memac, bool en) return 0; } -int memac_modify_mac_address(struct fman_mac *memac, enet_addr_t *enet_addr) +int memac_modify_mac_address(struct fman_mac *memac, const enet_addr_t *enet_addr) { if (!is_init_done(memac->memac_drv_param)) return -EINVAL; - add_addr_in_paddr(memac->regs, (u8 *)(*enet_addr), 0); + add_addr_in_paddr(memac->regs, (const u8 *)(*enet_addr), 0); return 0; } @@ -1058,7 +1058,7 @@ int memac_init(struct fman_mac *memac) /* MAC Address */ if (memac->addr != 0) { MAKE_ENET_ADDR_FROM_UINT64(memac->addr, eth_addr); - add_addr_in_paddr(memac->regs, (u8 *)eth_addr, 0); + add_addr_in_paddr(memac->regs, (const u8 *)eth_addr, 0); } fixed_link = memac_drv_param->fixed_link; diff --git a/drivers/net/ethernet/freescale/fman/fman_memac.h b/drivers/net/ethernet/freescale/fman/fman_memac.h index b2c671ec0ce7..3820f7a22983 100644 --- a/drivers/net/ethernet/freescale/fman/fman_memac.h +++ b/drivers/net/ethernet/freescale/fman/fman_memac.h @@ -40,7 +40,7 @@ struct fman_mac *memac_config(struct fman_mac_params *params); int memac_set_promiscuous(struct fman_mac *memac, bool new_val); -int memac_modify_mac_address(struct fman_mac *memac, enet_addr_t *enet_addr); +int memac_modify_mac_address(struct fman_mac *memac, const enet_addr_t *enet_addr); int memac_adjust_link(struct fman_mac *memac, u16 speed); int memac_cfg_max_frame_len(struct fman_mac *memac, u16 new_val); int memac_cfg_reset_on_init(struct fman_mac *memac, bool enable); diff --git a/drivers/net/ethernet/freescale/fman/fman_tgec.c b/drivers/net/ethernet/freescale/fman/fman_tgec.c index 41946b16f6c7..311c1906e044 100644 --- a/drivers/net/ethernet/freescale/fman/fman_tgec.c +++ b/drivers/net/ethernet/freescale/fman/fman_tgec.c @@ -221,7 +221,7 @@ struct fman_mac { bool allmulti_enabled; }; -static void set_mac_address(struct tgec_regs __iomem *regs, u8 *adr) +static void set_mac_address(struct tgec_regs __iomem *regs, const u8 *adr) { u32 tmp0, tmp1; @@ -514,13 +514,13 @@ int tgec_accept_rx_pause_frames(struct fman_mac *tgec, bool en) return 0; } -int tgec_modify_mac_address(struct fman_mac *tgec, enet_addr_t *p_enet_addr) +int tgec_modify_mac_address(struct fman_mac *tgec, const enet_addr_t *p_enet_addr) { if (!is_init_done(tgec->cfg)) return -EINVAL; tgec->addr = ENET_ADDR_TO_UINT64(*p_enet_addr); - set_mac_address(tgec->regs, (u8 *)(*p_enet_addr)); + set_mac_address(tgec->regs, (const u8 *)(*p_enet_addr)); return 0; } @@ -704,7 +704,7 @@ int tgec_init(struct fman_mac *tgec) if (tgec->addr) { MAKE_ENET_ADDR_FROM_UINT64(tgec->addr, eth_addr); - set_mac_address(tgec->regs, (u8 *)eth_addr); + set_mac_address(tgec->regs, (const u8 *)eth_addr); } /* interrupts */ diff --git a/drivers/net/ethernet/freescale/fman/fman_tgec.h b/drivers/net/ethernet/freescale/fman/fman_tgec.h index 3bfd1062b386..b28b20b26148 100644 --- a/drivers/net/ethernet/freescale/fman/fman_tgec.h +++ b/drivers/net/ethernet/freescale/fman/fman_tgec.h @@ -37,7 +37,7 @@ struct fman_mac *tgec_config(struct fman_mac_params *params); int tgec_set_promiscuous(struct fman_mac *tgec, bool new_val); -int tgec_modify_mac_address(struct fman_mac *tgec, enet_addr_t *enet_addr); +int tgec_modify_mac_address(struct fman_mac *tgec, const enet_addr_t *enet_addr); int tgec_cfg_max_frame_len(struct fman_mac *tgec, u16 new_val); int tgec_enable(struct fman_mac *tgec, enum comm_mode mode); int tgec_disable(struct fman_mac *tgec, enum comm_mode mode); diff --git a/drivers/net/ethernet/freescale/fman/mac.h b/drivers/net/ethernet/freescale/fman/mac.h index 824a81a9f350..daa285a9b8b2 100644 --- a/drivers/net/ethernet/freescale/fman/mac.h +++ b/drivers/net/ethernet/freescale/fman/mac.h @@ -66,7 +66,7 @@ struct mac_device { int (*stop)(struct mac_device *mac_dev); void (*adjust_link)(struct mac_device *mac_dev); int (*set_promisc)(struct fman_mac *mac_dev, bool enable); - int (*change_addr)(struct fman_mac *mac_dev, enet_addr_t *enet_addr); + int (*change_addr)(struct fman_mac *mac_dev, const enet_addr_t *enet_addr); int (*set_allmulti)(struct fman_mac *mac_dev, bool enable); int (*set_tstamp)(struct fman_mac *mac_dev, bool enable); int (*set_multi)(struct net_device *net_dev, diff --git a/drivers/net/ethernet/fujitsu/fmvj18x_cs.c b/drivers/net/ethernet/fujitsu/fmvj18x_cs.c index 62c0bed82ced..b0d733e9a7c6 100644 --- a/drivers/net/ethernet/fujitsu/fmvj18x_cs.c +++ b/drivers/net/ethernet/fujitsu/fmvj18x_cs.c @@ -334,6 +334,7 @@ static int fmvj18x_config(struct pcmcia_device *link) u8 *buf; size_t len; u_char buggybuf[32]; + u8 addr[ETH_ALEN]; dev_dbg(&link->dev, "fmvj18x_config\n"); @@ -468,8 +469,7 @@ static int fmvj18x_config(struct pcmcia_device *link) goto failed; } /* Read MACID from CIS */ - for (i = 0; i < 6; i++) - dev->dev_addr[i] = buf[i + 5]; + eth_hw_addr_set(dev, &buf[5]); kfree(buf); } else { if (pcmcia_get_mac_from_cis(link, dev)) @@ -490,7 +490,8 @@ static int fmvj18x_config(struct pcmcia_device *link) case UNGERMANN: /* Read MACID from register */ for (i = 0; i < 6; i++) - dev->dev_addr[i] = inb(ioaddr + UNGERMANN_MAC_ID + i); + addr[i] = inb(ioaddr + UNGERMANN_MAC_ID + i); + eth_hw_addr_set(dev, addr); card_name = "Access/CARD"; break; case XXX10304: @@ -499,16 +500,15 @@ static int fmvj18x_config(struct pcmcia_device *link) pr_notice("unable to read hardware net address\n"); goto failed; } - for (i = 0 ; i < 6; i++) { - dev->dev_addr[i] = buggybuf[i]; - } + eth_hw_addr_set(dev, buggybuf); card_name = "FMV-J182"; break; case MBH10302: default: /* Read MACID from register */ for (i = 0; i < 6; i++) - dev->dev_addr[i] = inb(ioaddr + MAC_ID + i); + addr[i] = inb(ioaddr + MAC_ID + i); + eth_hw_addr_set(dev, addr); card_name = "FMV-J181"; break; } diff --git a/drivers/net/ethernet/google/gve/gve.h b/drivers/net/ethernet/google/gve/gve.h index 2f93ed470590..51ed8fe71d2d 100644 --- a/drivers/net/ethernet/google/gve/gve.h +++ b/drivers/net/ethernet/google/gve/gve.h @@ -30,7 +30,7 @@ #define GVE_MIN_MSIX 3 /* Numbers of gve tx/rx stats in stats report. */ -#define GVE_TX_STATS_REPORT_NUM 5 +#define GVE_TX_STATS_REPORT_NUM 6 #define GVE_RX_STATS_REPORT_NUM 2 /* Interval to schedule a stats report update, 20000ms. */ @@ -341,8 +341,8 @@ struct gve_tx_ring { union { /* GQI fields */ struct { - /* NIC tail pointer */ - __be32 last_nic_done; + /* Spinlock for when cleanup in progress */ + spinlock_t clean_lock; }; /* DQO fields. */ @@ -413,7 +413,9 @@ struct gve_tx_ring { u32 q_num ____cacheline_aligned; /* queue idx */ u32 stop_queue; /* count of queue stops */ u32 wake_queue; /* count of queue wakes */ + u32 queue_timeout; /* count of queue timeouts */ u32 ntfy_id; /* notification block index */ + u32 last_kick_msec; /* Last time the queue was kicked */ dma_addr_t bus; /* dma address of the descr ring */ dma_addr_t q_resources_bus; /* dma address of the queue resources */ dma_addr_t complq_bus_dqo; /* dma address of the dqo.compl_ring */ @@ -821,15 +823,15 @@ netdev_tx_t gve_tx(struct sk_buff *skb, struct net_device *dev); bool gve_tx_poll(struct gve_notify_block *block, int budget); int gve_tx_alloc_rings(struct gve_priv *priv); void gve_tx_free_rings_gqi(struct gve_priv *priv); -__be32 gve_tx_load_event_counter(struct gve_priv *priv, - struct gve_tx_ring *tx); +u32 gve_tx_load_event_counter(struct gve_priv *priv, + struct gve_tx_ring *tx); +bool gve_tx_clean_pending(struct gve_priv *priv, struct gve_tx_ring *tx); /* rx handling */ void gve_rx_write_doorbell(struct gve_priv *priv, struct gve_rx_ring *rx); -bool gve_rx_poll(struct gve_notify_block *block, int budget); +int gve_rx_poll(struct gve_notify_block *block, int budget); +bool gve_rx_work_pending(struct gve_rx_ring *rx); int gve_rx_alloc_rings(struct gve_priv *priv); void gve_rx_free_rings_gqi(struct gve_priv *priv); -bool gve_clean_rx_done(struct gve_rx_ring *rx, int budget, - netdev_features_t feat); /* Reset */ void gve_schedule_reset(struct gve_priv *priv); int gve_reset(struct gve_priv *priv, bool attempt_teardown); diff --git a/drivers/net/ethernet/google/gve/gve_adminq.h b/drivers/net/ethernet/google/gve/gve_adminq.h index 47c3d8f313fc..3953f6f7a427 100644 --- a/drivers/net/ethernet/google/gve/gve_adminq.h +++ b/drivers/net/ethernet/google/gve/gve_adminq.h @@ -270,6 +270,7 @@ enum gve_stat_names { TX_LAST_COMPLETION_PROCESSED = 5, RX_NEXT_EXPECTED_SEQUENCE = 6, RX_BUFFERS_POSTED = 7, + TX_TIMEOUT_CNT = 8, // stats from NIC RX_QUEUE_DROP_CNT = 65, RX_NO_BUFFERS_POSTED = 66, diff --git a/drivers/net/ethernet/google/gve/gve_ethtool.c b/drivers/net/ethernet/google/gve/gve_ethtool.c index 716e6240305d..618a3e1d858e 100644 --- a/drivers/net/ethernet/google/gve/gve_ethtool.c +++ b/drivers/net/ethernet/google/gve/gve_ethtool.c @@ -330,8 +330,7 @@ gve_get_ethtool_stats(struct net_device *netdev, data[i++] = tmp_tx_bytes; data[i++] = tx->wake_queue; data[i++] = tx->stop_queue; - data[i++] = be32_to_cpu(gve_tx_load_event_counter(priv, - tx)); + data[i++] = gve_tx_load_event_counter(priv, tx); data[i++] = tx->dma_mapping_error; /* stats from NIC */ if (skip_nic_stats) { diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index 5b5dcaaeed7f..7647cd05b1d2 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -24,6 +24,9 @@ #define GVE_VERSION "1.0.0" #define GVE_VERSION_PREFIX "GVE-" +// Minimum amount of time between queue kicks in msec (10 seconds) +#define MIN_TX_TIMEOUT_GAP (1000 * 10) + const char gve_version_str[] = GVE_VERSION; static const char gve_version_prefix[] = GVE_VERSION_PREFIX; @@ -192,34 +195,40 @@ static int gve_napi_poll(struct napi_struct *napi, int budget) __be32 __iomem *irq_doorbell; bool reschedule = false; struct gve_priv *priv; + int work_done = 0; block = container_of(napi, struct gve_notify_block, napi); priv = block->priv; if (block->tx) reschedule |= gve_tx_poll(block, budget); - if (block->rx) - reschedule |= gve_rx_poll(block, budget); + if (block->rx) { + work_done = gve_rx_poll(block, budget); + reschedule |= work_done == budget; + } if (reschedule) return budget; - napi_complete(napi); - irq_doorbell = gve_irq_doorbell(priv, block); - iowrite32be(GVE_IRQ_ACK | GVE_IRQ_EVENT, irq_doorbell); + /* Complete processing - don't unmask irq if busy polling is enabled */ + if (likely(napi_complete_done(napi, work_done))) { + irq_doorbell = gve_irq_doorbell(priv, block); + iowrite32be(GVE_IRQ_ACK | GVE_IRQ_EVENT, irq_doorbell); - /* Double check we have no extra work. - * Ensure unmask synchronizes with checking for work. - */ - mb(); - if (block->tx) - reschedule |= gve_tx_poll(block, -1); - if (block->rx) - reschedule |= gve_rx_poll(block, -1); - if (reschedule && napi_reschedule(napi)) - iowrite32be(GVE_IRQ_MASK, irq_doorbell); + /* Ensure IRQ ACK is visible before we check pending work. + * If queue had issued updates, it would be truly visible. + */ + mb(); - return 0; + if (block->tx) + reschedule |= gve_tx_clean_pending(priv, block->tx); + if (block->rx) + reschedule |= gve_rx_work_pending(block->rx); + + if (reschedule && napi_reschedule(napi)) + iowrite32be(GVE_IRQ_MASK, irq_doorbell); + } + return work_done; } static int gve_napi_poll_dqo(struct napi_struct *napi, int budget) @@ -1115,9 +1124,47 @@ static void gve_turnup(struct gve_priv *priv) static void gve_tx_timeout(struct net_device *dev, unsigned int txqueue) { - struct gve_priv *priv = netdev_priv(dev); + struct gve_notify_block *block; + struct gve_tx_ring *tx = NULL; + struct gve_priv *priv; + u32 last_nic_done; + u32 current_time; + u32 ntfy_idx; + netdev_info(dev, "Timeout on tx queue, %d", txqueue); + priv = netdev_priv(dev); + if (txqueue > priv->tx_cfg.num_queues) + goto reset; + + ntfy_idx = gve_tx_idx_to_ntfy(priv, txqueue); + if (ntfy_idx > priv->num_ntfy_blks) + goto reset; + + block = &priv->ntfy_blocks[ntfy_idx]; + tx = block->tx; + + current_time = jiffies_to_msecs(jiffies); + if (tx->last_kick_msec + MIN_TX_TIMEOUT_GAP > current_time) + goto reset; + + /* Check to see if there are missed completions, which will allow us to + * kick the queue. + */ + last_nic_done = gve_tx_load_event_counter(priv, tx); + if (last_nic_done - tx->done) { + netdev_info(dev, "Kicking queue %d", txqueue); + iowrite32be(GVE_IRQ_MASK, gve_irq_doorbell(priv, block)); + napi_schedule(&block->napi); + tx->last_kick_msec = current_time; + goto out; + } // Else reset. + +reset: gve_schedule_reset(priv); + +out: + if (tx) + tx->queue_timeout++; priv->tx_timeo_cnt++; } @@ -1246,6 +1293,11 @@ void gve_handle_report_stats(struct gve_priv *priv) .value = cpu_to_be64(last_completion), .queue_id = cpu_to_be32(idx), }; + stats[stats_idx++] = (struct stats) { + .stat_name = cpu_to_be32(TX_TIMEOUT_CNT), + .value = cpu_to_be64(priv->tx[idx].queue_timeout), + .queue_id = cpu_to_be32(idx), + }; } } /* rx stats */ diff --git a/drivers/net/ethernet/google/gve/gve_rx.c b/drivers/net/ethernet/google/gve/gve_rx.c index 94941d4e4744..95bc4d8a1811 100644 --- a/drivers/net/ethernet/google/gve/gve_rx.c +++ b/drivers/net/ethernet/google/gve/gve_rx.c @@ -16,19 +16,23 @@ static void gve_rx_free_buffer(struct device *dev, dma_addr_t dma = (dma_addr_t)(be64_to_cpu(data_slot->addr) & GVE_DATA_SLOT_ADDR_PAGE_MASK); + page_ref_sub(page_info->page, page_info->pagecnt_bias - 1); gve_free_page(dev, page_info->page, dma, DMA_FROM_DEVICE); } static void gve_rx_unfill_pages(struct gve_priv *priv, struct gve_rx_ring *rx) { - if (rx->data.raw_addressing) { - u32 slots = rx->mask + 1; - int i; + u32 slots = rx->mask + 1; + int i; + if (rx->data.raw_addressing) { for (i = 0; i < slots; i++) gve_rx_free_buffer(&priv->pdev->dev, &rx->data.page_info[i], &rx->data.data_ring[i]); } else { + for (i = 0; i < slots; i++) + page_ref_sub(rx->data.page_info[i].page, + rx->data.page_info[i].pagecnt_bias - 1); gve_unassign_qpl(priv, rx->data.qpl->id); rx->data.qpl = NULL; } @@ -69,6 +73,9 @@ static void gve_setup_rx_buffer(struct gve_rx_slot_page_info *page_info, page_info->page_offset = 0; page_info->page_address = page_address(page); *slot_addr = cpu_to_be64(addr); + /* The page already has 1 ref */ + page_ref_add(page, INT_MAX - 1); + page_info->pagecnt_bias = INT_MAX; } static int gve_rx_alloc_buffer(struct gve_priv *priv, struct device *dev, @@ -295,21 +302,22 @@ static void gve_rx_flip_buff(struct gve_rx_slot_page_info *page_info, __be64 *sl static bool gve_rx_can_flip_buffers(struct net_device *netdev) { - return PAGE_SIZE == 4096 + return PAGE_SIZE >= 4096 ? netdev->mtu + GVE_RX_PAD + ETH_HLEN <= PAGE_SIZE / 2 : false; } -static int gve_rx_can_recycle_buffer(struct page *page) +static int gve_rx_can_recycle_buffer(struct gve_rx_slot_page_info *page_info) { - int pagecount = page_count(page); + int pagecount = page_count(page_info->page); /* This page is not being used by any SKBs - reuse */ - if (pagecount == 1) + if (pagecount == page_info->pagecnt_bias) return 1; /* This page is still being used by an SKB - we can't reuse */ - else if (pagecount >= 2) + else if (pagecount > page_info->pagecnt_bias) return 0; - WARN(pagecount < 1, "Pagecount should never be < 1"); + WARN(pagecount < page_info->pagecnt_bias, + "Pagecount should never be less than the bias."); return -1; } @@ -325,11 +333,11 @@ gve_rx_raw_addressing(struct device *dev, struct net_device *netdev, if (!skb) return NULL; - /* Optimistically stop the kernel from freeing the page by increasing - * the page bias. We will check the refcount in refill to determine if - * we need to alloc a new page. + /* Optimistically stop the kernel from freeing the page. + * We will check again in refill to determine if we need to alloc a + * new page. */ - get_page(page_info->page); + gve_dec_pagecnt_bias(page_info); return skb; } @@ -352,7 +360,7 @@ gve_rx_qpl(struct device *dev, struct net_device *netdev, /* No point in recycling if we didn't get the skb */ if (skb) { /* Make sure that the page isn't freed. */ - get_page(page_info->page); + gve_dec_pagecnt_bias(page_info); gve_rx_flip_buff(page_info, &data_slot->qpl_offset); } } else { @@ -376,8 +384,18 @@ static bool gve_rx(struct gve_rx_ring *rx, struct gve_rx_desc *rx_desc, union gve_rx_data_slot *data_slot; struct sk_buff *skb = NULL; dma_addr_t page_bus; + void *va; u16 len; + /* Prefetch two packet pages ahead, we will need it soon. */ + page_info = &rx->data.page_info[(idx + 2) & rx->mask]; + va = page_info->page_address + GVE_RX_PAD + + page_info->page_offset; + + prefetch(page_info->page); /* Kernel page struct. */ + prefetch(va); /* Packet header. */ + prefetch(va + 64); /* Next cacheline too. */ + /* drop this packet */ if (unlikely(rx_desc->flags_seq & GVE_RXF_ERR)) { u64_stats_update_begin(&rx->statss); @@ -408,7 +426,7 @@ static bool gve_rx(struct gve_rx_ring *rx, struct gve_rx_desc *rx_desc, int recycle = 0; if (can_flip) { - recycle = gve_rx_can_recycle_buffer(page_info->page); + recycle = gve_rx_can_recycle_buffer(page_info); if (recycle < 0) { if (!rx->data.raw_addressing) gve_schedule_reset(priv); @@ -456,7 +474,7 @@ static bool gve_rx(struct gve_rx_ring *rx, struct gve_rx_desc *rx_desc, return true; } -static bool gve_rx_work_pending(struct gve_rx_ring *rx) +bool gve_rx_work_pending(struct gve_rx_ring *rx) { struct gve_rx_desc *desc; __be16 flags_seq; @@ -499,7 +517,7 @@ static bool gve_rx_refill_buffers(struct gve_priv *priv, struct gve_rx_ring *rx) * owns half the page it is impossible to tell which half. Either * the whole page is free or it needs to be replaced. */ - int recycle = gve_rx_can_recycle_buffer(page_info->page); + int recycle = gve_rx_can_recycle_buffer(page_info); if (recycle < 0) { if (!rx->data.raw_addressing) @@ -514,8 +532,13 @@ static bool gve_rx_refill_buffers(struct gve_priv *priv, struct gve_rx_ring *rx) gve_rx_free_buffer(dev, page_info, data_slot); page_info->page = NULL; - if (gve_rx_alloc_buffer(priv, dev, page_info, data_slot)) + if (gve_rx_alloc_buffer(priv, dev, page_info, + data_slot)) { + u64_stats_update_begin(&rx->statss); + rx->rx_buf_alloc_fail++; + u64_stats_update_end(&rx->statss); break; + } } } fill_cnt++; @@ -524,8 +547,8 @@ static bool gve_rx_refill_buffers(struct gve_priv *priv, struct gve_rx_ring *rx) return true; } -bool gve_clean_rx_done(struct gve_rx_ring *rx, int budget, - netdev_features_t feat) +static int gve_clean_rx_done(struct gve_rx_ring *rx, int budget, + netdev_features_t feat) { struct gve_priv *priv = rx->gve; u32 work_done = 0, packets = 0; @@ -546,6 +569,10 @@ bool gve_clean_rx_done(struct gve_rx_ring *rx, int budget, "[%d] seqno=%d rx->desc.seqno=%d\n", rx->q_num, GVE_SEQNO(desc->flags_seq), rx->desc.seqno); + + /* prefetch two descriptors ahead */ + prefetch(rx->desc.desc_ring + ((cnt + 2) & rx->mask)); + dropped = !gve_rx(rx, desc, feat, idx); if (!dropped) { bytes += be16_to_cpu(desc->len) - GVE_RX_PAD; @@ -559,13 +586,15 @@ bool gve_clean_rx_done(struct gve_rx_ring *rx, int budget, } if (!work_done && rx->fill_cnt - cnt > rx->db_threshold) - return false; + return 0; - u64_stats_update_begin(&rx->statss); - rx->rpackets += packets; - rx->rbytes += bytes; - u64_stats_update_end(&rx->statss); - rx->cnt = cnt; + if (work_done) { + u64_stats_update_begin(&rx->statss); + rx->rpackets += packets; + rx->rbytes += bytes; + u64_stats_update_end(&rx->statss); + rx->cnt = cnt; + } /* restock ring slots */ if (!rx->data.raw_addressing) { @@ -576,26 +605,26 @@ bool gve_clean_rx_done(struct gve_rx_ring *rx, int budget, * falls below a threshold. */ if (!gve_rx_refill_buffers(priv, rx)) - return false; + return 0; /* If we were not able to completely refill buffers, we'll want * to schedule this queue for work again to refill buffers. */ if (rx->fill_cnt - cnt <= rx->db_threshold) { gve_rx_write_doorbell(priv, rx); - return true; + return budget; } } gve_rx_write_doorbell(priv, rx); - return gve_rx_work_pending(rx); + return work_done; } -bool gve_rx_poll(struct gve_notify_block *block, int budget) +int gve_rx_poll(struct gve_notify_block *block, int budget) { struct gve_rx_ring *rx = block->rx; netdev_features_t feat; - bool repoll = false; + int work_done = 0; feat = block->napi.dev->features; @@ -604,8 +633,7 @@ bool gve_rx_poll(struct gve_notify_block *block, int budget) budget = INT_MAX; if (budget > 0) - repoll |= gve_clean_rx_done(rx, budget, feat); - else - repoll |= gve_rx_work_pending(rx); - return repoll; + work_done = gve_clean_rx_done(rx, budget, feat); + + return work_done; } diff --git a/drivers/net/ethernet/google/gve/gve_tx.c b/drivers/net/ethernet/google/gve/gve_tx.c index 9922ce46a635..a9cb241fedf4 100644 --- a/drivers/net/ethernet/google/gve/gve_tx.c +++ b/drivers/net/ethernet/google/gve/gve_tx.c @@ -144,7 +144,7 @@ static void gve_tx_free_ring(struct gve_priv *priv, int idx) gve_tx_remove_from_block(priv, idx); slots = tx->mask + 1; - gve_clean_tx_done(priv, tx, tx->req, false); + gve_clean_tx_done(priv, tx, priv->tx_desc_cnt, false); netdev_tx_reset_queue(tx->netdev_txq); dma_free_coherent(hdev, sizeof(*tx->q_resources), @@ -176,6 +176,7 @@ static int gve_tx_alloc_ring(struct gve_priv *priv, int idx) /* Make sure everything is zeroed to start */ memset(tx, 0, sizeof(*tx)); + spin_lock_init(&tx->clean_lock); tx->q_num = idx; tx->mask = slots - 1; @@ -328,10 +329,16 @@ static inline bool gve_can_tx(struct gve_tx_ring *tx, int bytes_required) return (gve_tx_avail(tx) >= MAX_TX_DESC_NEEDED && can_alloc); } +static_assert(NAPI_POLL_WEIGHT >= MAX_TX_DESC_NEEDED); + /* Stops the queue if the skb cannot be transmitted. */ -static int gve_maybe_stop_tx(struct gve_tx_ring *tx, struct sk_buff *skb) +static int gve_maybe_stop_tx(struct gve_priv *priv, struct gve_tx_ring *tx, + struct sk_buff *skb) { int bytes_required = 0; + u32 nic_done; + u32 to_do; + int ret; if (!tx->raw_addressing) bytes_required = gve_skb_fifo_bytes_required(tx, skb); @@ -339,29 +346,28 @@ static int gve_maybe_stop_tx(struct gve_tx_ring *tx, struct sk_buff *skb) if (likely(gve_can_tx(tx, bytes_required))) return 0; - /* No space, so stop the queue */ - tx->stop_queue++; - netif_tx_stop_queue(tx->netdev_txq); - smp_mb(); /* sync with restarting queue in gve_clean_tx_done() */ + ret = -EBUSY; + spin_lock(&tx->clean_lock); + nic_done = gve_tx_load_event_counter(priv, tx); + to_do = nic_done - tx->done; - /* Now check for resources again, in case gve_clean_tx_done() freed - * resources after we checked and we stopped the queue after - * gve_clean_tx_done() checked. - * - * gve_maybe_stop_tx() gve_clean_tx_done() - * nsegs/can_alloc test failed - * gve_tx_free_fifo() - * if (tx queue stopped) - * netif_tx_queue_wake() - * netif_tx_stop_queue() - * Need to check again for space here! - */ - if (likely(!gve_can_tx(tx, bytes_required))) - return -EBUSY; + /* Only try to clean if there is hope for TX */ + if (to_do + gve_tx_avail(tx) >= MAX_TX_DESC_NEEDED) { + if (to_do > 0) { + to_do = min_t(u32, to_do, NAPI_POLL_WEIGHT); + gve_clean_tx_done(priv, tx, to_do, false); + } + if (likely(gve_can_tx(tx, bytes_required))) + ret = 0; + } + if (ret) { + /* No space, so stop the queue */ + tx->stop_queue++; + netif_tx_stop_queue(tx->netdev_txq); + } + spin_unlock(&tx->clean_lock); - netif_tx_start_queue(tx->netdev_txq); - tx->wake_queue++; - return 0; + return ret; } static void gve_tx_fill_pkt_desc(union gve_tx_desc *pkt_desc, @@ -576,7 +582,7 @@ netdev_tx_t gve_tx(struct sk_buff *skb, struct net_device *dev) WARN(skb_get_queue_mapping(skb) >= priv->tx_cfg.num_queues, "skb queue index out of range"); tx = &priv->tx[skb_get_queue_mapping(skb)]; - if (unlikely(gve_maybe_stop_tx(tx, skb))) { + if (unlikely(gve_maybe_stop_tx(priv, tx, skb))) { /* We need to ring the txq doorbell -- we have stopped the Tx * queue for want of resources, but prior calls to gve_tx() * may have added descriptors without ringing the doorbell. @@ -672,19 +678,19 @@ static int gve_clean_tx_done(struct gve_priv *priv, struct gve_tx_ring *tx, return pkts; } -__be32 gve_tx_load_event_counter(struct gve_priv *priv, - struct gve_tx_ring *tx) +u32 gve_tx_load_event_counter(struct gve_priv *priv, + struct gve_tx_ring *tx) { - u32 counter_index = be32_to_cpu((tx->q_resources->counter_index)); + u32 counter_index = be32_to_cpu(tx->q_resources->counter_index); + __be32 counter = READ_ONCE(priv->counter_array[counter_index]); - return READ_ONCE(priv->counter_array[counter_index]); + return be32_to_cpu(counter); } bool gve_tx_poll(struct gve_notify_block *block, int budget) { struct gve_priv *priv = block->priv; struct gve_tx_ring *tx = block->tx; - bool repoll = false; u32 nic_done; u32 to_do; @@ -692,17 +698,23 @@ bool gve_tx_poll(struct gve_notify_block *block, int budget) if (budget == 0) budget = INT_MAX; + /* In TX path, it may try to clean completed pkts in order to xmit, + * to avoid cleaning conflict, use spin_lock(), it yields better + * concurrency between xmit/clean than netif's lock. + */ + spin_lock(&tx->clean_lock); /* Find out how much work there is to be done */ - tx->last_nic_done = gve_tx_load_event_counter(priv, tx); - nic_done = be32_to_cpu(tx->last_nic_done); - if (budget > 0) { - /* Do as much work as we have that the budget will - * allow - */ - to_do = min_t(u32, (nic_done - tx->done), budget); - gve_clean_tx_done(priv, tx, to_do, true); - } + nic_done = gve_tx_load_event_counter(priv, tx); + to_do = min_t(u32, (nic_done - tx->done), budget); + gve_clean_tx_done(priv, tx, to_do, true); + spin_unlock(&tx->clean_lock); /* If we still have work we want to repoll */ - repoll |= (nic_done != tx->done); - return repoll; + return nic_done != tx->done; +} + +bool gve_tx_clean_pending(struct gve_priv *priv, struct gve_tx_ring *tx) +{ + u32 nic_done = gve_tx_load_event_counter(priv, tx); + + return nic_done != tx->done; } diff --git a/drivers/net/ethernet/google/gve/gve_utils.c b/drivers/net/ethernet/google/gve/gve_utils.c index 93f3dcbeeea9..45ff7a9ab5f9 100644 --- a/drivers/net/ethernet/google/gve/gve_utils.c +++ b/drivers/net/ethernet/google/gve/gve_utils.c @@ -18,12 +18,16 @@ void gve_tx_remove_from_block(struct gve_priv *priv, int queue_idx) void gve_tx_add_to_block(struct gve_priv *priv, int queue_idx) { + unsigned int active_cpus = min_t(int, priv->num_ntfy_blks / 2, + num_online_cpus()); int ntfy_idx = gve_tx_idx_to_ntfy(priv, queue_idx); struct gve_notify_block *block = &priv->ntfy_blocks[ntfy_idx]; struct gve_tx_ring *tx = &priv->tx[queue_idx]; block->tx = tx; tx->ntfy_id = ntfy_idx; + netif_set_xps_queue(priv->dev, get_cpu_mask(ntfy_idx % active_cpus), + queue_idx); } void gve_rx_remove_from_block(struct gve_priv *priv, int queue_idx) diff --git a/drivers/net/ethernet/hisilicon/hip04_eth.c b/drivers/net/ethernet/hisilicon/hip04_eth.c index 37b605fed32c..c84ef494bd60 100644 --- a/drivers/net/ethernet/hisilicon/hip04_eth.c +++ b/drivers/net/ethernet/hisilicon/hip04_eth.c @@ -998,7 +998,7 @@ static int hip04_mac_probe(struct platform_device *pdev) hip04_config_port(ndev, SPEED_100, DUPLEX_FULL); hip04_config_fifo(priv); - eth_random_addr(ndev->dev_addr); + eth_hw_addr_random(ndev); hip04_update_mac_address(ndev); ret = hip04_alloc_ring(ndev, d); diff --git a/drivers/net/ethernet/hisilicon/hisi_femac.c b/drivers/net/ethernet/hisilicon/hisi_femac.c index 29190eb890c8..a6c18b6527f9 100644 --- a/drivers/net/ethernet/hisilicon/hisi_femac.c +++ b/drivers/net/ethernet/hisilicon/hisi_femac.c @@ -427,7 +427,7 @@ static void hisi_femac_free_skb_rings(struct hisi_femac_priv *priv) } static int hisi_femac_set_hw_mac_addr(struct hisi_femac_priv *priv, - unsigned char *mac) + const unsigned char *mac) { u32 reg; diff --git a/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c b/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c index 5f7ccdc834b7..d7e62eca050f 100644 --- a/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c +++ b/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c @@ -429,7 +429,7 @@ static void hix5hd2_port_disable(struct hix5hd2_priv *priv) static void hix5hd2_hw_set_mac_addr(struct net_device *dev) { struct hix5hd2_priv *priv = netdev_priv(dev); - unsigned char *mac = dev->dev_addr; + const unsigned char *mac = dev->dev_addr; u32 val; val = mac[1] | (mac[0] << 8); diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.h b/drivers/net/ethernet/hisilicon/hns/hnae.h index 2b7db1c22321..d72657444ef3 100644 --- a/drivers/net/ethernet/hisilicon/hns/hnae.h +++ b/drivers/net/ethernet/hisilicon/hns/hnae.h @@ -499,7 +499,7 @@ struct hnae_ae_ops { u32 *tx_usecs_high, u32 *rx_usecs_high); void (*set_promisc_mode)(struct hnae_handle *handle, u32 en); int (*get_mac_addr)(struct hnae_handle *handle, void **p); - int (*set_mac_addr)(struct hnae_handle *handle, void *p); + int (*set_mac_addr)(struct hnae_handle *handle, const void *p); int (*add_uc_addr)(struct hnae_handle *handle, const unsigned char *addr); int (*rm_uc_addr)(struct hnae_handle *handle, @@ -558,7 +558,7 @@ struct hnae_handle { enum hnae_media_type media_type; struct list_head node; /* list to hnae_ae_dev->handle_list */ struct hnae_buf_ops *bops; /* operation for the buffer */ - struct hnae_queue **qs; /* array base of all queues */ + struct hnae_queue *qs[]; /* flexible array of all queues */ }; #define ring_to_dev(ring) ((ring)->q->dev->dev) diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c index 75e4ec569da8..bc3e406f0139 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c @@ -81,8 +81,8 @@ static struct hnae_handle *hns_ae_get_handle(struct hnae_ae_dev *dev, vfnum_per_port = hns_ae_get_vf_num_per_port(dsaf_dev, port_id); qnum_per_vf = hns_ae_get_q_num_per_vf(dsaf_dev, port_id); - vf_cb = kzalloc(sizeof(*vf_cb) + - qnum_per_vf * sizeof(struct hnae_queue *), GFP_KERNEL); + vf_cb = kzalloc(struct_size(vf_cb, ae_handle.qs, qnum_per_vf), + GFP_KERNEL); if (unlikely(!vf_cb)) { dev_err(dsaf_dev->dev, "malloc vf_cb fail!\n"); ae_handle = ERR_PTR(-ENOMEM); @@ -108,7 +108,6 @@ static struct hnae_handle *hns_ae_get_handle(struct hnae_ae_dev *dev, goto vf_id_err; } - ae_handle->qs = (struct hnae_queue **)(&ae_handle->qs + 1); for (i = 0; i < qnum_per_vf; i++) { ae_handle->qs[i] = &ring_pair_cb->q; ae_handle->qs[i]->rx_ring.q = ae_handle->qs[i]; @@ -207,7 +206,7 @@ static void hns_ae_fini_queue(struct hnae_queue *q) hns_rcb_reset_ring_hw(q); } -static int hns_ae_set_mac_address(struct hnae_handle *handle, void *p) +static int hns_ae_set_mac_address(struct hnae_handle *handle, const void *p) { int ret; struct hns_mac_cb *mac_cb = hns_get_mac_cb(handle); diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c index f387a859a201..8f391e2adcc0 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c @@ -450,7 +450,7 @@ static void hns_gmac_update_stats(void *mac_drv) += dsaf_read_dev(drv, GMAC_TX_PAUSE_FRAMES_REG); } -static void hns_gmac_set_mac_addr(void *mac_drv, char *mac_addr) +static void hns_gmac_set_mac_addr(void *mac_drv, const char *mac_addr) { struct mac_driver *drv = (struct mac_driver *)mac_drv; diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c index f41379de2186..7edf8569514c 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c @@ -240,7 +240,7 @@ int hns_mac_get_inner_port_num(struct hns_mac_cb *mac_cb, u8 vmid, u8 *port_num) *@addr:mac address */ int hns_mac_change_vf_addr(struct hns_mac_cb *mac_cb, - u32 vmid, char *addr) + u32 vmid, const char *addr) { int ret; struct mac_driver *mac_ctrl_drv = hns_mac_get_drv(mac_cb); diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h index 8943ffab4418..e3bb05959ba9 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h @@ -348,7 +348,7 @@ struct mac_driver { /*disable mac when disable nic or dsaf*/ void (*mac_disable)(void *mac_drv, enum mac_commom_mode mode); /* config mac address*/ - void (*set_mac_addr)(void *mac_drv, char *mac_addr); + void (*set_mac_addr)(void *mac_drv, const char *mac_addr); /*adjust mac mode of port,include speed and duplex*/ int (*adjust_link)(void *mac_drv, enum mac_speed speed, u32 full_duplex); @@ -425,7 +425,8 @@ int hns_mac_init(struct dsaf_device *dsaf_dev); void mac_adjust_link(struct net_device *net_dev); bool hns_mac_need_adjust_link(struct hns_mac_cb *mac_cb, int speed, int duplex); void hns_mac_get_link_status(struct hns_mac_cb *mac_cb, u32 *link_status); -int hns_mac_change_vf_addr(struct hns_mac_cb *mac_cb, u32 vmid, char *addr); +int hns_mac_change_vf_addr(struct hns_mac_cb *mac_cb, u32 vmid, + const char *addr); int hns_mac_set_multi(struct hns_mac_cb *mac_cb, u32 port_num, char *addr, bool enable); int hns_mac_vm_config_bc_en(struct hns_mac_cb *mac_cb, u32 vm, bool enable); diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h index cba04bfa0b3f..5526a10caac5 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h @@ -210,7 +210,7 @@ struct hnae_vf_cb { u8 port_index; struct hns_mac_cb *mac_cb; struct dsaf_device *dsaf_dev; - struct hnae_handle ae_handle; /* must be the last number */ + struct hnae_handle ae_handle; /* must be the last member */ }; struct dsaf_int_xge_src { diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c index 401fef5f1d07..fc26ffaae620 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c @@ -255,7 +255,7 @@ static void hns_xgmac_pausefrm_cfg(void *mac_drv, u32 rx_en, u32 tx_en) dsaf_write_dev(drv, XGMAC_MAC_PAUSE_CTRL_REG, origin); } -static void hns_xgmac_set_pausefrm_mac_addr(void *mac_drv, char *mac_addr) +static void hns_xgmac_set_pausefrm_mac_addr(void *mac_drv, const char *mac_addr) { struct mac_driver *drv = (struct mac_driver *)mac_drv; diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h index 7225407b44b2..30a3954b78e0 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h +++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h @@ -298,6 +298,7 @@ enum hnae3_dbg_cmd { HNAE3_DBG_CMD_MAC_TNL_STATUS, HNAE3_DBG_CMD_SERV_INFO, HNAE3_DBG_CMD_UMV_INFO, + HNAE3_DBG_CMD_PAGE_POOL_INFO, HNAE3_DBG_CMD_UNKNOWN, }; @@ -594,7 +595,7 @@ struct hnae3_ae_ops { u32 *tx_usecs_high, u32 *rx_usecs_high); void (*get_mac_addr)(struct hnae3_handle *handle, u8 *p); - int (*set_mac_addr)(struct hnae3_handle *handle, void *p, + int (*set_mac_addr)(struct hnae3_handle *handle, const void *p, bool is_first); int (*do_ioctl)(struct hnae3_handle *handle, struct ifreq *ifr, int cmd); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c index 90045a19224b..6bc5adff496a 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c @@ -336,6 +336,13 @@ static struct hns3_dbg_cmd_info hns3_dbg_cmd[] = { .buf_len = HNS3_DBG_READ_LEN, .init = hns3_dbg_common_file_init, }, + { + .name = "page_pool_info", + .cmd = HNAE3_DBG_CMD_PAGE_POOL_INFO, + .dentry = HNS3_DBG_DENTRY_COMMON, + .buf_len = HNS3_DBG_READ_LEN, + .init = hns3_dbg_common_file_init, + }, }; static struct hns3_dbg_cap_info hns3_dbg_cap[] = { @@ -941,6 +948,69 @@ static int hns3_dbg_dev_info(struct hnae3_handle *h, char *buf, int len) return 0; } +static const struct hns3_dbg_item page_pool_info_items[] = { + { "QUEUE_ID", 2 }, + { "ALLOCATE_CNT", 2 }, + { "FREE_CNT", 6 }, + { "POOL_SIZE(PAGE_NUM)", 2 }, + { "ORDER", 2 }, + { "NUMA_ID", 2 }, + { "MAX_LEN", 2 }, +}; + +static void hns3_dump_page_pool_info(struct hns3_enet_ring *ring, + char **result, u32 index) +{ + u32 j = 0; + + sprintf(result[j++], "%u", index); + sprintf(result[j++], "%u", ring->page_pool->pages_state_hold_cnt); + sprintf(result[j++], "%u", + atomic_read(&ring->page_pool->pages_state_release_cnt)); + sprintf(result[j++], "%u", ring->page_pool->p.pool_size); + sprintf(result[j++], "%u", ring->page_pool->p.order); + sprintf(result[j++], "%d", ring->page_pool->p.nid); + sprintf(result[j++], "%uK", ring->page_pool->p.max_len / 1024); +} + +static int +hns3_dbg_page_pool_info(struct hnae3_handle *h, char *buf, int len) +{ + char data_str[ARRAY_SIZE(page_pool_info_items)][HNS3_DBG_DATA_STR_LEN]; + char *result[ARRAY_SIZE(page_pool_info_items)]; + struct hns3_nic_priv *priv = h->priv; + char content[HNS3_DBG_INFO_LEN]; + struct hns3_enet_ring *ring; + int pos = 0; + u32 i; + + if (!priv->ring) { + dev_err(&h->pdev->dev, "priv->ring is NULL\n"); + return -EFAULT; + } + + for (i = 0; i < ARRAY_SIZE(page_pool_info_items); i++) + result[i] = &data_str[i][0]; + + hns3_dbg_fill_content(content, sizeof(content), page_pool_info_items, + NULL, ARRAY_SIZE(page_pool_info_items)); + pos += scnprintf(buf + pos, len - pos, "%s", content); + for (i = 0; i < h->kinfo.num_tqps; i++) { + if (!test_bit(HNS3_NIC_STATE_INITED, &priv->state) || + test_bit(HNS3_NIC_STATE_RESETTING, &priv->state)) + return -EPERM; + ring = &priv->ring[(u32)(i + h->kinfo.num_tqps)]; + hns3_dump_page_pool_info(ring, result, i); + hns3_dbg_fill_content(content, sizeof(content), + page_pool_info_items, + (const char **)result, + ARRAY_SIZE(page_pool_info_items)); + pos += scnprintf(buf + pos, len - pos, "%s", content); + } + + return 0; +} + static int hns3_dbg_get_cmd_index(struct hns3_dbg_data *dbg_data, u32 *index) { u32 i; @@ -982,6 +1052,10 @@ static const struct hns3_dbg_func hns3_dbg_cmd_func[] = { .cmd = HNAE3_DBG_CMD_TX_QUEUE_INFO, .dbg_dump = hns3_dbg_tx_queue_info, }, + { + .cmd = HNAE3_DBG_CMD_PAGE_POOL_INFO, + .dbg_dump = hns3_dbg_page_pool_info, + }, }; static int hns3_dbg_read_cmd(struct hns3_dbg_data *dbg_data, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_devlink.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_devlink.c index 59b0ae7d59e0..4c441e6a5082 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_devlink.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_devlink.c @@ -119,8 +119,8 @@ int hclge_devlink_init(struct hclge_dev *hdev) priv->hdev = hdev; hdev->devlink = devlink; + devlink_set_features(devlink, DEVLINK_F_RELOAD); devlink_register(devlink); - devlink_reload_enable(devlink); return 0; } @@ -128,8 +128,6 @@ void hclge_devlink_uninit(struct hclge_dev *hdev) { struct devlink *devlink = hdev->devlink; - devlink_reload_disable(devlink); - devlink_unregister(devlink); devlink_free(devlink); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 26e766242dee..77ab3b269ff9 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -9419,7 +9419,7 @@ int hclge_update_mac_node_for_dev_addr(struct hclge_vport *vport, return 0; } -static int hclge_set_mac_addr(struct hnae3_handle *handle, void *p, +static int hclge_set_mac_addr(struct hnae3_handle *handle, const void *p, bool is_first) { const unsigned char *new_addr = (const unsigned char *)p; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_devlink.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_devlink.c index d60cc9426f70..fdc19868b818 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_devlink.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_devlink.c @@ -121,8 +121,8 @@ int hclgevf_devlink_init(struct hclgevf_dev *hdev) priv->hdev = hdev; hdev->devlink = devlink; + devlink_set_features(devlink, DEVLINK_F_RELOAD); devlink_register(devlink); - devlink_reload_enable(devlink); return 0; } @@ -130,8 +130,6 @@ void hclgevf_devlink_uninit(struct hclgevf_dev *hdev) { struct devlink *devlink = hdev->devlink; - devlink_reload_disable(devlink); - devlink_unregister(devlink); devlink_free(devlink); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index cf00ad7bb881..645b2c0011e6 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -1349,7 +1349,7 @@ static void hclgevf_get_mac_addr(struct hnae3_handle *handle, u8 *p) ether_addr_copy(p, hdev->hw.mac.mac_addr); } -static int hclgevf_set_mac_addr(struct hnae3_handle *handle, void *p, +static int hclgevf_set_mac_addr(struct hnae3_handle *handle, const void *p, bool is_first) { struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle); diff --git a/drivers/net/ethernet/huawei/hinic/hinic_main.c b/drivers/net/ethernet/huawei/hinic/hinic_main.c index 6414e922cf8c..f9a766b8ac43 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_main.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c @@ -1181,6 +1181,7 @@ static int nic_dev_init(struct pci_dev *pdev) struct net_device *netdev; struct hinic_hwdev *hwdev; struct devlink *devlink; + u8 addr[ETH_ALEN]; int err, num_qps; devlink = hinic_devlink_alloc(&pdev->dev); @@ -1259,11 +1260,12 @@ static int nic_dev_init(struct pci_dev *pdev) pci_set_drvdata(pdev, netdev); - err = hinic_port_get_mac(nic_dev, netdev->dev_addr); + err = hinic_port_get_mac(nic_dev, addr); if (err) { dev_err(&pdev->dev, "Failed to get mac address\n"); goto err_get_mac; } + eth_hw_addr_set(netdev, addr); if (!is_valid_ether_addr(netdev->dev_addr)) { if (!HINIC_IS_VF(nic_dev->hwdev->hwif)) { diff --git a/drivers/net/ethernet/i825xx/sun3_82586.c b/drivers/net/ethernet/i825xx/sun3_82586.c index 0696f723228a..3909c6a0af89 100644 --- a/drivers/net/ethernet/i825xx/sun3_82586.c +++ b/drivers/net/ethernet/i825xx/sun3_82586.c @@ -339,14 +339,13 @@ static const struct net_device_ops sun3_82586_netdev_ops = { static int __init sun3_82586_probe1(struct net_device *dev,int ioaddr) { - int i, size, retval; + int size, retval; if (!request_region(ioaddr, SUN3_82586_TOTAL_SIZE, DRV_NAME)) return -EBUSY; /* copy in the ethernet address from the prom */ - for(i = 0; i < 6 ; i++) - dev->dev_addr[i] = idprom->id_ethaddr[i]; + eth_hw_addr_set(dev, idprom->id_ethaddr); printk("%s: SUN3 Intel 82586 found at %lx, ",dev->name,dev->base_addr); @@ -461,7 +460,7 @@ static int init586(struct net_device *dev) ias_cmd->cmd_cmd = swab16(CMD_IASETUP | CMD_LAST); ias_cmd->cmd_link = 0xffff; - memcpy((char *)&ias_cmd->iaddr,(char *) dev->dev_addr,ETH_ALEN); + memcpy((char *)&ias_cmd->iaddr,(const char *) dev->dev_addr,ETH_ALEN); p->scb->cbl_offset = make16(ias_cmd); diff --git a/drivers/net/ethernet/ibm/emac/core.c b/drivers/net/ethernet/ibm/emac/core.c index 8db0ec38bbee..6b3fc8823c54 100644 --- a/drivers/net/ethernet/ibm/emac/core.c +++ b/drivers/net/ethernet/ibm/emac/core.c @@ -2975,7 +2975,7 @@ static int emac_init_config(struct emac_instance *dev) } /* Read MAC-address */ - err = of_get_mac_address(np, dev->ndev->dev_addr); + err = of_get_ethdev_address(np, dev->ndev); if (err) { if (err != -EPROBE_DEFER) dev_err(&dev->ofdev->dev, "Can't get valid [local-]mac-address from OF !\n"); diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c index 836617fb3f40..45ba40cf4d07 100644 --- a/drivers/net/ethernet/ibm/ibmveth.c +++ b/drivers/net/ethernet/ibm/ibmveth.c @@ -483,17 +483,6 @@ retry: return rc; } -static u64 ibmveth_encode_mac_addr(u8 *mac) -{ - int i; - u64 encoded = 0; - - for (i = 0; i < ETH_ALEN; i++) - encoded = (encoded << 8) | mac[i]; - - return encoded; -} - static int ibmveth_open(struct net_device *netdev) { struct ibmveth_adapter *adapter = netdev_priv(netdev); @@ -553,7 +542,7 @@ static int ibmveth_open(struct net_device *netdev) adapter->rx_queue.num_slots = rxq_entries; adapter->rx_queue.toggle = 1; - mac_address = ibmveth_encode_mac_addr(netdev->dev_addr); + mac_address = ether_addr_to_u64(netdev->dev_addr); rxq_desc.fields.flags_len = IBMVETH_BUF_VALID | adapter->rx_queue.queue_len; @@ -1476,7 +1465,7 @@ static void ibmveth_set_multicast_list(struct net_device *netdev) netdev_for_each_mc_addr(ha, netdev) { /* add the multicast address to the filter table */ u64 mcast_addr; - mcast_addr = ibmveth_encode_mac_addr(ha->addr); + mcast_addr = ether_addr_to_u64(ha->addr); lpar_rc = h_multicast_ctrl(adapter->vdev->unit_address, IbmVethMcastAddFilter, mcast_addr); @@ -1606,7 +1595,7 @@ static int ibmveth_set_mac_addr(struct net_device *dev, void *p) if (!is_valid_ether_addr(addr->sa_data)) return -EADDRNOTAVAIL; - mac_address = ibmveth_encode_mac_addr(addr->sa_data); + mac_address = ether_addr_to_u64(addr->sa_data); rc = h_change_logical_lan_mac(adapter->vdev->unit_address, mac_address); if (rc) { netdev_err(adapter->netdev, "h_change_logical_lan_mac failed with rc=%d\n", rc); diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 66bdeb74f0af..44e2dc8328a2 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -2550,7 +2550,6 @@ static void e1000_set_itr(struct e1000_adapter *adapter) /* for non-gigabit speeds, just fix the interrupt rate at 4000 */ if (adapter->link_speed != SPEED_1000) { - current_itr = 0; new_itr = 4000; goto set_itr_now; } diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index 39fb3d57c057..3d528fba754b 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -435,7 +435,7 @@ static inline bool i40e_is_channel_macvlan(struct i40e_channel *ch) return !!ch->fwd; } -static inline u8 *i40e_channel_mac(struct i40e_channel *ch) +static inline const u8 *i40e_channel_mac(struct i40e_channel *ch) { if (i40e_is_channel_macvlan(ch)) return ch->fwd->netdev->dev_addr; diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h index 68c80f04113c..e0b88ff76466 100644 --- a/drivers/net/ethernet/intel/iavf/iavf.h +++ b/drivers/net/ethernet/intel/iavf/iavf.h @@ -177,6 +177,7 @@ enum iavf_state_t { __IAVF_INIT_VERSION_CHECK, /* aq msg sent, awaiting reply */ __IAVF_INIT_GET_RESOURCES, /* aq msg sent, awaiting reply */ __IAVF_INIT_SW, /* got resources, setting up structs */ + __IAVF_INIT_FAILED, /* init failed, restarting procedure */ __IAVF_RESETTING, /* in reset */ __IAVF_COMM_FAILED, /* communication with PF failed */ /* Below here, watchdog is running */ @@ -225,7 +226,6 @@ struct iavf_adapter { struct work_struct reset_task; struct work_struct adminq_task; struct delayed_work client_task; - struct delayed_work init_task; wait_queue_head_t down_waitqueue; struct iavf_q_vector *q_vectors; struct list_head vlan_filter_list; @@ -312,6 +312,7 @@ struct iavf_adapter { struct iavf_hw hw; /* defined in iavf_type.h */ enum iavf_state_t state; + enum iavf_state_t last_state; unsigned long crit_section; struct delayed_work watchdog_task; @@ -393,6 +394,15 @@ struct iavf_device { extern char iavf_driver_name[]; extern struct workqueue_struct *iavf_wq; +static inline void iavf_change_state(struct iavf_adapter *adapter, + enum iavf_state_t state) +{ + if (adapter->state != state) { + adapter->last_state = adapter->state; + adapter->state = state; + } +} + int iavf_up(struct iavf_adapter *adapter); void iavf_down(struct iavf_adapter *adapter); int iavf_process_config(struct iavf_adapter *adapter); diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index ca4712a73574..56956e449c97 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -14,7 +14,7 @@ static int iavf_setup_all_tx_resources(struct iavf_adapter *adapter); static int iavf_setup_all_rx_resources(struct iavf_adapter *adapter); static int iavf_close(struct net_device *netdev); -static int iavf_init_get_resources(struct iavf_adapter *adapter); +static void iavf_init_get_resources(struct iavf_adapter *adapter); static int iavf_check_reset_complete(struct iavf_hw *hw); char iavf_driver_name[] = "iavf"; @@ -960,7 +960,7 @@ static void iavf_configure(struct iavf_adapter *adapter) **/ static void iavf_up_complete(struct iavf_adapter *adapter) { - adapter->state = __IAVF_RUNNING; + iavf_change_state(adapter, __IAVF_RUNNING); clear_bit(__IAVF_VSI_DOWN, adapter->vsi.state); iavf_napi_enable_all(adapter); @@ -1688,9 +1688,9 @@ static int iavf_process_aq_command(struct iavf_adapter *adapter) * * Function process __IAVF_STARTUP driver state. * When success the state is changed to __IAVF_INIT_VERSION_CHECK - * when fails it returns -EAGAIN + * when fails the state is changed to __IAVF_INIT_FAILED **/ -static int iavf_startup(struct iavf_adapter *adapter) +static void iavf_startup(struct iavf_adapter *adapter) { struct pci_dev *pdev = adapter->pdev; struct iavf_hw *hw = &adapter->hw; @@ -1729,9 +1729,10 @@ static int iavf_startup(struct iavf_adapter *adapter) iavf_shutdown_adminq(hw); goto err; } - adapter->state = __IAVF_INIT_VERSION_CHECK; + iavf_change_state(adapter, __IAVF_INIT_VERSION_CHECK); + return; err: - return err; + iavf_change_state(adapter, __IAVF_INIT_FAILED); } /** @@ -1740,9 +1741,9 @@ err: * * Function process __IAVF_INIT_VERSION_CHECK driver state. * When success the state is changed to __IAVF_INIT_GET_RESOURCES - * when fails it returns -EAGAIN + * when fails the state is changed to __IAVF_INIT_FAILED **/ -static int iavf_init_version_check(struct iavf_adapter *adapter) +static void iavf_init_version_check(struct iavf_adapter *adapter) { struct pci_dev *pdev = adapter->pdev; struct iavf_hw *hw = &adapter->hw; @@ -1753,7 +1754,7 @@ static int iavf_init_version_check(struct iavf_adapter *adapter) if (!iavf_asq_done(hw)) { dev_err(&pdev->dev, "Admin queue command never completed\n"); iavf_shutdown_adminq(hw); - adapter->state = __IAVF_STARTUP; + iavf_change_state(adapter, __IAVF_STARTUP); goto err; } @@ -1776,10 +1777,10 @@ static int iavf_init_version_check(struct iavf_adapter *adapter) err); goto err; } - adapter->state = __IAVF_INIT_GET_RESOURCES; - + iavf_change_state(adapter, __IAVF_INIT_GET_RESOURCES); + return; err: - return err; + iavf_change_state(adapter, __IAVF_INIT_FAILED); } /** @@ -1789,9 +1790,9 @@ err: * Function process __IAVF_INIT_GET_RESOURCES driver state and * finishes driver initialization procedure. * When success the state is changed to __IAVF_DOWN - * when fails it returns -EAGAIN + * when fails the state is changed to __IAVF_INIT_FAILED **/ -static int iavf_init_get_resources(struct iavf_adapter *adapter) +static void iavf_init_get_resources(struct iavf_adapter *adapter) { struct net_device *netdev = adapter->netdev; struct pci_dev *pdev = adapter->pdev; @@ -1819,7 +1820,7 @@ static int iavf_init_get_resources(struct iavf_adapter *adapter) */ iavf_shutdown_adminq(hw); dev_err(&pdev->dev, "Unable to get VF config due to PF error condition, not retrying\n"); - return 0; + return; } if (err) { dev_err(&pdev->dev, "Unable to get VF config (%d)\n", err); @@ -1893,7 +1894,7 @@ static int iavf_init_get_resources(struct iavf_adapter *adapter) if (netdev->features & NETIF_F_GRO) dev_info(&pdev->dev, "GRO is enabled\n"); - adapter->state = __IAVF_DOWN; + iavf_change_state(adapter, __IAVF_DOWN); set_bit(__IAVF_VSI_DOWN, adapter->vsi.state); rtnl_unlock(); @@ -1911,7 +1912,7 @@ static int iavf_init_get_resources(struct iavf_adapter *adapter) else iavf_init_rss(adapter); - return err; + return; err_mem: iavf_free_rss(adapter); err_register: @@ -1922,7 +1923,7 @@ err_alloc: kfree(adapter->vf_res); adapter->vf_res = NULL; err: - return err; + iavf_change_state(adapter, __IAVF_INIT_FAILED); } /** @@ -1941,9 +1942,50 @@ static void iavf_watchdog_task(struct work_struct *work) goto restart_watchdog; if (adapter->flags & IAVF_FLAG_PF_COMMS_FAILED) - adapter->state = __IAVF_COMM_FAILED; + iavf_change_state(adapter, __IAVF_COMM_FAILED); + + if (adapter->flags & IAVF_FLAG_RESET_NEEDED && + adapter->state != __IAVF_RESETTING) { + iavf_change_state(adapter, __IAVF_RESETTING); + adapter->aq_required = 0; + adapter->current_op = VIRTCHNL_OP_UNKNOWN; + } switch (adapter->state) { + case __IAVF_STARTUP: + iavf_startup(adapter); + mutex_unlock(&adapter->crit_lock); + queue_delayed_work(iavf_wq, &adapter->watchdog_task, + msecs_to_jiffies(30)); + return; + case __IAVF_INIT_VERSION_CHECK: + iavf_init_version_check(adapter); + mutex_unlock(&adapter->crit_lock); + queue_delayed_work(iavf_wq, &adapter->watchdog_task, + msecs_to_jiffies(30)); + return; + case __IAVF_INIT_GET_RESOURCES: + iavf_init_get_resources(adapter); + mutex_unlock(&adapter->crit_lock); + queue_delayed_work(iavf_wq, &adapter->watchdog_task, + msecs_to_jiffies(1)); + return; + case __IAVF_INIT_FAILED: + if (++adapter->aq_wait_count > IAVF_AQ_MAX_ERR) { + dev_err(&adapter->pdev->dev, + "Failed to communicate with PF; waiting before retry\n"); + adapter->flags |= IAVF_FLAG_PF_COMMS_FAILED; + iavf_shutdown_adminq(hw); + mutex_unlock(&adapter->crit_lock); + queue_delayed_work(iavf_wq, + &adapter->watchdog_task, (5 * HZ)); + return; + } + /* Try again from failed step*/ + iavf_change_state(adapter, adapter->last_state); + mutex_unlock(&adapter->crit_lock); + queue_delayed_work(iavf_wq, &adapter->watchdog_task, HZ); + return; case __IAVF_COMM_FAILED: reg_val = rd32(hw, IAVF_VFGEN_RSTAT) & IAVF_VFGEN_RSTAT_VFR_STATE_MASK; @@ -1952,23 +1994,19 @@ static void iavf_watchdog_task(struct work_struct *work) /* A chance for redemption! */ dev_err(&adapter->pdev->dev, "Hardware came out of reset. Attempting reinit.\n"); - adapter->state = __IAVF_STARTUP; - adapter->flags &= ~IAVF_FLAG_PF_COMMS_FAILED; - queue_delayed_work(iavf_wq, &adapter->init_task, 10); - mutex_unlock(&adapter->crit_lock); - /* Don't reschedule the watchdog, since we've restarted - * the init task. When init_task contacts the PF and + /* When init task contacts the PF and * gets everything set up again, it'll restart the * watchdog for us. Down, boy. Sit. Stay. Woof. */ - return; + iavf_change_state(adapter, __IAVF_STARTUP); + adapter->flags &= ~IAVF_FLAG_PF_COMMS_FAILED; } adapter->aq_required = 0; adapter->current_op = VIRTCHNL_OP_UNKNOWN; queue_delayed_work(iavf_wq, &adapter->watchdog_task, msecs_to_jiffies(10)); - goto watchdog_done; + return; case __IAVF_RESETTING: mutex_unlock(&adapter->crit_lock); queue_delayed_work(iavf_wq, &adapter->watchdog_task, HZ * 2); @@ -1991,38 +2029,40 @@ static void iavf_watchdog_task(struct work_struct *work) adapter->state == __IAVF_RUNNING) iavf_request_stats(adapter); } + if (adapter->state == __IAVF_RUNNING) + iavf_detect_recover_hung(&adapter->vsi); break; case __IAVF_REMOVE: mutex_unlock(&adapter->crit_lock); return; default: - goto restart_watchdog; + return; } - /* check for hw reset */ + /* check for hw reset */ reg_val = rd32(hw, IAVF_VF_ARQLEN1) & IAVF_VF_ARQLEN1_ARQENABLE_MASK; if (!reg_val) { + iavf_change_state(adapter, __IAVF_RESETTING); adapter->flags |= IAVF_FLAG_RESET_PENDING; adapter->aq_required = 0; adapter->current_op = VIRTCHNL_OP_UNKNOWN; dev_err(&adapter->pdev->dev, "Hardware reset detected\n"); queue_work(iavf_wq, &adapter->reset_task); - goto watchdog_done; + mutex_unlock(&adapter->crit_lock); + queue_delayed_work(iavf_wq, + &adapter->watchdog_task, HZ * 2); + return; } schedule_delayed_work(&adapter->client_task, msecs_to_jiffies(5)); -watchdog_done: - if (adapter->state == __IAVF_RUNNING || - adapter->state == __IAVF_COMM_FAILED) - iavf_detect_recover_hung(&adapter->vsi); mutex_unlock(&adapter->crit_lock); restart_watchdog: + queue_work(iavf_wq, &adapter->adminq_task); if (adapter->aq_required) queue_delayed_work(iavf_wq, &adapter->watchdog_task, msecs_to_jiffies(20)); else queue_delayed_work(iavf_wq, &adapter->watchdog_task, HZ * 2); - queue_work(iavf_wq, &adapter->adminq_task); } static void iavf_disable_vf(struct iavf_adapter *adapter) @@ -2081,7 +2121,7 @@ static void iavf_disable_vf(struct iavf_adapter *adapter) adapter->netdev->flags &= ~IFF_UP; mutex_unlock(&adapter->crit_lock); adapter->flags &= ~IAVF_FLAG_RESET_PENDING; - adapter->state = __IAVF_DOWN; + iavf_change_state(adapter, __IAVF_DOWN); wake_up(&adapter->down_waitqueue); dev_info(&adapter->pdev->dev, "Reset task did not complete, VF disabled\n"); } @@ -2191,7 +2231,7 @@ continue_reset: } iavf_irq_disable(adapter); - adapter->state = __IAVF_RESETTING; + iavf_change_state(adapter, __IAVF_RESETTING); adapter->flags &= ~IAVF_FLAG_RESET_PENDING; /* free the Tx/Rx rings and descriptors, might be better to just @@ -2291,11 +2331,14 @@ continue_reset: iavf_configure(adapter); + /* iavf_up_complete() will switch device back + * to __IAVF_RUNNING + */ iavf_up_complete(adapter); iavf_irq_enable(adapter, true); } else { - adapter->state = __IAVF_DOWN; + iavf_change_state(adapter, __IAVF_DOWN); wake_up(&adapter->down_waitqueue); } mutex_unlock(&adapter->client_lock); @@ -2305,6 +2348,8 @@ continue_reset: reset_err: mutex_unlock(&adapter->client_lock); mutex_unlock(&adapter->crit_lock); + if (running) + iavf_change_state(adapter, __IAVF_RUNNING); dev_err(&adapter->pdev->dev, "failed to allocate resources during reinit\n"); iavf_close(netdev); } @@ -3297,7 +3342,7 @@ static int iavf_close(struct net_device *netdev) adapter->flags |= IAVF_FLAG_CLIENT_NEEDS_CLOSE; iavf_down(adapter); - adapter->state = __IAVF_DOWN_PENDING; + iavf_change_state(adapter, __IAVF_DOWN_PENDING); iavf_free_traffic_irqs(adapter); mutex_unlock(&adapter->crit_lock); @@ -3630,64 +3675,6 @@ int iavf_process_config(struct iavf_adapter *adapter) return 0; } -/** - * iavf_init_task - worker thread to perform delayed initialization - * @work: pointer to work_struct containing our data - * - * This task completes the work that was begun in probe. Due to the nature - * of VF-PF communications, we may need to wait tens of milliseconds to get - * responses back from the PF. Rather than busy-wait in probe and bog down the - * whole system, we'll do it in a task so we can sleep. - * This task only runs during driver init. Once we've established - * communications with the PF driver and set up our netdev, the watchdog - * takes over. - **/ -static void iavf_init_task(struct work_struct *work) -{ - struct iavf_adapter *adapter = container_of(work, - struct iavf_adapter, - init_task.work); - struct iavf_hw *hw = &adapter->hw; - - if (iavf_lock_timeout(&adapter->crit_lock, 5000)) { - dev_warn(&adapter->pdev->dev, "failed to acquire crit_lock in %s\n", __FUNCTION__); - return; - } - switch (adapter->state) { - case __IAVF_STARTUP: - if (iavf_startup(adapter) < 0) - goto init_failed; - break; - case __IAVF_INIT_VERSION_CHECK: - if (iavf_init_version_check(adapter) < 0) - goto init_failed; - break; - case __IAVF_INIT_GET_RESOURCES: - if (iavf_init_get_resources(adapter) < 0) - goto init_failed; - goto out; - default: - goto init_failed; - } - - queue_delayed_work(iavf_wq, &adapter->init_task, - msecs_to_jiffies(30)); - goto out; -init_failed: - if (++adapter->aq_wait_count > IAVF_AQ_MAX_ERR) { - dev_err(&adapter->pdev->dev, - "Failed to communicate with PF; waiting before retry\n"); - adapter->flags |= IAVF_FLAG_PF_COMMS_FAILED; - iavf_shutdown_adminq(hw); - adapter->state = __IAVF_STARTUP; - queue_delayed_work(iavf_wq, &adapter->init_task, HZ * 5); - goto out; - } - queue_delayed_work(iavf_wq, &adapter->init_task, HZ); -out: - mutex_unlock(&adapter->crit_lock); -} - /** * iavf_shutdown - Shutdown the device in preparation for a reboot * @pdev: pci device structure @@ -3705,7 +3692,7 @@ static void iavf_shutdown(struct pci_dev *pdev) if (iavf_lock_timeout(&adapter->crit_lock, 5000)) dev_warn(&adapter->pdev->dev, "failed to acquire crit_lock in %s\n", __FUNCTION__); /* Prevent the watchdog from running. */ - adapter->state = __IAVF_REMOVE; + iavf_change_state(adapter, __IAVF_REMOVE); adapter->aq_required = 0; mutex_unlock(&adapter->crit_lock); @@ -3778,7 +3765,7 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) hw->back = adapter; adapter->msg_enable = BIT(DEFAULT_DEBUG_LEVEL_SHIFT) - 1; - adapter->state = __IAVF_STARTUP; + iavf_change_state(adapter, __IAVF_STARTUP); /* Call save state here because it relies on the adapter struct. */ pci_save_state(pdev); @@ -3822,8 +3809,7 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) INIT_WORK(&adapter->adminq_task, iavf_adminq_task); INIT_DELAYED_WORK(&adapter->watchdog_task, iavf_watchdog_task); INIT_DELAYED_WORK(&adapter->client_task, iavf_client_task); - INIT_DELAYED_WORK(&adapter->init_task, iavf_init_task); - queue_delayed_work(iavf_wq, &adapter->init_task, + queue_delayed_work(iavf_wq, &adapter->watchdog_task, msecs_to_jiffies(5 * (pdev->devfn & 0x07))); /* Setup the wait queue for indicating transition to down status */ @@ -3929,8 +3915,8 @@ static void iavf_remove(struct pci_dev *pdev) int err; /* Indicate we are in remove and not to run reset_task */ mutex_lock(&adapter->remove_lock); - cancel_delayed_work_sync(&adapter->init_task); cancel_work_sync(&adapter->reset_task); + cancel_delayed_work_sync(&adapter->watchdog_task); cancel_delayed_work_sync(&adapter->client_task); if (adapter->netdev_registered) { unregister_netdev(netdev); @@ -3954,7 +3940,7 @@ static void iavf_remove(struct pci_dev *pdev) dev_warn(&adapter->pdev->dev, "failed to acquire crit_lock in %s\n", __FUNCTION__); /* Shut down all the garbage mashers on the detention level */ - adapter->state = __IAVF_REMOVE; + iavf_change_state(adapter, __IAVF_REMOVE); adapter->aq_required = 0; adapter->flags &= ~IAVF_FLAG_REINIT_ITR_NEEDED; iavf_free_all_tx_resources(adapter); diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c index 8eb8d4663a81..8c3f0f77cb57 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c +++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c @@ -1735,7 +1735,7 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, iavf_free_all_tx_resources(adapter); iavf_free_all_rx_resources(adapter); if (adapter->state == __IAVF_DOWN_PENDING) { - adapter->state = __IAVF_DOWN; + iavf_change_state(adapter, __IAVF_DOWN); wake_up(&adapter->down_waitqueue); } break; diff --git a/drivers/net/ethernet/intel/ice/Makefile b/drivers/net/ethernet/intel/ice/Makefile index 1866be50095d..c36faa7d1471 100644 --- a/drivers/net/ethernet/intel/ice/Makefile +++ b/drivers/net/ethernet/intel/ice/Makefile @@ -27,7 +27,8 @@ ice-y := ice_main.o \ ice_fw_update.o \ ice_lag.o \ ice_ethtool.o \ - ice_repr.o + ice_repr.o \ + ice_tc_lib.o ice-$(CONFIG_PCI_IOV) += ice_virtchnl_allowlist.o ice-$(CONFIG_PCI_IOV) += ice_virtchnl_pf.o ice_sriov.o ice_virtchnl_fdir.o ice-$(CONFIG_PTP_1588_CLOCK) += ice_ptp.o ice_ptp_hw.o diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index 0d44a3767bad..967a90efcb11 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -38,6 +38,10 @@ #include #include #include +#include +#include +#include +#include #include #include #include @@ -55,6 +59,7 @@ #include "ice_dcb.h" #include "ice_switch.h" #include "ice_common.h" +#include "ice_flow.h" #include "ice_sched.h" #include "ice_idc_int.h" #include "ice_virtchnl_pf.h" @@ -64,6 +69,7 @@ #include "ice_xsk.h" #include "ice_arfs.h" #include "ice_repr.h" +#include "ice_eswitch.h" #include "ice_lag.h" #define ICE_BAR0 0 @@ -103,6 +109,10 @@ #define ICE_INVAL_VFID 256 #define ICE_MAX_RXQS_PER_TC 256 /* Used when setting VSI context per TC Rx queues */ + +#define ICE_CHNL_START_TC 1 +#define ICE_CHNL_MAX_TC 16 + #define ICE_MAX_RESET_WAIT 20 #define ICE_VSIQF_HKEY_ARRAY_SIZE ((VSIQF_HKEY_MAX_INDEX + 1) * 4) @@ -120,14 +130,24 @@ #define ICE_TX_CTX_DESC(R, i) (&(((struct ice_tx_ctx_desc *)((R)->desc))[i])) #define ICE_TX_FDIRDESC(R, i) (&(((struct ice_fltr_desc *)((R)->desc))[i])) +/* Minimum BW limit is 500 Kbps for any scheduler node */ +#define ICE_MIN_BW_LIMIT 500 +/* User can specify BW in either Kbit/Mbit/Gbit and OS converts it in bytes. + * use it to convert user specified BW limit into Kbps + */ +#define ICE_BW_KBPS_DIVISOR 125 + /* Macro for each VSI in a PF */ #define ice_for_each_vsi(pf, i) \ for ((i) = 0; (i) < (pf)->num_alloc_vsi; (i)++) -/* Macros for each Tx/Rx ring in a VSI */ +/* Macros for each Tx/Xdp/Rx ring in a VSI */ #define ice_for_each_txq(vsi, i) \ for ((i) = 0; (i) < (vsi)->num_txq; (i)++) +#define ice_for_each_xdp_txq(vsi, i) \ + for ((i) = 0; (i) < (vsi)->num_xdp_txq; (i)++) + #define ice_for_each_rxq(vsi, i) \ for ((i) = 0; (i) < (vsi)->num_rxq; (i)++) @@ -141,6 +161,9 @@ #define ice_for_each_q_vector(vsi, i) \ for ((i) = 0; (i) < (vsi)->num_q_vectors; (i)++) +#define ice_for_each_chnl_tc(i) \ + for ((i) = ICE_CHNL_START_TC; (i) < ICE_CHNL_MAX_TC; (i)++) + #define ICE_UCAST_PROMISC_BITS (ICE_PROMISC_UCAST_TX | ICE_PROMISC_MCAST_TX | \ ICE_PROMISC_UCAST_RX | ICE_PROMISC_MCAST_RX) @@ -162,9 +185,27 @@ enum ice_feature { ICE_F_DSCP, + ICE_F_SMA_CTRL, ICE_F_MAX }; +DECLARE_STATIC_KEY_FALSE(ice_xdp_locking_key); + +struct ice_channel { + struct list_head list; + u8 type; + u16 sw_id; + u16 base_q; + u16 num_rxq; + u16 num_txq; + u16 vsi_num; + u8 ena_tc; + struct ice_aqc_vsi_props info; + u64 max_tx_rate; + u64 min_tx_rate; + struct ice_vsi *ch_vsi; +}; + struct ice_txq_meta { u32 q_teid; /* Tx-scheduler element identifier */ u16 q_id; /* Entry in VSI's txq_map bitmap */ @@ -182,7 +223,7 @@ struct ice_tc_info { struct ice_tc_cfg { u8 numtc; /* Total number of enabled TCs */ - u8 ena_tc; /* Tx map */ + u16 ena_tc; /* Tx map */ struct ice_tc_info tc_info[ICE_MAX_TRAFFIC_CLASS]; }; @@ -273,8 +314,8 @@ struct ice_vsi { struct ice_sw *vsw; /* switch this VSI is on */ struct ice_pf *back; /* back pointer to PF */ struct ice_port_info *port_info; /* back pointer to port_info */ - struct ice_ring **rx_rings; /* Rx ring array */ - struct ice_ring **tx_rings; /* Tx ring array */ + struct ice_rx_ring **rx_rings; /* Rx ring array */ + struct ice_tx_ring **tx_rings; /* Tx ring array */ struct ice_q_vector **q_vectors; /* q_vector array */ irqreturn_t (*irq_handler)(int irq, void *data); @@ -347,13 +388,42 @@ struct ice_vsi { u16 qset_handle[ICE_MAX_TRAFFIC_CLASS]; struct ice_tc_cfg tc_cfg; struct bpf_prog *xdp_prog; - struct ice_ring **xdp_rings; /* XDP ring array */ + struct ice_tx_ring **xdp_rings; /* XDP ring array */ unsigned long *af_xdp_zc_qps; /* tracks AF_XDP ZC enabled qps */ u16 num_xdp_txq; /* Used XDP queues */ u8 xdp_mapping_mode; /* ICE_MAP_MODE_[CONTIG|SCATTER] */ struct net_device **target_netdevs; + struct tc_mqprio_qopt_offload mqprio_qopt; /* queue parameters */ + + /* Channel Specific Fields */ + struct ice_vsi *tc_map_vsi[ICE_CHNL_MAX_TC]; + u16 cnt_q_avail; + u16 next_base_q; /* next queue to be used for channel setup */ + struct list_head ch_list; + u16 num_chnl_rxq; + u16 num_chnl_txq; + u16 ch_rss_size; + u16 num_chnl_fltr; + /* store away rss size info before configuring ADQ channels so that, + * it can be used after tc-qdisc delete, to get back RSS setting as + * they were before + */ + u16 orig_rss_size; + /* this keeps tracks of all enabled TC with and without DCB + * and inclusive of ADQ, vsi->mqprio_opt keeps track of queue + * information + */ + u8 all_numtc; + u16 all_enatc; + + /* store away TC info, to be used for rebuild logic */ + u8 old_numtc; + u16 old_ena_tc; + + struct ice_channel *ch; + /* setup back reference, to which aggregator node this VSI * corresponds to */ @@ -382,6 +452,8 @@ struct ice_q_vector { cpumask_t affinity_mask; struct irq_affinity_notify affinity_notify; + struct ice_channel *ch; + char name[ICE_INT_NAME_STR_LEN]; u16 total_events; /* net_dim(): number of interrupts processed */ @@ -400,6 +472,8 @@ enum ice_pf_flags { ICE_FLAG_PTP, /* PTP is enabled by software */ ICE_FLAG_AUX_ENA, ICE_FLAG_ADV_FEATURES, + ICE_FLAG_TC_MQPRIO, /* support for Multi queue TC */ + ICE_FLAG_CLS_FLOWER, ICE_FLAG_LINK_DOWN_ON_CLOSE_ENA, ICE_FLAG_TOTAL_PORT_SHUTDOWN_ENA, ICE_FLAG_NO_MEDIA, @@ -511,6 +585,11 @@ struct ice_pf { struct auxiliary_device *adev; int aux_idx; u32 sw_int_count; + /* count of tc_flower filters specific to channel (aka where filter + * action is "hw_tc ") + */ + u16 num_dmac_chnl_fltrs; + struct hlist_head tc_flower_fltr_list; __le64 nvm_phy_type_lo; /* NVM PHY type low */ __le64 nvm_phy_type_hi; /* NVM PHY type high */ @@ -533,6 +612,17 @@ struct ice_netdev_priv { struct ice_repr *repr; }; +/** + * ice_vector_ch_enabled + * @qv: pointer to q_vector, can be NULL + * + * This function returns true if vector is channel enabled otherwise false + */ +static inline bool ice_vector_ch_enabled(struct ice_q_vector *qv) +{ + return !!qv->ch; /* Enable it to run with TC */ +} + /** * ice_irq_dynamic_ena - Enable default interrupt generation settings * @hw: pointer to HW struct @@ -575,25 +665,42 @@ static inline bool ice_is_xdp_ena_vsi(struct ice_vsi *vsi) return !!vsi->xdp_prog; } -static inline void ice_set_ring_xdp(struct ice_ring *ring) +static inline void ice_set_ring_xdp(struct ice_tx_ring *ring) { ring->flags |= ICE_TX_FLAGS_RING_XDP; } /** * ice_xsk_pool - get XSK buffer pool bound to a ring - * @ring: ring to use + * @ring: Rx ring to use * * Returns a pointer to xdp_umem structure if there is a buffer pool present, * NULL otherwise. */ -static inline struct xsk_buff_pool *ice_xsk_pool(struct ice_ring *ring) +static inline struct xsk_buff_pool *ice_xsk_pool(struct ice_rx_ring *ring) { struct ice_vsi *vsi = ring->vsi; u16 qid = ring->q_index; - if (ice_ring_is_xdp(ring)) - qid -= vsi->num_xdp_txq; + if (!ice_is_xdp_ena_vsi(vsi) || !test_bit(qid, vsi->af_xdp_zc_qps)) + return NULL; + + return xsk_get_pool_from_qid(vsi->netdev, qid); +} + +/** + * ice_tx_xsk_pool - get XSK buffer pool bound to a ring + * @ring: Tx ring to use + * + * Returns a pointer to xdp_umem structure if there is a buffer pool present, + * NULL otherwise. Tx equivalent of ice_xsk_pool. + */ +static inline struct xsk_buff_pool *ice_tx_xsk_pool(struct ice_tx_ring *ring) +{ + struct ice_vsi *vsi = ring->vsi; + u16 qid; + + qid = ring->q_index - vsi->num_xdp_txq; if (!ice_is_xdp_ena_vsi(vsi) || !test_bit(qid, vsi->af_xdp_zc_qps)) return NULL; @@ -677,6 +784,30 @@ static inline void ice_clear_sriov_cap(struct ice_pf *pf) ((base_idx) * ICE_FD_STAT_CTR_BLOCK_COUNT) #define ICE_FD_SB_STAT_IDX(base_idx) ICE_FD_STAT_PF_IDX(base_idx) +/** + * ice_is_adq_active - any active ADQs + * @pf: pointer to PF + * + * This function returns true if there are any ADQs configured (which is + * determined by looking at VSI type (which should be VSI_PF), numtc, and + * TC_MQPRIO flag) otherwise return false + */ +static inline bool ice_is_adq_active(struct ice_pf *pf) +{ + struct ice_vsi *vsi; + + vsi = ice_get_main_vsi(pf); + if (!vsi) + return false; + + /* is ADQ configured */ + if (vsi->tc_cfg.numtc > ICE_CHNL_START_TC && + test_bit(ICE_FLAG_TC_MQPRIO, pf->flags)) + return true; + + return false; +} + bool netif_is_ice(struct net_device *dev); int ice_vsi_setup_tx_rings(struct ice_vsi *vsi); int ice_vsi_setup_rx_rings(struct ice_vsi *vsi); @@ -694,6 +825,7 @@ int ice_up(struct ice_vsi *vsi); int ice_down(struct ice_vsi *vsi); int ice_vsi_cfg(struct ice_vsi *vsi); struct ice_vsi *ice_lb_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi); +int ice_vsi_determine_xdp_res(struct ice_vsi *vsi); int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog); int ice_destroy_xdp_rings(struct ice_vsi *vsi); int diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h index d407cf8c829d..a5425f0dce3f 100644 --- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h +++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h @@ -233,6 +233,7 @@ struct ice_aqc_get_sw_cfg_resp_elem { */ #define ICE_AQC_RES_TYPE_VSI_LIST_REP 0x03 #define ICE_AQC_RES_TYPE_VSI_LIST_PRUNE 0x04 +#define ICE_AQC_RES_TYPE_RECIPE 0x05 #define ICE_AQC_RES_TYPE_FDIR_COUNTER_BLOCK 0x21 #define ICE_AQC_RES_TYPE_FDIR_GUARANTEED_ENTRIES 0x22 #define ICE_AQC_RES_TYPE_FDIR_SHARED_ENTRIES 0x23 @@ -241,6 +242,7 @@ struct ice_aqc_get_sw_cfg_resp_elem { #define ICE_AQC_RES_TYPE_HASH_PROF_BLDR_PROFID 0x60 #define ICE_AQC_RES_TYPE_HASH_PROF_BLDR_TCAM 0x61 +#define ICE_AQC_RES_TYPE_FLAG_SHARED BIT(7) #define ICE_AQC_RES_TYPE_FLAG_SCAN_BOTTOM BIT(12) #define ICE_AQC_RES_TYPE_FLAG_IGNORE_INDEX BIT(13) @@ -474,6 +476,53 @@ struct ice_aqc_vsi_props { #define ICE_MAX_NUM_RECIPES 64 +/* Add/Get Recipe (indirect 0x0290/0x0292) */ +struct ice_aqc_add_get_recipe { + __le16 num_sub_recipes; /* Input in Add cmd, Output in Get cmd */ + __le16 return_index; /* Input, used for Get cmd only */ + u8 reserved[4]; + __le32 addr_high; + __le32 addr_low; +}; + +struct ice_aqc_recipe_content { + u8 rid; +#define ICE_AQ_RECIPE_ID_IS_ROOT BIT(7) +#define ICE_AQ_SW_ID_LKUP_IDX 0 + u8 lkup_indx[5]; +#define ICE_AQ_RECIPE_LKUP_IGNORE BIT(7) +#define ICE_AQ_SW_ID_LKUP_MASK 0x00FF + __le16 mask[5]; + u8 result_indx; +#define ICE_AQ_RECIPE_RESULT_DATA_S 0 +#define ICE_AQ_RECIPE_RESULT_DATA_M (0x3F << ICE_AQ_RECIPE_RESULT_DATA_S) +#define ICE_AQ_RECIPE_RESULT_EN BIT(7) + u8 rsvd0[3]; + u8 act_ctrl_join_priority; + u8 act_ctrl_fwd_priority; + u8 act_ctrl; +#define ICE_AQ_RECIPE_ACT_INV_ACT BIT(2) + u8 rsvd1; + __le32 dflt_act; +}; + +struct ice_aqc_recipe_data_elem { + u8 recipe_indx; + u8 resp_bits; + u8 rsvd0[2]; + u8 recipe_bitmap[8]; + u8 rsvd1[4]; + struct ice_aqc_recipe_content content; + u8 rsvd2[20]; +}; + +/* Set/Get Recipes to Profile Association (direct 0x0291/0x0293) */ +struct ice_aqc_recipe_to_profile { + __le16 profile_id; + u8 rsvd[6]; + DECLARE_BITMAP(recipe_assoc, ICE_MAX_NUM_RECIPES); +}; + /* Add/Update/Remove/Get switch rules (indirect 0x02A0, 0x02A1, 0x02A2, 0x02A3) */ struct ice_aqc_sw_rules { @@ -1230,7 +1279,7 @@ struct ice_aqc_set_mac_lb { u8 reserved[15]; }; -struct ice_aqc_link_topo_addr { +struct ice_aqc_link_topo_params { u8 lport_num; u8 lport_num_valid; #define ICE_AQC_LINK_TOPO_PORT_NUM_VALID BIT(0) @@ -1256,6 +1305,10 @@ struct ice_aqc_link_topo_addr { #define ICE_AQC_LINK_TOPO_NODE_CTX_PROVIDED 4 #define ICE_AQC_LINK_TOPO_NODE_CTX_OVERRIDE 5 u8 index; +}; + +struct ice_aqc_link_topo_addr { + struct ice_aqc_link_topo_params topo_params; __le16 handle; #define ICE_AQC_LINK_TOPO_HANDLE_S 0 #define ICE_AQC_LINK_TOPO_HANDLE_M (0x3FF << ICE_AQC_LINK_TOPO_HANDLE_S) @@ -1278,6 +1331,7 @@ struct ice_aqc_link_topo_addr { struct ice_aqc_get_link_topo { struct ice_aqc_link_topo_addr addr; u8 node_part_num; +#define ICE_AQC_GET_LINK_TOPO_NODE_NR_PCA9575 0x21 u8 rsvd[9]; }; @@ -1291,6 +1345,16 @@ struct ice_aqc_set_port_id_led { u8 rsvd[13]; }; +/* Set/Get GPIO (direct, 0x06EC/0x06ED) */ +struct ice_aqc_gpio { + __le16 gpio_ctrl_handle; +#define ICE_AQC_GPIO_HANDLE_S 0 +#define ICE_AQC_GPIO_HANDLE_M (0x3FF << ICE_AQC_GPIO_HANDLE_S) + u8 gpio_num; + u8 gpio_val; + u8 rsvd[12]; +}; + /* Read/Write SFF EEPROM command (indirect 0x06EE) */ struct ice_aqc_sff_eeprom { u8 lport_num; @@ -1932,10 +1996,13 @@ struct ice_aq_desc { struct ice_aqc_get_phy_caps get_phy; struct ice_aqc_set_phy_cfg set_phy; struct ice_aqc_restart_an restart_an; + struct ice_aqc_gpio read_write_gpio; struct ice_aqc_sff_eeprom read_write_sff_param; struct ice_aqc_set_port_id_led set_port_id_led; struct ice_aqc_get_sw_cfg get_sw_conf; struct ice_aqc_sw_rules sw_rules; + struct ice_aqc_add_get_recipe add_get_recipe; + struct ice_aqc_recipe_to_profile recipe_to_profile; struct ice_aqc_get_topo get_topo; struct ice_aqc_sched_elem_cmd sched_elem_cmd; struct ice_aqc_query_txsched_res query_sched_res; @@ -2044,6 +2111,12 @@ enum ice_adminq_opc { ice_aqc_opc_update_vsi = 0x0211, ice_aqc_opc_free_vsi = 0x0213, + /* recipe commands */ + ice_aqc_opc_add_recipe = 0x0290, + ice_aqc_opc_recipe_to_profile = 0x0291, + ice_aqc_opc_get_recipe = 0x0292, + ice_aqc_opc_get_recipe_to_profile = 0x0293, + /* switch rules population commands */ ice_aqc_opc_add_sw_rules = 0x02A0, ice_aqc_opc_update_sw_rules = 0x02A1, @@ -2079,6 +2152,8 @@ enum ice_adminq_opc { ice_aqc_opc_set_mac_lb = 0x0620, ice_aqc_opc_get_link_topo = 0x06E0, ice_aqc_opc_set_port_id_led = 0x06E9, + ice_aqc_opc_set_gpio = 0x06EC, + ice_aqc_opc_get_gpio = 0x06ED, ice_aqc_opc_sff_eeprom = 0x06EE, /* NVM commands */ diff --git a/drivers/net/ethernet/intel/ice/ice_arfs.c b/drivers/net/ethernet/intel/ice/ice_arfs.c index 3071b8e79499..5daade32ea62 100644 --- a/drivers/net/ethernet/intel/ice/ice_arfs.c +++ b/drivers/net/ethernet/intel/ice/ice_arfs.c @@ -614,7 +614,7 @@ int ice_set_cpu_rx_rmap(struct ice_vsi *vsi) return -EINVAL; base_idx = vsi->base_vector; - for (i = 0; i < vsi->num_q_vectors; i++) + ice_for_each_q_vector(vsi, i) if (irq_cpu_rmap_add(netdev->rx_cpu_rmap, pf->msix_entries[base_idx + i].vector)) { ice_free_cpu_rx_rmap(vsi); diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c index d7a5ac9346bc..fa6cd63cbf1f 100644 --- a/drivers/net/ethernet/intel/ice/ice_base.c +++ b/drivers/net/ethernet/intel/ice/ice_base.c @@ -115,6 +115,8 @@ static int ice_vsi_alloc_q_vector(struct ice_vsi *vsi, u16 v_idx) q_vector->rx.itr_setting = ICE_DFLT_RX_ITR; q_vector->tx.itr_mode = ITR_DYNAMIC; q_vector->rx.itr_mode = ITR_DYNAMIC; + q_vector->tx.type = ICE_TX_CONTAINER; + q_vector->rx.type = ICE_RX_CONTAINER; if (vsi->type == ICE_VSI_VF) goto out; @@ -146,7 +148,8 @@ static void ice_free_q_vector(struct ice_vsi *vsi, int v_idx) { struct ice_q_vector *q_vector; struct ice_pf *pf = vsi->back; - struct ice_ring *ring; + struct ice_tx_ring *tx_ring; + struct ice_rx_ring *rx_ring; struct device *dev; dev = ice_pf_to_dev(pf); @@ -156,10 +159,10 @@ static void ice_free_q_vector(struct ice_vsi *vsi, int v_idx) } q_vector = vsi->q_vectors[v_idx]; - ice_for_each_ring(ring, q_vector->tx) - ring->q_vector = NULL; - ice_for_each_ring(ring, q_vector->rx) - ring->q_vector = NULL; + ice_for_each_tx_ring(tx_ring, q_vector->tx) + tx_ring->q_vector = NULL; + ice_for_each_rx_ring(rx_ring, q_vector->rx) + rx_ring->q_vector = NULL; /* only VSI with an associated netdev is set up with NAPI */ if (vsi->netdev) @@ -201,15 +204,18 @@ static void ice_cfg_itr_gran(struct ice_hw *hw) } /** - * ice_calc_q_handle - calculate the queue handle + * ice_calc_txq_handle - calculate the queue handle * @vsi: VSI that ring belongs to * @ring: ring to get the absolute queue index * @tc: traffic class number */ -static u16 ice_calc_q_handle(struct ice_vsi *vsi, struct ice_ring *ring, u8 tc) +static u16 ice_calc_txq_handle(struct ice_vsi *vsi, struct ice_tx_ring *ring, u8 tc) { WARN_ONCE(ice_ring_is_xdp(ring) && tc, "XDP ring can't belong to TC other than 0\n"); + if (ring->ch) + return ring->q_index - ring->ch->base_q; + /* Idea here for calculation is that we subtract the number of queue * count from TC that ring belongs to from it's absolute queue index * and as a result we get the queue's index within TC. @@ -218,7 +224,7 @@ static u16 ice_calc_q_handle(struct ice_vsi *vsi, struct ice_ring *ring, u8 tc) } /** - * ice_eswitch_calc_q_handle + * ice_eswitch_calc_txq_handle * @ring: pointer to ring which unique index is needed * * To correctly work with many netdevs ring->q_index of Tx rings on switchdev @@ -228,7 +234,7 @@ static u16 ice_calc_q_handle(struct ice_vsi *vsi, struct ice_ring *ring, u8 tc) * Return ICE_INVAL_Q_INDEX when index wasn't found. Should never happen, * because VSI is get from ring->vsi, so it has to be present in this VSI. */ -static u16 ice_eswitch_calc_q_handle(struct ice_ring *ring) +static u16 ice_eswitch_calc_txq_handle(struct ice_tx_ring *ring) { struct ice_vsi *vsi = ring->vsi; int i; @@ -248,7 +254,7 @@ static u16 ice_eswitch_calc_q_handle(struct ice_ring *ring) * This enables/disables XPS for a given Tx descriptor ring * based on the TCs enabled for the VSI that ring belongs to. */ -static void ice_cfg_xps_tx_ring(struct ice_ring *ring) +static void ice_cfg_xps_tx_ring(struct ice_tx_ring *ring) { if (!ring->q_vector || !ring->netdev) return; @@ -270,7 +276,7 @@ static void ice_cfg_xps_tx_ring(struct ice_ring *ring) * Configure the Tx descriptor ring in TLAN context. */ static void -ice_setup_tx_ctx(struct ice_ring *ring, struct ice_tlan_ctx *tlan_ctx, u16 pf_q) +ice_setup_tx_ctx(struct ice_tx_ring *ring, struct ice_tlan_ctx *tlan_ctx, u16 pf_q) { struct ice_vsi *vsi = ring->vsi; struct ice_hw *hw = &vsi->back->hw; @@ -282,7 +288,7 @@ ice_setup_tx_ctx(struct ice_ring *ring, struct ice_tlan_ctx *tlan_ctx, u16 pf_q) /* Transmit Queue Length */ tlan_ctx->qlen = ring->count; - ice_set_cgd_num(tlan_ctx, ring); + ice_set_cgd_num(tlan_ctx, ring->dcb_tc); /* PF number */ tlan_ctx->pf_num = hw->pf_id; @@ -297,7 +303,10 @@ ice_setup_tx_ctx(struct ice_ring *ring, struct ice_tlan_ctx *tlan_ctx, u16 pf_q) case ICE_VSI_LB: case ICE_VSI_CTRL: case ICE_VSI_PF: - tlan_ctx->vmvf_type = ICE_TLAN_CTX_VMVF_TYPE_PF; + if (ring->ch) + tlan_ctx->vmvf_type = ICE_TLAN_CTX_VMVF_TYPE_VMQ; + else + tlan_ctx->vmvf_type = ICE_TLAN_CTX_VMVF_TYPE_PF; break; case ICE_VSI_VF: /* Firmware expects vmvf_num to be absolute VF ID */ @@ -312,7 +321,10 @@ ice_setup_tx_ctx(struct ice_ring *ring, struct ice_tlan_ctx *tlan_ctx, u16 pf_q) } /* make sure the context is associated with the right VSI */ - tlan_ctx->src_vsi = ice_get_hw_vsi_num(hw, vsi->idx); + if (ring->ch) + tlan_ctx->src_vsi = ring->ch->vsi_num; + else + tlan_ctx->src_vsi = ice_get_hw_vsi_num(hw, vsi->idx); /* Restrict Tx timestamps to the PF VSI */ switch (vsi->type) { @@ -339,7 +351,7 @@ ice_setup_tx_ctx(struct ice_ring *ring, struct ice_tlan_ctx *tlan_ctx, u16 pf_q) * * Returns the offset value for ring into the data buffer. */ -static unsigned int ice_rx_offset(struct ice_ring *rx_ring) +static unsigned int ice_rx_offset(struct ice_rx_ring *rx_ring) { if (ice_ring_uses_build_skb(rx_ring)) return ICE_SKB_PAD; @@ -355,7 +367,7 @@ static unsigned int ice_rx_offset(struct ice_ring *rx_ring) * * Configure the Rx descriptor ring in RLAN context. */ -static int ice_setup_rx_ctx(struct ice_ring *ring) +static int ice_setup_rx_ctx(struct ice_rx_ring *ring) { int chain_len = ICE_MAX_CHAINED_RX_BUFS; struct ice_vsi *vsi = ring->vsi; @@ -466,7 +478,7 @@ static int ice_setup_rx_ctx(struct ice_ring *ring) * * Return 0 on success and a negative value on error. */ -int ice_vsi_cfg_rxq(struct ice_ring *ring) +int ice_vsi_cfg_rxq(struct ice_rx_ring *ring) { struct device *dev = ice_pf_to_dev(ring->vsi->back); u16 num_bufs = ICE_DESC_UNUSED(ring); @@ -687,16 +699,16 @@ void ice_vsi_map_rings_to_vectors(struct ice_vsi *vsi) tx_rings_per_v = (u8)DIV_ROUND_UP(tx_rings_rem, q_vectors - v_id); q_vector->num_ring_tx = tx_rings_per_v; - q_vector->tx.ring = NULL; + q_vector->tx.tx_ring = NULL; q_vector->tx.itr_idx = ICE_TX_ITR; q_base = vsi->num_txq - tx_rings_rem; for (q_id = q_base; q_id < (q_base + tx_rings_per_v); q_id++) { - struct ice_ring *tx_ring = vsi->tx_rings[q_id]; + struct ice_tx_ring *tx_ring = vsi->tx_rings[q_id]; tx_ring->q_vector = q_vector; - tx_ring->next = q_vector->tx.ring; - q_vector->tx.ring = tx_ring; + tx_ring->next = q_vector->tx.tx_ring; + q_vector->tx.tx_ring = tx_ring; } tx_rings_rem -= tx_rings_per_v; @@ -704,16 +716,16 @@ void ice_vsi_map_rings_to_vectors(struct ice_vsi *vsi) rx_rings_per_v = (u8)DIV_ROUND_UP(rx_rings_rem, q_vectors - v_id); q_vector->num_ring_rx = rx_rings_per_v; - q_vector->rx.ring = NULL; + q_vector->rx.rx_ring = NULL; q_vector->rx.itr_idx = ICE_RX_ITR; q_base = vsi->num_rxq - rx_rings_rem; for (q_id = q_base; q_id < (q_base + rx_rings_per_v); q_id++) { - struct ice_ring *rx_ring = vsi->rx_rings[q_id]; + struct ice_rx_ring *rx_ring = vsi->rx_rings[q_id]; rx_ring->q_vector = q_vector; - rx_ring->next = q_vector->rx.ring; - q_vector->rx.ring = rx_ring; + rx_ring->next = q_vector->rx.rx_ring; + q_vector->rx.rx_ring = rx_ring; } rx_rings_rem -= rx_rings_per_v; } @@ -738,12 +750,13 @@ void ice_vsi_free_q_vectors(struct ice_vsi *vsi) * @qg_buf: queue group buffer */ int -ice_vsi_cfg_txq(struct ice_vsi *vsi, struct ice_ring *ring, +ice_vsi_cfg_txq(struct ice_vsi *vsi, struct ice_tx_ring *ring, struct ice_aqc_add_tx_qgrp *qg_buf) { u8 buf_len = struct_size(qg_buf, txqs, 1); struct ice_tlan_ctx tlan_ctx = { 0 }; struct ice_aqc_add_txqs_perq *txq; + struct ice_channel *ch = ring->ch; struct ice_pf *pf = vsi->back; struct ice_hw *hw = &pf->hw; enum ice_status status; @@ -774,16 +787,22 @@ ice_vsi_cfg_txq(struct ice_vsi *vsi, struct ice_ring *ring, * TC into the VSI Tx ring */ if (vsi->type == ICE_VSI_SWITCHDEV_CTRL) { - ring->q_handle = ice_eswitch_calc_q_handle(ring); + ring->q_handle = ice_eswitch_calc_txq_handle(ring); if (ring->q_handle == ICE_INVAL_Q_INDEX) return -ENODEV; } else { - ring->q_handle = ice_calc_q_handle(vsi, ring, tc); + ring->q_handle = ice_calc_txq_handle(vsi, ring, tc); } - status = ice_ena_vsi_txq(vsi->port_info, vsi->idx, tc, ring->q_handle, - 1, qg_buf, buf_len, NULL); + if (ch) + status = ice_ena_vsi_txq(vsi->port_info, ch->ch_vsi->idx, 0, + ring->q_handle, 1, qg_buf, buf_len, + NULL); + else + status = ice_ena_vsi_txq(vsi->port_info, vsi->idx, tc, + ring->q_handle, 1, qg_buf, buf_len, + NULL); if (status) { dev_err(ice_pf_to_dev(pf), "Failed to set LAN Tx queue context, error: %s\n", ice_stat_str(status)); @@ -904,7 +923,7 @@ void ice_trigger_sw_intr(struct ice_hw *hw, struct ice_q_vector *q_vector) */ int ice_vsi_stop_tx_ring(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src, - u16 rel_vmvf_num, struct ice_ring *ring, + u16 rel_vmvf_num, struct ice_tx_ring *ring, struct ice_txq_meta *txq_meta) { struct ice_pf *pf = vsi->back; @@ -961,9 +980,10 @@ ice_vsi_stop_tx_ring(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src, * are needed for stopping Tx queue */ void -ice_fill_txq_meta(struct ice_vsi *vsi, struct ice_ring *ring, +ice_fill_txq_meta(struct ice_vsi *vsi, struct ice_tx_ring *ring, struct ice_txq_meta *txq_meta) { + struct ice_channel *ch = ring->ch; u8 tc; if (IS_ENABLED(CONFIG_DCB)) @@ -974,6 +994,11 @@ ice_fill_txq_meta(struct ice_vsi *vsi, struct ice_ring *ring, txq_meta->q_id = ring->reg_idx; txq_meta->q_teid = ring->txq_teid; txq_meta->q_handle = ring->q_handle; - txq_meta->vsi_idx = vsi->idx; - txq_meta->tc = tc; + if (ch) { + txq_meta->vsi_idx = ch->ch_vsi->idx; + txq_meta->tc = 0; + } else { + txq_meta->vsi_idx = vsi->idx; + txq_meta->tc = tc; + } } diff --git a/drivers/net/ethernet/intel/ice/ice_base.h b/drivers/net/ethernet/intel/ice/ice_base.h index 20e1c29aa68a..b67dca417acb 100644 --- a/drivers/net/ethernet/intel/ice/ice_base.h +++ b/drivers/net/ethernet/intel/ice/ice_base.h @@ -6,7 +6,7 @@ #include "ice.h" -int ice_vsi_cfg_rxq(struct ice_ring *ring); +int ice_vsi_cfg_rxq(struct ice_rx_ring *ring); int __ice_vsi_get_qs(struct ice_qs_cfg *qs_cfg); int ice_vsi_ctrl_one_rx_ring(struct ice_vsi *vsi, bool ena, u16 rxq_idx, bool wait); @@ -15,7 +15,7 @@ int ice_vsi_alloc_q_vectors(struct ice_vsi *vsi); void ice_vsi_map_rings_to_vectors(struct ice_vsi *vsi); void ice_vsi_free_q_vectors(struct ice_vsi *vsi); int -ice_vsi_cfg_txq(struct ice_vsi *vsi, struct ice_ring *ring, +ice_vsi_cfg_txq(struct ice_vsi *vsi, struct ice_tx_ring *ring, struct ice_aqc_add_tx_qgrp *qg_buf); void ice_cfg_itr(struct ice_hw *hw, struct ice_q_vector *q_vector); void @@ -25,9 +25,9 @@ ice_cfg_rxq_interrupt(struct ice_vsi *vsi, u16 rxq, u16 msix_idx, u16 itr_idx); void ice_trigger_sw_intr(struct ice_hw *hw, struct ice_q_vector *q_vector); int ice_vsi_stop_tx_ring(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src, - u16 rel_vmvf_num, struct ice_ring *ring, + u16 rel_vmvf_num, struct ice_tx_ring *ring, struct ice_txq_meta *txq_meta); void -ice_fill_txq_meta(struct ice_vsi *vsi, struct ice_ring *ring, +ice_fill_txq_meta(struct ice_vsi *vsi, struct ice_tx_ring *ring, struct ice_txq_meta *txq_meta); #endif /* _ICE_BASE_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index df5ad4de1f00..b3066d0fea8b 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -71,6 +71,27 @@ bool ice_is_e810(struct ice_hw *hw) return hw->mac_type == ICE_MAC_E810; } +/** + * ice_is_e810t + * @hw: pointer to the hardware structure + * + * returns true if the device is E810T based, false if not. + */ +bool ice_is_e810t(struct ice_hw *hw) +{ + switch (hw->device_id) { + case ICE_DEV_ID_E810C_SFP: + if (hw->subsystem_device_id == ICE_SUBDEV_ID_E810T || + hw->subsystem_device_id == ICE_SUBDEV_ID_E810T2) + return true; + break; + default: + break; + } + + return false; +} + /** * ice_clear_pf_cfg - Clear PF configuration * @hw: pointer to the hardware structure @@ -242,11 +263,13 @@ ice_aq_get_link_topo_handle(struct ice_port_info *pi, u8 node_type, ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_link_topo); - cmd->addr.node_type_ctx = (ICE_AQC_LINK_TOPO_NODE_CTX_PORT << - ICE_AQC_LINK_TOPO_NODE_CTX_S); + cmd->addr.topo_params.node_type_ctx = + (ICE_AQC_LINK_TOPO_NODE_CTX_PORT << + ICE_AQC_LINK_TOPO_NODE_CTX_S); /* set node type */ - cmd->addr.node_type_ctx |= (ICE_AQC_LINK_TOPO_NODE_TYPE_M & node_type); + cmd->addr.topo_params.node_type_ctx |= + (ICE_AQC_LINK_TOPO_NODE_TYPE_M & node_type); return ice_aq_send_cmd(pi->hw, &desc, NULL, 0, cd); } @@ -570,6 +593,7 @@ static enum ice_status ice_init_fltr_mgmt_struct(struct ice_hw *hw) return ICE_ERR_NO_MEMORY; INIT_LIST_HEAD(&sw->vsi_list_map_head); + sw->prof_res_bm_init = 0; status = ice_init_def_sw_recp(hw); if (status) { @@ -596,17 +620,42 @@ static void ice_cleanup_fltr_mgmt_struct(struct ice_hw *hw) list_del(&v_pos_map->list_entry); devm_kfree(ice_hw_to_dev(hw), v_pos_map); } - recps = hw->switch_info->recp_list; - for (i = 0; i < ICE_SW_LKUP_LAST; i++) { - struct ice_fltr_mgmt_list_entry *lst_itr, *tmp_entry; + recps = sw->recp_list; + for (i = 0; i < ICE_MAX_NUM_RECIPES; i++) { + struct ice_recp_grp_entry *rg_entry, *tmprg_entry; recps[i].root_rid = i; - mutex_destroy(&recps[i].filt_rule_lock); - list_for_each_entry_safe(lst_itr, tmp_entry, - &recps[i].filt_rules, list_entry) { - list_del(&lst_itr->list_entry); - devm_kfree(ice_hw_to_dev(hw), lst_itr); + list_for_each_entry_safe(rg_entry, tmprg_entry, + &recps[i].rg_list, l_entry) { + list_del(&rg_entry->l_entry); + devm_kfree(ice_hw_to_dev(hw), rg_entry); } + + if (recps[i].adv_rule) { + struct ice_adv_fltr_mgmt_list_entry *tmp_entry; + struct ice_adv_fltr_mgmt_list_entry *lst_itr; + + mutex_destroy(&recps[i].filt_rule_lock); + list_for_each_entry_safe(lst_itr, tmp_entry, + &recps[i].filt_rules, + list_entry) { + list_del(&lst_itr->list_entry); + devm_kfree(ice_hw_to_dev(hw), lst_itr->lkups); + devm_kfree(ice_hw_to_dev(hw), lst_itr); + } + } else { + struct ice_fltr_mgmt_list_entry *lst_itr, *tmp_entry; + + mutex_destroy(&recps[i].filt_rule_lock); + list_for_each_entry_safe(lst_itr, tmp_entry, + &recps[i].filt_rules, + list_entry) { + list_del(&lst_itr->list_entry); + devm_kfree(ice_hw_to_dev(hw), lst_itr); + } + } + if (recps[i].root_buf) + devm_kfree(ice_hw_to_dev(hw), recps[i].root_buf); } ice_rm_all_sw_replay_rule_info(hw); devm_kfree(ice_hw_to_dev(hw), sw->recp_list); @@ -4768,6 +4817,64 @@ ice_aq_get_driver_param(struct ice_hw *hw, enum ice_aqc_driver_params idx, return 0; } +/** + * ice_aq_set_gpio + * @hw: pointer to the hw struct + * @gpio_ctrl_handle: GPIO controller node handle + * @pin_idx: IO Number of the GPIO that needs to be set + * @value: SW provide IO value to set in the LSB + * @cd: pointer to command details structure or NULL + * + * Sends 0x06EC AQ command to set the GPIO pin state that's part of the topology + */ +int +ice_aq_set_gpio(struct ice_hw *hw, u16 gpio_ctrl_handle, u8 pin_idx, bool value, + struct ice_sq_cd *cd) +{ + struct ice_aqc_gpio *cmd; + struct ice_aq_desc desc; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_gpio); + cmd = &desc.params.read_write_gpio; + cmd->gpio_ctrl_handle = cpu_to_le16(gpio_ctrl_handle); + cmd->gpio_num = pin_idx; + cmd->gpio_val = value ? 1 : 0; + + return ice_status_to_errno(ice_aq_send_cmd(hw, &desc, NULL, 0, cd)); +} + +/** + * ice_aq_get_gpio + * @hw: pointer to the hw struct + * @gpio_ctrl_handle: GPIO controller node handle + * @pin_idx: IO Number of the GPIO that needs to be set + * @value: IO value read + * @cd: pointer to command details structure or NULL + * + * Sends 0x06ED AQ command to get the value of a GPIO signal which is part of + * the topology + */ +int +ice_aq_get_gpio(struct ice_hw *hw, u16 gpio_ctrl_handle, u8 pin_idx, + bool *value, struct ice_sq_cd *cd) +{ + struct ice_aqc_gpio *cmd; + struct ice_aq_desc desc; + enum ice_status status; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_gpio); + cmd = &desc.params.read_write_gpio; + cmd->gpio_ctrl_handle = cpu_to_le16(gpio_ctrl_handle); + cmd->gpio_num = pin_idx; + + status = ice_aq_send_cmd(hw, &desc, NULL, 0, cd); + if (status) + return ice_status_to_errno(status); + + *value = !!cmd->gpio_val; + return 0; +} + /** * ice_fw_supports_link_override * @hw: pointer to the hardware structure diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h index fb16070f02e2..65c1b3244264 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.h +++ b/drivers/net/ethernet/intel/ice/ice_common.h @@ -183,6 +183,7 @@ ice_stat_update40(struct ice_hw *hw, u32 reg, bool prev_stat_loaded, void ice_stat_update32(struct ice_hw *hw, u32 reg, bool prev_stat_loaded, u64 *prev_stat, u64 *cur_stat); +bool ice_is_e810t(struct ice_hw *hw); enum ice_status ice_sched_query_elem(struct ice_hw *hw, u32 node_teid, struct ice_aqc_txsched_elem_data *buf); @@ -192,6 +193,12 @@ ice_aq_set_driver_param(struct ice_hw *hw, enum ice_aqc_driver_params idx, int ice_aq_get_driver_param(struct ice_hw *hw, enum ice_aqc_driver_params idx, u32 *value, struct ice_sq_cd *cd); +int +ice_aq_set_gpio(struct ice_hw *hw, u16 gpio_ctrl_handle, u8 pin_idx, bool value, + struct ice_sq_cd *cd); +int +ice_aq_get_gpio(struct ice_hw *hw, u16 gpio_ctrl_handle, u8 pin_idx, + bool *value, struct ice_sq_cd *cd); enum ice_status ice_aq_set_lldp_mib(struct ice_hw *hw, u8 mib_type, void *buf, u16 buf_size, struct ice_sq_cd *cd); diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c index 73714685fb68..a72e18320a22 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c @@ -4,53 +4,11 @@ #include "ice_dcb_lib.h" #include "ice_dcb_nl.h" -/** - * ice_vsi_cfg_netdev_tc - Setup the netdev TC configuration - * @vsi: the VSI being configured - * @ena_tc: TC map to be enabled - */ -void ice_vsi_cfg_netdev_tc(struct ice_vsi *vsi, u8 ena_tc) -{ - struct net_device *netdev = vsi->netdev; - struct ice_pf *pf = vsi->back; - struct ice_dcbx_cfg *dcbcfg; - u8 netdev_tc; - int i; - - if (!netdev) - return; - - if (!ena_tc) { - netdev_reset_tc(netdev); - return; - } - - if (netdev_set_num_tc(netdev, vsi->tc_cfg.numtc)) - return; - - dcbcfg = &pf->hw.port_info->qos_cfg.local_dcbx_cfg; - - ice_for_each_traffic_class(i) - if (vsi->tc_cfg.ena_tc & BIT(i)) - netdev_set_tc_queue(netdev, - vsi->tc_cfg.tc_info[i].netdev_tc, - vsi->tc_cfg.tc_info[i].qcount_tx, - vsi->tc_cfg.tc_info[i].qoffset); - - for (i = 0; i < ICE_MAX_USER_PRIORITY; i++) { - u8 ets_tc = dcbcfg->etscfg.prio_table[i]; - - /* Get the mapped netdev TC# for the UP */ - netdev_tc = vsi->tc_cfg.tc_info[ets_tc].netdev_tc; - netdev_set_prio_tc_map(netdev, i, netdev_tc); - } -} - /** * ice_dcb_get_ena_tc - return bitmap of enabled TCs * @dcbcfg: DCB config to evaluate for enabled TCs */ -u8 ice_dcb_get_ena_tc(struct ice_dcbx_cfg *dcbcfg) +static u8 ice_dcb_get_ena_tc(struct ice_dcbx_cfg *dcbcfg) { u8 i, num_tc, ena_tc = 1; @@ -178,6 +136,67 @@ u8 ice_dcb_get_num_tc(struct ice_dcbx_cfg *dcbcfg) return ret; } +/** + * ice_get_first_droptc - returns number of first droptc + * @vsi: used to find the first droptc + * + * This function returns the value of first_droptc. + * When DCB is enabled, first droptc information is derived from enabled_tc + * and PFC enabled bits. otherwise this function returns 0 as there is one + * TC without DCB (tc0) + */ +static u8 ice_get_first_droptc(struct ice_vsi *vsi) +{ + struct ice_dcbx_cfg *cfg = &vsi->port_info->qos_cfg.local_dcbx_cfg; + struct device *dev = ice_pf_to_dev(vsi->back); + u8 num_tc, ena_tc_map, pfc_ena_map; + u8 i; + + num_tc = ice_dcb_get_num_tc(cfg); + + /* get bitmap of enabled TCs */ + ena_tc_map = ice_dcb_get_ena_tc(cfg); + + /* get bitmap of PFC enabled TCs */ + pfc_ena_map = cfg->pfc.pfcena; + + /* get first TC that is not PFC enabled */ + for (i = 0; i < num_tc; i++) { + if ((ena_tc_map & BIT(i)) && (!(pfc_ena_map & BIT(i)))) { + dev_dbg(dev, "first drop tc = %d\n", i); + return i; + } + } + + dev_dbg(dev, "first drop tc = 0\n"); + return 0; +} + +/** + * ice_vsi_set_dcb_tc_cfg - Set VSI's TC based on DCB configuration + * @vsi: pointer to the VSI instance + */ +void ice_vsi_set_dcb_tc_cfg(struct ice_vsi *vsi) +{ + struct ice_dcbx_cfg *cfg = &vsi->port_info->qos_cfg.local_dcbx_cfg; + + switch (vsi->type) { + case ICE_VSI_PF: + vsi->tc_cfg.ena_tc = ice_dcb_get_ena_tc(cfg); + vsi->tc_cfg.numtc = ice_dcb_get_num_tc(cfg); + break; + case ICE_VSI_CHNL: + vsi->tc_cfg.ena_tc = BIT(ice_get_first_droptc(vsi)); + vsi->tc_cfg.numtc = 1; + break; + case ICE_VSI_CTRL: + case ICE_VSI_LB: + default: + vsi->tc_cfg.ena_tc = ICE_DFLT_TRAFFIC_CLASS; + vsi->tc_cfg.numtc = 1; + } +} + /** * ice_dcb_get_tc - Get the TC associated with the queue * @vsi: ptr to the VSI @@ -194,17 +213,18 @@ u8 ice_dcb_get_tc(struct ice_vsi *vsi, int queue_index) */ void ice_vsi_cfg_dcb_rings(struct ice_vsi *vsi) { - struct ice_ring *tx_ring, *rx_ring; + struct ice_tx_ring *tx_ring; + struct ice_rx_ring *rx_ring; u16 qoffset, qcount; int i, n; if (!test_bit(ICE_FLAG_DCB_ENA, vsi->back->flags)) { /* Reset the TC information */ - for (i = 0; i < vsi->num_txq; i++) { + ice_for_each_txq(vsi, i) { tx_ring = vsi->tx_rings[i]; tx_ring->dcb_tc = 0; } - for (i = 0; i < vsi->num_rxq; i++) { + ice_for_each_rxq(vsi, i) { rx_ring = vsi->rx_rings[i]; rx_ring->dcb_tc = 0; } @@ -217,11 +237,68 @@ void ice_vsi_cfg_dcb_rings(struct ice_vsi *vsi) qoffset = vsi->tc_cfg.tc_info[n].qoffset; qcount = vsi->tc_cfg.tc_info[n].qcount_tx; - for (i = qoffset; i < (qoffset + qcount); i++) { - tx_ring = vsi->tx_rings[i]; - rx_ring = vsi->rx_rings[i]; - tx_ring->dcb_tc = n; - rx_ring->dcb_tc = n; + for (i = qoffset; i < (qoffset + qcount); i++) + vsi->tx_rings[i]->dcb_tc = n; + + qcount = vsi->tc_cfg.tc_info[n].qcount_rx; + for (i = qoffset; i < (qoffset + qcount); i++) + vsi->rx_rings[i]->dcb_tc = n; + } + /* applicable only if "all_enatc" is set, which will be set from + * setup_tc method as part of configuring channels + */ + if (vsi->all_enatc) { + u8 first_droptc = ice_get_first_droptc(vsi); + + /* When DCB is configured, TC for ADQ queues (which are really + * PF queues) should be the first drop TC of the main VSI + */ + ice_for_each_chnl_tc(n) { + if (!(vsi->all_enatc & BIT(n))) + break; + + qoffset = vsi->mqprio_qopt.qopt.offset[n]; + qcount = vsi->mqprio_qopt.qopt.count[n]; + for (i = qoffset; i < (qoffset + qcount); i++) { + vsi->tx_rings[i]->dcb_tc = first_droptc; + vsi->rx_rings[i]->dcb_tc = first_droptc; + } + } + } +} + +/** + * ice_dcb_ena_dis_vsi - disable certain VSIs for DCB config/reconfig + * @pf: pointer to the PF instance + * @ena: true to enable VSIs, false to disable + * @locked: true if caller holds RTNL lock, false otherwise + * + * Before a new DCB configuration can be applied, VSIs of type PF, SWITCHDEV + * and CHNL need to be brought down. Following completion of DCB configuration + * the VSIs that were downed need to be brought up again. This helper function + * does both. + */ +static void ice_dcb_ena_dis_vsi(struct ice_pf *pf, bool ena, bool locked) +{ + int i; + + ice_for_each_vsi(pf, i) { + struct ice_vsi *vsi = pf->vsi[i]; + + if (!vsi) + continue; + + switch (vsi->type) { + case ICE_VSI_CHNL: + case ICE_VSI_SWITCHDEV_CTRL: + case ICE_VSI_PF: + if (ena) + ice_ena_vsi(vsi, locked); + else + ice_dis_vsi(vsi, locked); + break; + default: + continue; } } } @@ -330,7 +407,9 @@ int ice_pf_dcb_cfg(struct ice_pf *pf, struct ice_dcbx_cfg *new_cfg, bool locked) */ if (!locked) rtnl_lock(); - ice_dis_vsi(pf_vsi, true); + + /* disable VSIs affected by DCB changes */ + ice_dcb_ena_dis_vsi(pf, false, true); memcpy(curr_cfg, new_cfg, sizeof(*curr_cfg)); memcpy(&curr_cfg->etsrec, &curr_cfg->etscfg, sizeof(curr_cfg->etsrec)); @@ -358,7 +437,8 @@ int ice_pf_dcb_cfg(struct ice_pf *pf, struct ice_dcbx_cfg *new_cfg, bool locked) ice_pf_dcb_recfg(pf); out: - ice_ena_vsi(pf_vsi, true); + /* enable previously downed VSIs */ + ice_dcb_ena_dis_vsi(pf, true, true); if (!locked) rtnl_unlock(); free_cfg: @@ -673,6 +753,8 @@ void ice_pf_dcb_recfg(struct ice_pf *pf) tc_map = ICE_DFLT_TRAFFIC_CLASS; ice_dcb_noncontig_cfg(pf); } + } else if (vsi->type == ICE_VSI_CHNL) { + tc_map = BIT(ice_get_first_droptc(vsi)); } else { tc_map = ICE_DFLT_TRAFFIC_CLASS; } @@ -683,10 +765,11 @@ void ice_pf_dcb_recfg(struct ice_pf *pf) vsi->idx); continue; } - /* no need to proceed with remaining cfg if it is switchdev - * VSI + /* no need to proceed with remaining cfg if it is CHNL + * or switchdev VSI */ - if (vsi->type == ICE_VSI_SWITCHDEV_CTRL) + if (vsi->type == ICE_VSI_CHNL || + vsi->type == ICE_VSI_SWITCHDEV_CTRL) continue; ice_vsi_map_rings_to_vectors(vsi); @@ -824,7 +907,7 @@ void ice_update_dcb_stats(struct ice_pf *pf) * tag will already be configured with the correct ID and priority bits */ void -ice_tx_prepare_vlan_flags_dcb(struct ice_ring *tx_ring, +ice_tx_prepare_vlan_flags_dcb(struct ice_tx_ring *tx_ring, struct ice_tx_buf *first) { struct sk_buff *skb = first->skb; @@ -861,7 +944,6 @@ ice_dcb_process_lldp_set_mib_change(struct ice_pf *pf, struct ice_dcbx_cfg tmp_dcbx_cfg; bool need_reconfig = false; struct ice_port_info *pi; - struct ice_vsi *pf_vsi; u8 mib_type; int ret; @@ -937,14 +1019,9 @@ ice_dcb_process_lldp_set_mib_change(struct ice_pf *pf, clear_bit(ICE_FLAG_DCB_ENA, pf->flags); } - pf_vsi = ice_get_main_vsi(pf); - if (!pf_vsi) { - dev_dbg(dev, "PF VSI doesn't exist\n"); - goto out; - } - rtnl_lock(); - ice_dis_vsi(pf_vsi, true); + /* disable VSIs affected by DCB changes */ + ice_dcb_ena_dis_vsi(pf, false, true); ret = ice_query_port_ets(pf->hw.port_info, &buf, sizeof(buf), NULL); if (ret) { @@ -955,7 +1032,8 @@ ice_dcb_process_lldp_set_mib_change(struct ice_pf *pf, /* changes in configuration update VSI */ ice_pf_dcb_recfg(pf); - ice_ena_vsi(pf_vsi, true); + /* enable previously downed VSIs */ + ice_dcb_ena_dis_vsi(pf, true, true); unlock_rtnl: rtnl_unlock(); out: diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.h b/drivers/net/ethernet/intel/ice/ice_dcb_lib.h index 3dcde1750a5e..4c421c842a13 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.h @@ -16,7 +16,6 @@ void ice_dcb_rebuild(struct ice_pf *pf); int ice_dcb_sw_dflt_cfg(struct ice_pf *pf, bool ets_willing, bool locked); -u8 ice_dcb_get_ena_tc(struct ice_dcbx_cfg *dcbcfg); u8 ice_dcb_get_num_tc(struct ice_dcbx_cfg *dcbcfg); void ice_vsi_set_dcb_tc_cfg(struct ice_vsi *vsi); bool ice_is_pfc_causing_hung_q(struct ice_pf *pf, unsigned int txqueue); @@ -29,13 +28,11 @@ void ice_vsi_cfg_dcb_rings(struct ice_vsi *vsi); int ice_init_pf_dcb(struct ice_pf *pf, bool locked); void ice_update_dcb_stats(struct ice_pf *pf); void -ice_tx_prepare_vlan_flags_dcb(struct ice_ring *tx_ring, +ice_tx_prepare_vlan_flags_dcb(struct ice_tx_ring *tx_ring, struct ice_tx_buf *first); void ice_dcb_process_lldp_set_mib_change(struct ice_pf *pf, struct ice_rq_event_info *event); -void ice_vsi_cfg_netdev_tc(struct ice_vsi *vsi, u8 ena_tc); - /** * ice_find_q_in_range * @low: start of queue range for a TC i.e. offset of TC @@ -50,9 +47,9 @@ static inline bool ice_find_q_in_range(u16 low, u16 high, unsigned int tx_q) } static inline void -ice_set_cgd_num(struct ice_tlan_ctx *tlan_ctx, struct ice_ring *ring) +ice_set_cgd_num(struct ice_tlan_ctx *tlan_ctx, u8 dcb_tc) { - tlan_ctx->cgd_num = ring->dcb_tc; + tlan_ctx->cgd_num = dcb_tc; } static inline bool ice_is_dcb_active(struct ice_pf *pf) @@ -69,6 +66,12 @@ static inline u8 ice_get_pfc_mode(struct ice_pf *pf) #else static inline void ice_dcb_rebuild(struct ice_pf *pf) { } +static inline void ice_vsi_set_dcb_tc_cfg(struct ice_vsi *vsi) +{ + vsi->tc_cfg.ena_tc = ICE_DFLT_TRAFFIC_CLASS; + vsi->tc_cfg.numtc = 1; +} + static inline u8 ice_dcb_get_ena_tc(struct ice_dcbx_cfg __always_unused *dcbcfg) { return ICE_DFLT_TRAFFIC_CLASS; @@ -102,7 +105,7 @@ ice_pf_dcb_cfg(struct ice_pf __always_unused *pf, } static inline int -ice_tx_prepare_vlan_flags_dcb(struct ice_ring __always_unused *tx_ring, +ice_tx_prepare_vlan_flags_dcb(struct ice_tx_ring __always_unused *tx_ring, struct ice_tx_buf __always_unused *first) { return 0; @@ -130,7 +133,6 @@ static inline void ice_vsi_cfg_dcb_rings(struct ice_vsi *vsi) { } static inline void ice_update_dcb_stats(struct ice_pf *pf) { } static inline void ice_dcb_process_lldp_set_mib_change(struct ice_pf *pf, struct ice_rq_event_info *event) { } -static inline void ice_vsi_cfg_netdev_tc(struct ice_vsi *vsi, u8 ena_tc) { } -static inline void ice_set_cgd_num(struct ice_tlan_ctx *tlan_ctx, struct ice_ring *ring) { } +static inline void ice_set_cgd_num(struct ice_tlan_ctx *tlan_ctx, u8 dcb_tc) { } #endif /* CONFIG_DCB */ #endif /* _ICE_DCB_LIB_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_devids.h b/drivers/net/ethernet/intel/ice/ice_devids.h index ef4392e6e244..61dd2f18dee8 100644 --- a/drivers/net/ethernet/intel/ice/ice_devids.h +++ b/drivers/net/ethernet/intel/ice/ice_devids.h @@ -21,6 +21,8 @@ #define ICE_DEV_ID_E810C_QSFP 0x1592 /* Intel(R) Ethernet Controller E810-C for SFP */ #define ICE_DEV_ID_E810C_SFP 0x1593 +#define ICE_SUBDEV_ID_E810T 0x000E +#define ICE_SUBDEV_ID_E810T2 0x000F /* Intel(R) Ethernet Controller E810-XXV for backplane */ #define ICE_DEV_ID_E810_XXV_BACKPLANE 0x1599 /* Intel(R) Ethernet Controller E810-XXV for QSFP */ diff --git a/drivers/net/ethernet/intel/ice/ice_devlink.c b/drivers/net/ethernet/intel/ice/ice_devlink.c index 48e7a5b914b9..b9bd9f9472f6 100644 --- a/drivers/net/ethernet/intel/ice/ice_devlink.c +++ b/drivers/net/ethernet/intel/ice/ice_devlink.c @@ -452,10 +452,8 @@ struct ice_pf *ice_allocate_pf(struct device *dev) return NULL; /* Add an action to teardown the devlink when unwinding the driver */ - if (devm_add_action(dev, ice_devlink_free, devlink)) { - devlink_free(devlink); + if (devm_add_action_or_reset(dev, ice_devlink_free, devlink)) return NULL; - } return devlink_priv(devlink); } diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.c b/drivers/net/ethernet/intel/ice/ice_eswitch.c index 477e3f2d616d..6cb50653b18d 100644 --- a/drivers/net/ethernet/intel/ice/ice_eswitch.c +++ b/drivers/net/ethernet/intel/ice/ice_eswitch.c @@ -7,6 +7,7 @@ #include "ice_fltr.h" #include "ice_repr.h" #include "ice_devlink.h" +#include "ice_tc_lib.h" /** * ice_eswitch_setup_env - configure switchdev HW filters @@ -67,21 +68,6 @@ err_def_rx: return -ENODEV; } -/** - * ice_eswitch_remap_ring - reconfigure ring of switchdev ctrl VSI - * @ring: pointer to ring - * @q_vector: pointer of q_vector which is connected with this ring - * @netdev: netdevice connected with this ring - */ -static void -ice_eswitch_remap_ring(struct ice_ring *ring, struct ice_q_vector *q_vector, - struct net_device *netdev) -{ - ring->q_vector = q_vector; - ring->next = NULL; - ring->netdev = netdev; -} - /** * ice_eswitch_remap_rings_to_vectors - reconfigure rings of switchdev ctrl VSI * @pf: pointer to PF struct @@ -101,23 +87,27 @@ static void ice_eswitch_remap_rings_to_vectors(struct ice_pf *pf) ice_for_each_txq(vsi, q_id) { struct ice_repr *repr = pf->vf[q_id].repr; struct ice_q_vector *q_vector = repr->q_vector; - struct ice_ring *tx_ring = vsi->tx_rings[q_id]; - struct ice_ring *rx_ring = vsi->rx_rings[q_id]; + struct ice_tx_ring *tx_ring = vsi->tx_rings[q_id]; + struct ice_rx_ring *rx_ring = vsi->rx_rings[q_id]; q_vector->vsi = vsi; q_vector->reg_idx = vsi->q_vectors[0]->reg_idx; q_vector->num_ring_tx = 1; - q_vector->tx.ring = tx_ring; - ice_eswitch_remap_ring(tx_ring, q_vector, repr->netdev); + q_vector->tx.tx_ring = tx_ring; + tx_ring->q_vector = q_vector; + tx_ring->next = NULL; + tx_ring->netdev = repr->netdev; /* In switchdev mode, from OS stack perspective, there is only * one queue for given netdev, so it needs to be indexed as 0. */ tx_ring->q_index = 0; q_vector->num_ring_rx = 1; - q_vector->rx.ring = rx_ring; - ice_eswitch_remap_ring(rx_ring, q_vector, repr->netdev); + q_vector->rx.rx_ring = rx_ring; + rx_ring->q_vector = q_vector; + rx_ring->next = NULL; + rx_ring->netdev = repr->netdev; } } @@ -339,7 +329,7 @@ static void ice_eswitch_release_env(struct ice_pf *pf) static struct ice_vsi * ice_eswitch_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi) { - return ice_vsi_setup(pf, pi, ICE_VSI_SWITCHDEV_CTRL, ICE_INVAL_VFID); + return ice_vsi_setup(pf, pi, ICE_VSI_SWITCHDEV_CTRL, ICE_INVAL_VFID, NULL); } /** @@ -389,7 +379,7 @@ static void ice_eswitch_set_rxdid(struct ice_vsi *vsi, u32 rxdid) int i; ice_for_each_rxq(vsi, i) { - struct ice_ring *ring = vsi->rx_rings[i]; + struct ice_rx_ring *ring = vsi->rx_rings[i]; u16 pf_q = vsi->rxq_map[ring->q_index]; ice_write_qrxflxp_cntxt(hw, pf_q, rxdid, 0x3, true); @@ -510,7 +500,7 @@ ice_eswitch_mode_set(struct devlink *devlink, u16 mode, * context, regular netdev associated with Rx ring is returned. */ struct net_device * -ice_eswitch_get_target_netdev(struct ice_ring *rx_ring, +ice_eswitch_get_target_netdev(struct ice_rx_ring *rx_ring, union ice_32b_rx_flex_desc *rx_desc) { struct ice_32b_rx_flex_desc_nic_2 *desc; @@ -645,6 +635,8 @@ int ice_eswitch_rebuild(struct ice_pf *pf) ice_eswitch_remap_rings_to_vectors(pf); + ice_replay_tc_fltrs(pf); + status = ice_vsi_open(ctrl_vsi); if (status) return status; diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.h b/drivers/net/ethernet/intel/ice/ice_eswitch.h index 23df0d400847..364cd2a79c37 100644 --- a/drivers/net/ethernet/intel/ice/ice_eswitch.h +++ b/drivers/net/ethernet/intel/ice/ice_eswitch.h @@ -22,7 +22,7 @@ void ice_eswitch_update_repr(struct ice_vsi *vsi); void ice_eswitch_stop_all_tx_queues(struct ice_pf *pf); struct net_device * -ice_eswitch_get_target_netdev(struct ice_ring *rx_ring, +ice_eswitch_get_target_netdev(struct ice_rx_ring *rx_ring, union ice_32b_rx_flex_desc *rx_desc); void ice_eswitch_set_target_vsi(struct sk_buff *skb, @@ -68,7 +68,7 @@ static inline bool ice_is_eswitch_mode_switchdev(struct ice_pf *pf) } static inline struct net_device * -ice_eswitch_get_target_netdev(struct ice_ring *rx_ring, +ice_eswitch_get_target_netdev(struct ice_rx_ring *rx_ring, union ice_32b_rx_flex_desc *rx_desc) { return rx_ring->netdev; diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index 201979cc47fb..cfe96a127ed4 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -192,7 +192,6 @@ __ice_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo, strscpy(drvinfo->bus_info, pci_name(pf->pdev), sizeof(drvinfo->bus_info)); - drvinfo->n_priv_flags = ICE_PRIV_FLAG_ARRAY_SIZE; } static void @@ -201,18 +200,8 @@ ice_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo) struct ice_netdev_priv *np = netdev_priv(netdev); __ice_get_drvinfo(netdev, drvinfo, np->vsi); -} -static void -ice_repr_get_drvinfo(struct net_device *netdev, - struct ethtool_drvinfo *drvinfo) -{ - struct ice_repr *repr = ice_netdev_to_repr(netdev); - - if (ice_check_vf_ready_for_cfg(repr->vf)) - return; - - __ice_get_drvinfo(netdev, drvinfo, repr->src_vsi); + drvinfo->n_priv_flags = ICE_PRIV_FLAG_ARRAY_SIZE; } static int ice_get_regs_len(struct net_device __always_unused *netdev) @@ -603,7 +592,7 @@ static bool ice_lbtest_check_frame(u8 *frame) * * Function sends loopback packets on a test Tx ring. */ -static int ice_diag_send(struct ice_ring *tx_ring, u8 *data, u16 size) +static int ice_diag_send(struct ice_tx_ring *tx_ring, u8 *data, u16 size) { struct ice_tx_desc *tx_desc; struct ice_tx_buf *tx_buf; @@ -656,7 +645,7 @@ static int ice_diag_send(struct ice_ring *tx_ring, u8 *data, u16 size) * Function receives loopback packets and verify their correctness. * Returns number of received valid frames. */ -static int ice_lbtest_receive_frames(struct ice_ring *rx_ring) +static int ice_lbtest_receive_frames(struct ice_rx_ring *rx_ring) { struct ice_rx_buf *rx_buf; int valid_frames, i; @@ -695,9 +684,10 @@ static u64 ice_loopback_test(struct net_device *netdev) struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_vsi *orig_vsi = np->vsi, *test_vsi; struct ice_pf *pf = orig_vsi->back; - struct ice_ring *tx_ring, *rx_ring; u8 broadcast[ETH_ALEN], ret = 0; int num_frames, valid_frames; + struct ice_tx_ring *tx_ring; + struct ice_rx_ring *rx_ring; struct device *dev; u8 *tx_frame; int i; @@ -885,10 +875,10 @@ skip_ol_tests: netdev_info(netdev, "testing finished\n"); } -static void ice_get_strings(struct net_device *netdev, u32 stringset, u8 *data) +static void +__ice_get_strings(struct net_device *netdev, u32 stringset, u8 *data, + struct ice_vsi *vsi) { - struct ice_netdev_priv *np = netdev_priv(netdev); - struct ice_vsi *vsi = ice_get_netdev_priv_vsi(np); unsigned int i; u8 *p = data; @@ -939,6 +929,13 @@ static void ice_get_strings(struct net_device *netdev, u32 stringset, u8 *data) } } +static void ice_get_strings(struct net_device *netdev, u32 stringset, u8 *data) +{ + struct ice_netdev_priv *np = netdev_priv(netdev); + + __ice_get_strings(netdev, stringset, data, np->vsi); +} + static int ice_set_phys_id(struct net_device *netdev, enum ethtool_phys_id_state state) { @@ -1330,9 +1327,6 @@ static int ice_get_sset_count(struct net_device *netdev, int sset) * order of strings will suffer from race conditions and are * not safe. */ - if (ice_is_port_repr_netdev(netdev)) - return ICE_VSI_STATS_LEN; - return ICE_ALL_STATS_LEN(netdev); case ETH_SS_TEST: return ICE_TEST_LEN; @@ -1344,13 +1338,13 @@ static int ice_get_sset_count(struct net_device *netdev, int sset) } static void -ice_get_ethtool_stats(struct net_device *netdev, - struct ethtool_stats __always_unused *stats, u64 *data) +__ice_get_ethtool_stats(struct net_device *netdev, + struct ethtool_stats __always_unused *stats, u64 *data, + struct ice_vsi *vsi) { - struct ice_netdev_priv *np = netdev_priv(netdev); - struct ice_vsi *vsi = ice_get_netdev_priv_vsi(np); struct ice_pf *pf = vsi->back; - struct ice_ring *ring; + struct ice_tx_ring *tx_ring; + struct ice_rx_ring *rx_ring; unsigned int j; int i = 0; char *p; @@ -1371,10 +1365,10 @@ ice_get_ethtool_stats(struct net_device *netdev, rcu_read_lock(); ice_for_each_alloc_txq(vsi, j) { - ring = READ_ONCE(vsi->tx_rings[j]); - if (ring) { - data[i++] = ring->stats.pkts; - data[i++] = ring->stats.bytes; + tx_ring = READ_ONCE(vsi->tx_rings[j]); + if (tx_ring) { + data[i++] = tx_ring->stats.pkts; + data[i++] = tx_ring->stats.bytes; } else { data[i++] = 0; data[i++] = 0; @@ -1382,10 +1376,10 @@ ice_get_ethtool_stats(struct net_device *netdev, } ice_for_each_alloc_rxq(vsi, j) { - ring = READ_ONCE(vsi->rx_rings[j]); - if (ring) { - data[i++] = ring->stats.pkts; - data[i++] = ring->stats.bytes; + rx_ring = READ_ONCE(vsi->rx_rings[j]); + if (rx_ring) { + data[i++] = rx_ring->stats.pkts; + data[i++] = rx_ring->stats.bytes; } else { data[i++] = 0; data[i++] = 0; @@ -1414,6 +1408,15 @@ ice_get_ethtool_stats(struct net_device *netdev, } } +static void +ice_get_ethtool_stats(struct net_device *netdev, + struct ethtool_stats __always_unused *stats, u64 *data) +{ + struct ice_netdev_priv *np = netdev_priv(netdev); + + __ice_get_ethtool_stats(netdev, stats, data, np->vsi); +} + #define ICE_PHY_TYPE_LOW_MASK_MIN_1G (ICE_PHY_TYPE_LOW_100BASE_TX | \ ICE_PHY_TYPE_LOW_100M_SGMII) @@ -2702,9 +2705,10 @@ ice_get_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring) static int ice_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring) { - struct ice_ring *tx_rings = NULL, *rx_rings = NULL; struct ice_netdev_priv *np = netdev_priv(netdev); - struct ice_ring *xdp_rings = NULL; + struct ice_tx_ring *xdp_rings = NULL; + struct ice_tx_ring *tx_rings = NULL; + struct ice_rx_ring *rx_rings = NULL; struct ice_vsi *vsi = np->vsi; struct ice_pf *pf = vsi->back; int i, timeout = 50, err = 0; @@ -2753,12 +2757,12 @@ ice_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring) /* set for the next time the netdev is started */ if (!netif_running(vsi->netdev)) { - for (i = 0; i < vsi->alloc_txq; i++) + ice_for_each_alloc_txq(vsi, i) vsi->tx_rings[i]->count = new_tx_cnt; - for (i = 0; i < vsi->alloc_rxq; i++) + ice_for_each_alloc_rxq(vsi, i) vsi->rx_rings[i]->count = new_rx_cnt; if (ice_is_xdp_ena_vsi(vsi)) - for (i = 0; i < vsi->num_xdp_txq; i++) + ice_for_each_xdp_txq(vsi, i) vsi->xdp_rings[i]->count = new_tx_cnt; vsi->num_tx_desc = (u16)new_tx_cnt; vsi->num_rx_desc = (u16)new_rx_cnt; @@ -2807,7 +2811,7 @@ ice_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring) goto free_tx; } - for (i = 0; i < vsi->num_xdp_txq; i++) { + ice_for_each_xdp_txq(vsi, i) { /* clone ring and setup updated count */ xdp_rings[i] = *vsi->xdp_rings[i]; xdp_rings[i].count = new_tx_cnt; @@ -2901,7 +2905,7 @@ process_link: } if (xdp_rings) { - for (i = 0; i < vsi->num_xdp_txq; i++) { + ice_for_each_xdp_txq(vsi, i) { ice_free_tx_ring(vsi->xdp_rings[i]); *vsi->xdp_rings[i] = xdp_rings[i]; } @@ -3190,6 +3194,11 @@ ice_set_rxfh(struct net_device *netdev, const u32 *indir, const u8 *key, return -EIO; } + if (ice_is_adq_active(pf)) { + netdev_err(netdev, "Cannot change RSS params with ADQ configured.\n"); + return -EOPNOTSUPP; + } + if (key) { if (!vsi->rss_hkey_user) { vsi->rss_hkey_user = @@ -3290,7 +3299,7 @@ static u32 ice_get_combined_cnt(struct ice_vsi *vsi) ice_for_each_q_vector(vsi, q_idx) { struct ice_q_vector *q_vector = vsi->q_vectors[q_idx]; - if (q_vector->rx.ring && q_vector->tx.ring) + if (q_vector->rx.rx_ring && q_vector->tx.tx_ring) combined++; } @@ -3400,6 +3409,11 @@ static int ice_set_channels(struct net_device *dev, struct ethtool_channels *ch) if (ch->other_count != (test_bit(ICE_FLAG_FD_ENA, pf->flags) ? 1U : 0U)) return -EINVAL; + if (ice_is_adq_active(pf)) { + netdev_err(dev, "Cannot set channels with ADQ configured.\n"); + return -EOPNOTSUPP; + } + if (test_bit(ICE_FLAG_FD_ENA, pf->flags) && pf->hw.fdir_active_fltr) { netdev_err(dev, "Cannot set channels when Flow Director filters are active\n"); return -EOPNOTSUPP; @@ -3501,15 +3515,9 @@ static int ice_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol) return 0; } -enum ice_container_type { - ICE_RX_CONTAINER, - ICE_TX_CONTAINER, -}; - /** * ice_get_rc_coalesce - get ITR values for specific ring container * @ec: ethtool structure to fill with driver's coalesce settings - * @c_type: container type, Rx or Tx * @rc: ring container that the ITR values will come from * * Query the device for ice_ring_container specific ITR values. This is @@ -3519,24 +3527,23 @@ enum ice_container_type { * Returns 0 on success, negative otherwise. */ static int -ice_get_rc_coalesce(struct ethtool_coalesce *ec, enum ice_container_type c_type, - struct ice_ring_container *rc) +ice_get_rc_coalesce(struct ethtool_coalesce *ec, struct ice_ring_container *rc) { - if (!rc->ring) + if (!rc->rx_ring) return -EINVAL; - switch (c_type) { + switch (rc->type) { case ICE_RX_CONTAINER: ec->use_adaptive_rx_coalesce = ITR_IS_DYNAMIC(rc); ec->rx_coalesce_usecs = rc->itr_setting; - ec->rx_coalesce_usecs_high = rc->ring->q_vector->intrl; + ec->rx_coalesce_usecs_high = rc->rx_ring->q_vector->intrl; break; case ICE_TX_CONTAINER: ec->use_adaptive_tx_coalesce = ITR_IS_DYNAMIC(rc); ec->tx_coalesce_usecs = rc->itr_setting; break; default: - dev_dbg(ice_pf_to_dev(rc->ring->vsi->back), "Invalid c_type %d\n", c_type); + dev_dbg(ice_pf_to_dev(rc->rx_ring->vsi->back), "Invalid c_type %d\n", rc->type); return -EINVAL; } @@ -3557,18 +3564,18 @@ static int ice_get_q_coalesce(struct ice_vsi *vsi, struct ethtool_coalesce *ec, int q_num) { if (q_num < vsi->num_rxq && q_num < vsi->num_txq) { - if (ice_get_rc_coalesce(ec, ICE_RX_CONTAINER, + if (ice_get_rc_coalesce(ec, &vsi->rx_rings[q_num]->q_vector->rx)) return -EINVAL; - if (ice_get_rc_coalesce(ec, ICE_TX_CONTAINER, + if (ice_get_rc_coalesce(ec, &vsi->tx_rings[q_num]->q_vector->tx)) return -EINVAL; } else if (q_num < vsi->num_rxq) { - if (ice_get_rc_coalesce(ec, ICE_RX_CONTAINER, + if (ice_get_rc_coalesce(ec, &vsi->rx_rings[q_num]->q_vector->rx)) return -EINVAL; } else if (q_num < vsi->num_txq) { - if (ice_get_rc_coalesce(ec, ICE_TX_CONTAINER, + if (ice_get_rc_coalesce(ec, &vsi->tx_rings[q_num]->q_vector->tx)) return -EINVAL; } else { @@ -3620,7 +3627,6 @@ ice_get_per_q_coalesce(struct net_device *netdev, u32 q_num, /** * ice_set_rc_coalesce - set ITR values for specific ring container - * @c_type: container type, Rx or Tx * @ec: ethtool structure from user to update ITR settings * @rc: ring container that the ITR values will come from * @vsi: VSI associated to the ring container @@ -3632,19 +3638,22 @@ ice_get_per_q_coalesce(struct net_device *netdev, u32 q_num, * Returns 0 on success, negative otherwise. */ static int -ice_set_rc_coalesce(enum ice_container_type c_type, struct ethtool_coalesce *ec, +ice_set_rc_coalesce(struct ethtool_coalesce *ec, struct ice_ring_container *rc, struct ice_vsi *vsi) { - const char *c_type_str = (c_type == ICE_RX_CONTAINER) ? "rx" : "tx"; + const char *c_type_str = (rc->type == ICE_RX_CONTAINER) ? "rx" : "tx"; u32 use_adaptive_coalesce, coalesce_usecs; struct ice_pf *pf = vsi->back; u16 itr_setting; - if (!rc->ring) + if (!rc->rx_ring) return -EINVAL; - switch (c_type) { + switch (rc->type) { case ICE_RX_CONTAINER: + { + struct ice_q_vector *q_vector = rc->rx_ring->q_vector; + if (ec->rx_coalesce_usecs_high > ICE_MAX_INTRL || (ec->rx_coalesce_usecs_high && ec->rx_coalesce_usecs_high < pf->hw.intrl_gran)) { @@ -3653,22 +3662,20 @@ ice_set_rc_coalesce(enum ice_container_type c_type, struct ethtool_coalesce *ec, ICE_MAX_INTRL); return -EINVAL; } - if (ec->rx_coalesce_usecs_high != rc->ring->q_vector->intrl && + if (ec->rx_coalesce_usecs_high != q_vector->intrl && (ec->use_adaptive_rx_coalesce || ec->use_adaptive_tx_coalesce)) { netdev_info(vsi->netdev, "Invalid value, %s-usecs-high cannot be changed if adaptive-tx or adaptive-rx is enabled\n", c_type_str); return -EINVAL; } - if (ec->rx_coalesce_usecs_high != rc->ring->q_vector->intrl) { - rc->ring->q_vector->intrl = ec->rx_coalesce_usecs_high; - ice_write_intrl(rc->ring->q_vector, - ec->rx_coalesce_usecs_high); - } + if (ec->rx_coalesce_usecs_high != q_vector->intrl) + q_vector->intrl = ec->rx_coalesce_usecs_high; use_adaptive_coalesce = ec->use_adaptive_rx_coalesce; coalesce_usecs = ec->rx_coalesce_usecs; break; + } case ICE_TX_CONTAINER: use_adaptive_coalesce = ec->use_adaptive_tx_coalesce; coalesce_usecs = ec->tx_coalesce_usecs; @@ -3676,7 +3683,7 @@ ice_set_rc_coalesce(enum ice_container_type c_type, struct ethtool_coalesce *ec, break; default: dev_dbg(ice_pf_to_dev(pf), "Invalid container type %d\n", - c_type); + rc->type); return -EINVAL; } @@ -3725,22 +3732,22 @@ static int ice_set_q_coalesce(struct ice_vsi *vsi, struct ethtool_coalesce *ec, int q_num) { if (q_num < vsi->num_rxq && q_num < vsi->num_txq) { - if (ice_set_rc_coalesce(ICE_RX_CONTAINER, ec, + if (ice_set_rc_coalesce(ec, &vsi->rx_rings[q_num]->q_vector->rx, vsi)) return -EINVAL; - if (ice_set_rc_coalesce(ICE_TX_CONTAINER, ec, + if (ice_set_rc_coalesce(ec, &vsi->tx_rings[q_num]->q_vector->tx, vsi)) return -EINVAL; } else if (q_num < vsi->num_rxq) { - if (ice_set_rc_coalesce(ICE_RX_CONTAINER, ec, + if (ice_set_rc_coalesce(ec, &vsi->rx_rings[q_num]->q_vector->rx, vsi)) return -EINVAL; } else if (q_num < vsi->num_txq) { - if (ice_set_rc_coalesce(ICE_TX_CONTAINER, ec, + if (ice_set_rc_coalesce(ec, &vsi->tx_rings[q_num]->q_vector->tx, vsi)) return -EINVAL; @@ -3813,6 +3820,8 @@ __ice_set_coalesce(struct net_device *netdev, struct ethtool_coalesce *ec, if (ice_set_q_coalesce(vsi, ec, v_idx)) return -EINVAL; + + ice_set_q_vector_intrl(vsi->q_vectors[v_idx]); } goto set_complete; } @@ -3820,6 +3829,8 @@ __ice_set_coalesce(struct net_device *netdev, struct ethtool_coalesce *ec, if (ice_set_q_coalesce(vsi, ec, q_num)) return -EINVAL; + ice_set_q_vector_intrl(vsi->q_vectors[q_num]); + set_complete: return 0; } @@ -3839,6 +3850,54 @@ ice_set_per_q_coalesce(struct net_device *netdev, u32 q_num, return __ice_set_coalesce(netdev, ec, q_num); } +static void +ice_repr_get_drvinfo(struct net_device *netdev, + struct ethtool_drvinfo *drvinfo) +{ + struct ice_repr *repr = ice_netdev_to_repr(netdev); + + if (ice_check_vf_ready_for_cfg(repr->vf)) + return; + + __ice_get_drvinfo(netdev, drvinfo, repr->src_vsi); +} + +static void +ice_repr_get_strings(struct net_device *netdev, u32 stringset, u8 *data) +{ + struct ice_repr *repr = ice_netdev_to_repr(netdev); + + /* for port representors only ETH_SS_STATS is supported */ + if (ice_check_vf_ready_for_cfg(repr->vf) || + stringset != ETH_SS_STATS) + return; + + __ice_get_strings(netdev, stringset, data, repr->src_vsi); +} + +static void +ice_repr_get_ethtool_stats(struct net_device *netdev, + struct ethtool_stats __always_unused *stats, + u64 *data) +{ + struct ice_repr *repr = ice_netdev_to_repr(netdev); + + if (ice_check_vf_ready_for_cfg(repr->vf)) + return; + + __ice_get_ethtool_stats(netdev, stats, data, repr->src_vsi); +} + +static int ice_repr_get_sset_count(struct net_device *netdev, int sset) +{ + switch (sset) { + case ETH_SS_STATS: + return ICE_VSI_STATS_LEN; + default: + return -EOPNOTSUPP; + } +} + #define ICE_I2C_EEPROM_DEV_ADDR 0xA0 #define ICE_I2C_EEPROM_DEV_ADDR2 0xA2 #define ICE_MODULE_TYPE_SFP 0x03 @@ -4093,9 +4152,9 @@ void ice_set_ethtool_safe_mode_ops(struct net_device *netdev) static const struct ethtool_ops ice_ethtool_repr_ops = { .get_drvinfo = ice_repr_get_drvinfo, .get_link = ethtool_op_get_link, - .get_strings = ice_get_strings, - .get_ethtool_stats = ice_get_ethtool_stats, - .get_sset_count = ice_get_sset_count, + .get_strings = ice_repr_get_strings, + .get_ethtool_stats = ice_repr_get_ethtool_stats, + .get_sset_count = ice_repr_get_sset_count, }; /** diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c index 16de603b280c..38960bcc384c 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c @@ -706,7 +706,7 @@ ice_create_init_fdir_rule(struct ice_pf *pf, enum ice_fltr_ptype flow) if (!seg) return -ENOMEM; - tun_seg = devm_kzalloc(dev, sizeof(*seg) * ICE_FD_HW_SEG_MAX, + tun_seg = devm_kcalloc(dev, sizeof(*seg), ICE_FD_HW_SEG_MAX, GFP_KERNEL); if (!tun_seg) { devm_kfree(dev, seg); @@ -1068,7 +1068,7 @@ ice_cfg_fdir_xtrct_seq(struct ice_pf *pf, struct ethtool_rx_flow_spec *fsp, if (!seg) return -ENOMEM; - tun_seg = devm_kzalloc(dev, sizeof(*seg) * ICE_FD_HW_SEG_MAX, + tun_seg = devm_kcalloc(dev, sizeof(*seg), ICE_FD_HW_SEG_MAX, GFP_KERNEL); if (!tun_seg) { devm_kfree(dev, seg); diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c index 1ac96dc66d0d..e731b46270c3 100644 --- a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c +++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c @@ -735,7 +735,7 @@ static void ice_release_global_cfg_lock(struct ice_hw *hw) * * This function will request ownership of the change lock. */ -static enum ice_status +enum ice_status ice_acquire_change_lock(struct ice_hw *hw, enum ice_aq_res_access_type access) { return ice_acquire_res(hw, ICE_CHANGE_LOCK_RES_ID, access, @@ -748,7 +748,7 @@ ice_acquire_change_lock(struct ice_hw *hw, enum ice_aq_res_access_type access) * * This function will release the change lock using the proper Admin Command. */ -static void ice_release_change_lock(struct ice_hw *hw) +void ice_release_change_lock(struct ice_hw *hw) { ice_release_res(hw, ICE_CHANGE_LOCK_RES_ID); } @@ -1329,6 +1329,86 @@ fw_ddp_compat_free_alloc: return status; } +/** + * ice_sw_fv_handler + * @sect_type: section type + * @section: pointer to section + * @index: index of the field vector entry to be returned + * @offset: ptr to variable that receives the offset in the field vector table + * + * This is a callback function that can be passed to ice_pkg_enum_entry. + * This function treats the given section as of type ice_sw_fv_section and + * enumerates offset field. "offset" is an index into the field vector table. + */ +static void * +ice_sw_fv_handler(u32 sect_type, void *section, u32 index, u32 *offset) +{ + struct ice_sw_fv_section *fv_section = section; + + if (!section || sect_type != ICE_SID_FLD_VEC_SW) + return NULL; + if (index >= le16_to_cpu(fv_section->count)) + return NULL; + if (offset) + /* "index" passed in to this function is relative to a given + * 4k block. To get to the true index into the field vector + * table need to add the relative index to the base_offset + * field of this section + */ + *offset = le16_to_cpu(fv_section->base_offset) + index; + return fv_section->fv + index; +} + +/** + * ice_get_prof_index_max - get the max profile index for used profile + * @hw: pointer to the HW struct + * + * Calling this function will get the max profile index for used profile + * and store the index number in struct ice_switch_info *switch_info + * in HW for following use. + */ +static enum ice_status ice_get_prof_index_max(struct ice_hw *hw) +{ + u16 prof_index = 0, j, max_prof_index = 0; + struct ice_pkg_enum state; + struct ice_seg *ice_seg; + bool flag = false; + struct ice_fv *fv; + u32 offset; + + memset(&state, 0, sizeof(state)); + + if (!hw->seg) + return ICE_ERR_PARAM; + + ice_seg = hw->seg; + + do { + fv = ice_pkg_enum_entry(ice_seg, &state, ICE_SID_FLD_VEC_SW, + &offset, ice_sw_fv_handler); + if (!fv) + break; + ice_seg = NULL; + + /* in the profile that not be used, the prot_id is set to 0xff + * and the off is set to 0x1ff for all the field vectors. + */ + for (j = 0; j < hw->blk[ICE_BLK_SW].es.fvw; j++) + if (fv->ew[j].prot_id != ICE_PROT_INVALID || + fv->ew[j].off != ICE_FV_OFFSET_INVAL) + flag = true; + if (flag && prof_index > max_prof_index) + max_prof_index = prof_index; + + prof_index++; + flag = false; + } while (fv); + + hw->switch_info->max_used_prof_index = max_prof_index; + + return 0; +} + /** * ice_init_pkg - initialize/download package * @hw: pointer to the hardware structure @@ -1408,6 +1488,7 @@ enum ice_status ice_init_pkg(struct ice_hw *hw, u8 *buf, u32 len) */ ice_init_pkg_regs(hw); ice_fill_blk_tbls(hw); + ice_get_prof_index_max(hw); } else { ice_debug(hw, ICE_DBG_INIT, "package load failed, %d\n", status); @@ -1484,6 +1565,167 @@ static struct ice_buf_build *ice_pkg_buf_alloc(struct ice_hw *hw) return bld; } +/** + * ice_get_sw_fv_bitmap - Get switch field vector bitmap based on profile type + * @hw: pointer to hardware structure + * @req_profs: type of profiles requested + * @bm: pointer to memory for returning the bitmap of field vectors + */ +void +ice_get_sw_fv_bitmap(struct ice_hw *hw, enum ice_prof_type req_profs, + unsigned long *bm) +{ + struct ice_pkg_enum state; + struct ice_seg *ice_seg; + struct ice_fv *fv; + + if (req_profs == ICE_PROF_ALL) { + bitmap_set(bm, 0, ICE_MAX_NUM_PROFILES); + return; + } + + memset(&state, 0, sizeof(state)); + bitmap_zero(bm, ICE_MAX_NUM_PROFILES); + ice_seg = hw->seg; + do { + u32 offset; + + fv = ice_pkg_enum_entry(ice_seg, &state, ICE_SID_FLD_VEC_SW, + &offset, ice_sw_fv_handler); + ice_seg = NULL; + + if (fv) { + if (req_profs & ICE_PROF_NON_TUN) + set_bit((u16)offset, bm); + } + } while (fv); +} + +/** + * ice_get_sw_fv_list + * @hw: pointer to the HW structure + * @prot_ids: field vector to search for with a given protocol ID + * @ids_cnt: lookup/protocol count + * @bm: bitmap of field vectors to consider + * @fv_list: Head of a list + * + * Finds all the field vector entries from switch block that contain + * a given protocol ID and returns a list of structures of type + * "ice_sw_fv_list_entry". Every structure in the list has a field vector + * definition and profile ID information + * NOTE: The caller of the function is responsible for freeing the memory + * allocated for every list entry. + */ +enum ice_status +ice_get_sw_fv_list(struct ice_hw *hw, u8 *prot_ids, u16 ids_cnt, + unsigned long *bm, struct list_head *fv_list) +{ + struct ice_sw_fv_list_entry *fvl; + struct ice_sw_fv_list_entry *tmp; + struct ice_pkg_enum state; + struct ice_seg *ice_seg; + struct ice_fv *fv; + u32 offset; + + memset(&state, 0, sizeof(state)); + + if (!ids_cnt || !hw->seg) + return ICE_ERR_PARAM; + + ice_seg = hw->seg; + do { + u16 i; + + fv = ice_pkg_enum_entry(ice_seg, &state, ICE_SID_FLD_VEC_SW, + &offset, ice_sw_fv_handler); + if (!fv) + break; + ice_seg = NULL; + + /* If field vector is not in the bitmap list, then skip this + * profile. + */ + if (!test_bit((u16)offset, bm)) + continue; + + for (i = 0; i < ids_cnt; i++) { + int j; + + /* This code assumes that if a switch field vector line + * has a matching protocol, then this line will contain + * the entries necessary to represent every field in + * that protocol header. + */ + for (j = 0; j < hw->blk[ICE_BLK_SW].es.fvw; j++) + if (fv->ew[j].prot_id == prot_ids[i]) + break; + if (j >= hw->blk[ICE_BLK_SW].es.fvw) + break; + if (i + 1 == ids_cnt) { + fvl = devm_kzalloc(ice_hw_to_dev(hw), + sizeof(*fvl), GFP_KERNEL); + if (!fvl) + goto err; + fvl->fv_ptr = fv; + fvl->profile_id = offset; + list_add(&fvl->list_entry, fv_list); + break; + } + } + } while (fv); + if (list_empty(fv_list)) + return ICE_ERR_CFG; + return 0; + +err: + list_for_each_entry_safe(fvl, tmp, fv_list, list_entry) { + list_del(&fvl->list_entry); + devm_kfree(ice_hw_to_dev(hw), fvl); + } + + return ICE_ERR_NO_MEMORY; +} + +/** + * ice_init_prof_result_bm - Initialize the profile result index bitmap + * @hw: pointer to hardware structure + */ +void ice_init_prof_result_bm(struct ice_hw *hw) +{ + struct ice_pkg_enum state; + struct ice_seg *ice_seg; + struct ice_fv *fv; + + memset(&state, 0, sizeof(state)); + + if (!hw->seg) + return; + + ice_seg = hw->seg; + do { + u32 off; + u16 i; + + fv = ice_pkg_enum_entry(ice_seg, &state, ICE_SID_FLD_VEC_SW, + &off, ice_sw_fv_handler); + ice_seg = NULL; + if (!fv) + break; + + bitmap_zero(hw->switch_info->prof_res_bm[off], + ICE_MAX_FV_WORDS); + + /* Determine empty field vector indices, these can be + * used for recipe results. Skip index 0, since it is + * always used for Switch ID. + */ + for (i = 1; i < ICE_MAX_FV_WORDS; i++) + if (fv->ew[i].prot_id == ICE_PROT_INVALID && + fv->ew[i].off == ICE_FV_OFFSET_INVAL) + set_bit(i, hw->switch_info->prof_res_bm[off]); + } while (fv); +} + /** * ice_pkg_buf_free * @hw: pointer to the HW structure @@ -1863,6 +2105,35 @@ int ice_udp_tunnel_unset_port(struct net_device *netdev, unsigned int table, return 0; } +/** + * ice_find_prot_off - find prot ID and offset pair, based on prof and FV index + * @hw: pointer to the hardware structure + * @blk: hardware block + * @prof: profile ID + * @fv_idx: field vector word index + * @prot: variable to receive the protocol ID + * @off: variable to receive the protocol offset + */ +enum ice_status +ice_find_prot_off(struct ice_hw *hw, enum ice_block blk, u8 prof, u16 fv_idx, + u8 *prot, u16 *off) +{ + struct ice_fv_word *fv_ext; + + if (prof >= hw->blk[blk].es.count) + return ICE_ERR_PARAM; + + if (fv_idx >= hw->blk[blk].es.fvw) + return ICE_ERR_PARAM; + + fv_ext = hw->blk[blk].es.t + (prof * hw->blk[blk].es.fvw); + + *prot = fv_ext[fv_idx].prot_id; + *off = fv_ext[fv_idx].off; + + return 0; +} + /* PTG Management */ /** diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.h b/drivers/net/ethernet/intel/ice/ice_flex_pipe.h index 8a58e79729b9..344c2637facd 100644 --- a/drivers/net/ethernet/intel/ice/ice_flex_pipe.h +++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.h @@ -18,6 +18,20 @@ #define ICE_PKG_CNT 4 +enum ice_status +ice_acquire_change_lock(struct ice_hw *hw, enum ice_aq_res_access_type access); +void ice_release_change_lock(struct ice_hw *hw); +enum ice_status +ice_find_prot_off(struct ice_hw *hw, enum ice_block blk, u8 prof, u16 fv_idx, + u8 *prot, u16 *off); +void +ice_get_sw_fv_bitmap(struct ice_hw *hw, enum ice_prof_type type, + unsigned long *bm); +void +ice_init_prof_result_bm(struct ice_hw *hw); +enum ice_status +ice_get_sw_fv_list(struct ice_hw *hw, u8 *prot_ids, u16 ids_cnt, + unsigned long *bm, struct list_head *fv_list); bool ice_get_open_tunnel_port(struct ice_hw *hw, u16 *port); int ice_udp_tunnel_set_port(struct net_device *netdev, unsigned int table, diff --git a/drivers/net/ethernet/intel/ice/ice_flex_type.h b/drivers/net/ethernet/intel/ice/ice_flex_type.h index 7d8b517a63c9..120bcebaa080 100644 --- a/drivers/net/ethernet/intel/ice/ice_flex_type.h +++ b/drivers/net/ethernet/intel/ice/ice_flex_type.h @@ -13,6 +13,8 @@ struct ice_fv_word { u8 resvrd; } __packed; +#define ICE_MAX_NUM_PROFILES 256 + #define ICE_MAX_FV_WORDS 48 struct ice_fv { struct ice_fv_word ew[ICE_MAX_FV_WORDS]; @@ -279,6 +281,12 @@ struct ice_sw_fv_section { struct ice_fv fv[]; }; +struct ice_sw_fv_list_entry { + struct list_head list_entry; + u32 profile_id; + struct ice_fv *fv_ptr; +}; + /* The BOOST TCAM stores the match packet header in reverse order, meaning * the fields are reversed; in addition, this means that the normally big endian * fields of the packet are now little endian. @@ -603,4 +611,9 @@ struct ice_chs_chg { }; #define ICE_FLOW_PTYPE_MAX ICE_XLT1_CNT + +enum ice_prof_type { + ICE_PROF_NON_TUN = 0x1, + ICE_PROF_ALL = 0xFF, +}; #endif /* _ICE_FLEX_TYPE_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_fltr.h b/drivers/net/ethernet/intel/ice/ice_fltr.h index 949e38ce016c..8eec4febead1 100644 --- a/drivers/net/ethernet/intel/ice/ice_fltr.h +++ b/drivers/net/ethernet/intel/ice/ice_fltr.h @@ -36,10 +36,6 @@ enum ice_status ice_fltr_remove_eth(struct ice_vsi *vsi, u16 ethertype, u16 flag, enum ice_sw_fwd_act_type action); void ice_fltr_remove_all(struct ice_vsi *vsi); - -enum ice_status -ice_fltr_update_flags(struct ice_vsi *vsi, u16 rule_id, u16 recipe_id, - u32 new_flags); enum ice_status ice_fltr_update_flags_dflt_rule(struct ice_vsi *vsi, u16 rule_id, u8 direction, u32 new_flags); diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h index 76021d977b60..a49082485642 100644 --- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h +++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h @@ -182,6 +182,7 @@ #define GLINT_DYN_CTL_INTERVAL_S 5 #define GLINT_DYN_CTL_INTERVAL_M ICE_M(0xFFF, 5) #define GLINT_DYN_CTL_SW_ITR_INDX_ENA_M BIT(24) +#define GLINT_DYN_CTL_SW_ITR_INDX_S 25 #define GLINT_DYN_CTL_SW_ITR_INDX_M ICE_M(0x3, 25) #define GLINT_DYN_CTL_WB_ON_ITR_M BIT(30) #define GLINT_DYN_CTL_INTENA_MSK_M BIT(31) diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 754053178176..77dceab9fbbe 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -22,6 +22,8 @@ const char *ice_vsi_type_str(enum ice_vsi_type vsi_type) return "ICE_VSI_VF"; case ICE_VSI_CTRL: return "ICE_VSI_CTRL"; + case ICE_VSI_CHNL: + return "ICE_VSI_CHNL"; case ICE_VSI_LB: return "ICE_VSI_LB"; case ICE_VSI_SWITCHDEV_CTRL: @@ -46,12 +48,12 @@ static int ice_vsi_ctrl_all_rx_rings(struct ice_vsi *vsi, bool ena) int ret = 0; u16 i; - for (i = 0; i < vsi->num_rxq; i++) + ice_for_each_rxq(vsi, i) ice_vsi_ctrl_one_rx_ring(vsi, ena, i, false); ice_flush(&vsi->back->hw); - for (i = 0; i < vsi->num_rxq; i++) { + ice_for_each_rxq(vsi, i) { ret = ice_vsi_wait_one_rx_ring(vsi, ena, i); if (ret) break; @@ -73,6 +75,8 @@ static int ice_vsi_alloc_arrays(struct ice_vsi *vsi) struct device *dev; dev = ice_pf_to_dev(pf); + if (vsi->type == ICE_VSI_CHNL) + return 0; /* allocate memory for both Tx and Rx ring pointers */ vsi->tx_rings = devm_kcalloc(dev, vsi->alloc_txq, @@ -229,6 +233,10 @@ static void ice_vsi_set_num_qs(struct ice_vsi *vsi, u16 vf_id) vsi->alloc_rxq = 1; vsi->num_q_vectors = 1; break; + case ICE_VSI_CHNL: + vsi->alloc_txq = 0; + vsi->alloc_rxq = 0; + break; case ICE_VSI_LB: vsi->alloc_txq = 1; vsi->alloc_rxq = 1; @@ -274,7 +282,7 @@ static int ice_get_free_slot(void *array, int size, int curr) * ice_vsi_delete - delete a VSI from the switch * @vsi: pointer to VSI being removed */ -static void ice_vsi_delete(struct ice_vsi *vsi) +void ice_vsi_delete(struct ice_vsi *vsi) { struct ice_pf *pf = vsi->back; struct ice_vsi_ctx *ctxt; @@ -345,7 +353,7 @@ static void ice_vsi_free_arrays(struct ice_vsi *vsi) * * Returns 0 on success, negative on failure */ -static int ice_vsi_clear(struct ice_vsi *vsi) +int ice_vsi_clear(struct ice_vsi *vsi) { struct ice_pf *pf = NULL; struct device *dev; @@ -390,12 +398,12 @@ static irqreturn_t ice_msix_clean_ctrl_vsi(int __always_unused irq, void *data) { struct ice_q_vector *q_vector = (struct ice_q_vector *)data; - if (!q_vector->tx.ring) + if (!q_vector->tx.tx_ring) return IRQ_HANDLED; #define FDIR_RX_DESC_CLEAN_BUDGET 64 - ice_clean_rx_irq(q_vector->rx.ring, FDIR_RX_DESC_CLEAN_BUDGET); - ice_clean_ctrl_tx_irq(q_vector->tx.ring); + ice_clean_rx_irq(q_vector->rx.rx_ring, FDIR_RX_DESC_CLEAN_BUDGET); + ice_clean_ctrl_tx_irq(q_vector->tx.tx_ring); return IRQ_HANDLED; } @@ -409,7 +417,7 @@ static irqreturn_t ice_msix_clean_rings(int __always_unused irq, void *data) { struct ice_q_vector *q_vector = (struct ice_q_vector *)data; - if (!q_vector->tx.ring && !q_vector->rx.ring) + if (!q_vector->tx.tx_ring && !q_vector->rx.rx_ring) return IRQ_HANDLED; q_vector->total_events++; @@ -425,7 +433,7 @@ static irqreturn_t ice_eswitch_msix_clean_rings(int __always_unused irq, void *d struct ice_pf *pf = q_vector->vsi->back; int i; - if (!q_vector->tx.ring && !q_vector->rx.ring) + if (!q_vector->tx.tx_ring && !q_vector->rx.rx_ring) return IRQ_HANDLED; ice_for_each_vf(pf, i) @@ -438,12 +446,14 @@ static irqreturn_t ice_eswitch_msix_clean_rings(int __always_unused irq, void *d * ice_vsi_alloc - Allocates the next available struct VSI in the PF * @pf: board private structure * @vsi_type: type of VSI + * @ch: ptr to channel * @vf_id: ID of the VF being configured * * returns a pointer to a VSI on success, NULL on failure. */ static struct ice_vsi * -ice_vsi_alloc(struct ice_pf *pf, enum ice_vsi_type vsi_type, u16 vf_id) +ice_vsi_alloc(struct ice_pf *pf, enum ice_vsi_type vsi_type, + struct ice_channel *ch, u16 vf_id) { struct device *dev = ice_pf_to_dev(pf); struct ice_vsi *vsi = NULL; @@ -470,7 +480,7 @@ ice_vsi_alloc(struct ice_pf *pf, enum ice_vsi_type vsi_type, u16 vf_id) if (vsi_type == ICE_VSI_VF) ice_vsi_set_num_qs(vsi, vf_id); - else + else if (vsi_type != ICE_VSI_CHNL) ice_vsi_set_num_qs(vsi, ICE_INVAL_VFID); switch (vsi->type) { @@ -499,6 +509,13 @@ ice_vsi_alloc(struct ice_pf *pf, enum ice_vsi_type vsi_type, u16 vf_id) if (ice_vsi_alloc_arrays(vsi)) goto err_rings; break; + case ICE_VSI_CHNL: + if (!ch) + goto err_rings; + vsi->num_rxq = ch->num_rxq; + vsi->num_txq = ch->num_txq; + vsi->next_base_q = ch->base_q; + break; case ICE_VSI_LB: if (ice_vsi_alloc_arrays(vsi)) goto err_rings; @@ -615,6 +632,9 @@ static int ice_vsi_get_qs(struct ice_vsi *vsi) }; int ret; + if (vsi->type == ICE_VSI_CHNL) + return 0; + ret = __ice_vsi_get_qs(&tx_qs_cfg); if (ret) return ret; @@ -639,12 +659,12 @@ static void ice_vsi_put_qs(struct ice_vsi *vsi) mutex_lock(&pf->avail_q_mutex); - for (i = 0; i < vsi->alloc_txq; i++) { + ice_for_each_alloc_txq(vsi, i) { clear_bit(vsi->txq_map[i], pf->avail_txqs); vsi->txq_map[i] = ICE_INVAL_Q_INDEX; } - for (i = 0; i < vsi->alloc_rxq; i++) { + ice_for_each_alloc_rxq(vsi, i) { clear_bit(vsi->rxq_map[i], pf->avail_rxqs); vsi->rxq_map[i] = ICE_INVAL_Q_INDEX; } @@ -733,11 +753,16 @@ static void ice_vsi_set_rss_params(struct ice_vsi *vsi) cap = &pf->hw.func_caps.common_cap; switch (vsi->type) { + case ICE_VSI_CHNL: case ICE_VSI_PF: /* PF VSI will inherit RSS instance of PF */ vsi->rss_table_size = (u16)cap->rss_table_size; - vsi->rss_size = min_t(u16, num_online_cpus(), - BIT(cap->rss_table_entry_width)); + if (vsi->type == ICE_VSI_CHNL) + vsi->rss_size = min_t(u16, vsi->num_rxq, + BIT(cap->rss_table_entry_width)); + else + vsi->rss_size = min_t(u16, num_online_cpus(), + BIT(cap->rss_table_entry_width)); vsi->rss_lut_type = ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_PF; break; case ICE_VSI_SWITCHDEV_CTRL: @@ -814,21 +839,13 @@ static void ice_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt) u16 num_txq_per_tc, num_rxq_per_tc; u16 qcount_tx = vsi->alloc_txq; u16 qcount_rx = vsi->alloc_rxq; - bool ena_tc0 = false; u8 netdev_tc = 0; int i; - /* at least TC0 should be enabled by default */ - if (vsi->tc_cfg.numtc) { - if (!(vsi->tc_cfg.ena_tc & BIT(0))) - ena_tc0 = true; - } else { - ena_tc0 = true; - } - - if (ena_tc0) { - vsi->tc_cfg.numtc++; - vsi->tc_cfg.ena_tc |= 1; + if (!vsi->tc_cfg.numtc) { + /* at least TC0 should be enabled by default */ + vsi->tc_cfg.numtc = 1; + vsi->tc_cfg.ena_tc = 1; } num_rxq_per_tc = min_t(u16, qcount_rx / vsi->tc_cfg.numtc, ICE_MAX_RXQS_PER_TC); @@ -970,6 +987,7 @@ static void ice_set_rss_vsi_ctx(struct ice_vsi_ctx *ctxt, struct ice_vsi *vsi) dev = ice_pf_to_dev(pf); switch (vsi->type) { + case ICE_VSI_CHNL: case ICE_VSI_PF: /* PF VSI will inherit RSS instance of PF */ lut_type = ICE_AQ_VSI_Q_OPT_RSS_LUT_PF; @@ -992,6 +1010,28 @@ static void ice_set_rss_vsi_ctx(struct ice_vsi_ctx *ctxt, struct ice_vsi *vsi) ICE_AQ_VSI_Q_OPT_RSS_HASH_M); } +static void +ice_chnl_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt) +{ + struct ice_pf *pf = vsi->back; + u16 qcount, qmap; + u8 offset = 0; + int pow; + + qcount = min_t(int, vsi->num_rxq, pf->num_lan_msix); + + pow = order_base_2(qcount); + qmap = ((offset << ICE_AQ_VSI_TC_Q_OFFSET_S) & + ICE_AQ_VSI_TC_Q_OFFSET_M) | + ((pow << ICE_AQ_VSI_TC_Q_NUM_S) & + ICE_AQ_VSI_TC_Q_NUM_M); + + ctxt->info.tc_mapping[0] = cpu_to_le16(qmap); + ctxt->info.mapping_flags |= cpu_to_le16(ICE_AQ_VSI_Q_MAP_CONTIG); + ctxt->info.q_mapping[0] = cpu_to_le16(vsi->next_base_q); + ctxt->info.q_mapping[1] = cpu_to_le16(qcount); +} + /** * ice_vsi_init - Create and initialize a VSI * @vsi: the VSI being configured @@ -1020,6 +1060,7 @@ static int ice_vsi_init(struct ice_vsi *vsi, bool init_vsi) ctxt->flags = ICE_AQ_VSI_TYPE_PF; break; case ICE_VSI_SWITCHDEV_CTRL: + case ICE_VSI_CHNL: ctxt->flags = ICE_AQ_VSI_TYPE_VMDQ2; break; case ICE_VSI_VF: @@ -1032,6 +1073,21 @@ static int ice_vsi_init(struct ice_vsi *vsi, bool init_vsi) goto out; } + /* Handle VLAN pruning for channel VSI if main VSI has VLAN + * prune enabled + */ + if (vsi->type == ICE_VSI_CHNL) { + struct ice_vsi *main_vsi; + + main_vsi = ice_get_main_vsi(pf); + if (main_vsi && ice_vsi_is_vlan_pruning_ena(main_vsi)) + ctxt->info.sw_flags2 |= + ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA; + else + ctxt->info.sw_flags2 &= + ~ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA; + } + ice_set_dflt_vsi_ctx(ctxt); if (test_bit(ICE_FLAG_FD_ENA, pf->flags)) ice_set_fd_vsi_ctx(ctxt, vsi); @@ -1052,13 +1108,17 @@ static int ice_vsi_init(struct ice_vsi *vsi, bool init_vsi) } ctxt->info.sw_id = vsi->port_info->sw_id; - ice_vsi_setup_q_map(vsi, ctxt); - if (!init_vsi) /* means VSI being updated */ - /* must to indicate which section of VSI context are - * being modified - */ - ctxt->info.valid_sections |= - cpu_to_le16(ICE_AQ_VSI_PROP_RXQ_MAP_VALID); + if (vsi->type == ICE_VSI_CHNL) { + ice_chnl_vsi_setup_q_map(vsi, ctxt); + } else { + ice_vsi_setup_q_map(vsi, ctxt); + if (!init_vsi) /* means VSI being updated */ + /* must to indicate which section of VSI context are + * being modified + */ + ctxt->info.valid_sections |= + cpu_to_le16(ICE_AQ_VSI_PROP_RXQ_MAP_VALID); + } /* enable/disable MAC and VLAN anti-spoof when spoofchk is on/off * respectively @@ -1237,6 +1297,8 @@ static int ice_vsi_setup_vector_base(struct ice_vsi *vsi) /* SRIOV doesn't grab irq_tracker entries for each VSI */ if (vsi->type == ICE_VSI_VF) return 0; + if (vsi->type == ICE_VSI_CHNL) + return 0; if (vsi->base_vector) { dev_dbg(dev, "VSI %d has non-zero base vector %d\n", @@ -1291,14 +1353,14 @@ static void ice_vsi_clear_rings(struct ice_vsi *vsi) struct ice_q_vector *q_vector = vsi->q_vectors[i]; if (q_vector) { - q_vector->tx.ring = NULL; - q_vector->rx.ring = NULL; + q_vector->tx.tx_ring = NULL; + q_vector->rx.rx_ring = NULL; } } } if (vsi->tx_rings) { - for (i = 0; i < vsi->alloc_txq; i++) { + ice_for_each_alloc_txq(vsi, i) { if (vsi->tx_rings[i]) { kfree_rcu(vsi->tx_rings[i], rcu); WRITE_ONCE(vsi->tx_rings[i], NULL); @@ -1306,7 +1368,7 @@ static void ice_vsi_clear_rings(struct ice_vsi *vsi) } } if (vsi->rx_rings) { - for (i = 0; i < vsi->alloc_rxq; i++) { + ice_for_each_alloc_rxq(vsi, i) { if (vsi->rx_rings[i]) { kfree_rcu(vsi->rx_rings[i], rcu); WRITE_ONCE(vsi->rx_rings[i], NULL); @@ -1327,8 +1389,8 @@ static int ice_vsi_alloc_rings(struct ice_vsi *vsi) dev = ice_pf_to_dev(pf); /* Allocate Tx rings */ - for (i = 0; i < vsi->alloc_txq; i++) { - struct ice_ring *ring; + ice_for_each_alloc_txq(vsi, i) { + struct ice_tx_ring *ring; /* allocate with kzalloc(), free with kfree_rcu() */ ring = kzalloc(sizeof(*ring), GFP_KERNEL); @@ -1338,7 +1400,6 @@ static int ice_vsi_alloc_rings(struct ice_vsi *vsi) ring->q_index = i; ring->reg_idx = vsi->txq_map[i]; - ring->ring_active = false; ring->vsi = vsi; ring->tx_tstamps = &pf->ptp.port.tx; ring->dev = dev; @@ -1347,8 +1408,8 @@ static int ice_vsi_alloc_rings(struct ice_vsi *vsi) } /* Allocate Rx rings */ - for (i = 0; i < vsi->alloc_rxq; i++) { - struct ice_ring *ring; + ice_for_each_alloc_rxq(vsi, i) { + struct ice_rx_ring *ring; /* allocate with kzalloc(), free with kfree_rcu() */ ring = kzalloc(sizeof(*ring), GFP_KERNEL); @@ -1357,7 +1418,6 @@ static int ice_vsi_alloc_rings(struct ice_vsi *vsi) ring->q_index = i; ring->reg_idx = vsi->rxq_map[i]; - ring->ring_active = false; ring->vsi = vsi; ring->netdev = vsi->netdev; ring->dev = dev; @@ -1405,7 +1465,7 @@ void ice_vsi_manage_rss_lut(struct ice_vsi *vsi, bool ena) * ice_vsi_cfg_rss_lut_key - Configure RSS params for a VSI * @vsi: VSI to be configured */ -static int ice_vsi_cfg_rss_lut_key(struct ice_vsi *vsi) +int ice_vsi_cfg_rss_lut_key(struct ice_vsi *vsi) { struct ice_pf *pf = vsi->back; struct device *dev; @@ -1413,7 +1473,25 @@ static int ice_vsi_cfg_rss_lut_key(struct ice_vsi *vsi) int err; dev = ice_pf_to_dev(pf); - vsi->rss_size = min_t(u16, vsi->rss_size, vsi->num_rxq); + if (vsi->type == ICE_VSI_PF && vsi->ch_rss_size && + (test_bit(ICE_FLAG_TC_MQPRIO, pf->flags))) { + vsi->rss_size = min_t(u16, vsi->rss_size, vsi->ch_rss_size); + } else { + vsi->rss_size = min_t(u16, vsi->rss_size, vsi->num_rxq); + + /* If orig_rss_size is valid and it is less than determined + * main VSI's rss_size, update main VSI's rss_size to be + * orig_rss_size so that when tc-qdisc is deleted, main VSI + * RSS table gets programmed to be correct (whatever it was + * to begin with (prior to setup-tc for ADQ config) + */ + if (vsi->orig_rss_size && vsi->rss_size < vsi->orig_rss_size && + vsi->orig_rss_size <= vsi->num_rxq) { + vsi->rss_size = vsi->orig_rss_size; + /* now orig_rss_size is used, reset it to zero */ + vsi->orig_rss_size = 0; + } + } lut = kzalloc(vsi->rss_table_size, GFP_KERNEL); if (!lut) @@ -1752,7 +1830,7 @@ int ice_vsi_cfg_single_rxq(struct ice_vsi *vsi, u16 q_idx) return ice_vsi_cfg_rxq(vsi->rx_rings[q_idx]); } -int ice_vsi_cfg_single_txq(struct ice_vsi *vsi, struct ice_ring **tx_rings, u16 q_idx) +int ice_vsi_cfg_single_txq(struct ice_vsi *vsi, struct ice_tx_ring **tx_rings, u16 q_idx) { struct ice_aqc_add_tx_qgrp *qg_buf; int err; @@ -1808,7 +1886,7 @@ setup_rings: * Configure the Tx VSI for operation. */ static int -ice_vsi_cfg_txqs(struct ice_vsi *vsi, struct ice_ring **rings, u16 count) +ice_vsi_cfg_txqs(struct ice_vsi *vsi, struct ice_tx_ring **rings, u16 count) { struct ice_aqc_add_tx_qgrp *qg_buf; u16 q_idx = 0; @@ -1859,8 +1937,8 @@ int ice_vsi_cfg_xdp_txqs(struct ice_vsi *vsi) if (ret) return ret; - for (i = 0; i < vsi->num_xdp_txq; i++) - vsi->xdp_rings[i]->xsk_pool = ice_xsk_pool(vsi->xdp_rings[i]); + ice_for_each_xdp_txq(vsi, i) + vsi->xdp_rings[i]->xsk_pool = ice_tx_xsk_pool(vsi->xdp_rings[i]); return ret; } @@ -1895,6 +1973,23 @@ void ice_write_intrl(struct ice_q_vector *q_vector, u8 intrl) ice_intrl_usec_to_reg(intrl, ICE_INTRL_GRAN_ABOVE_25)); } +static struct ice_q_vector *ice_pull_qvec_from_rc(struct ice_ring_container *rc) +{ + switch (rc->type) { + case ICE_RX_CONTAINER: + if (rc->rx_ring) + return rc->rx_ring->q_vector; + break; + case ICE_TX_CONTAINER: + if (rc->tx_ring) + return rc->tx_ring->q_vector; + default: + break; + } + + return NULL; +} + /** * __ice_write_itr - write throttle rate to register * @q_vector: pointer to interrupt data structure @@ -1919,14 +2014,38 @@ void ice_write_itr(struct ice_ring_container *rc, u16 itr) { struct ice_q_vector *q_vector; - if (!rc->ring) + q_vector = ice_pull_qvec_from_rc(rc); + if (!q_vector) return; - q_vector = rc->ring->q_vector; - __ice_write_itr(q_vector, rc, itr); } +/** + * ice_set_q_vector_intrl - set up interrupt rate limiting + * @q_vector: the vector to be configured + * + * Interrupt rate limiting is local to the vector, not per-queue so we must + * detect if either ring container has dynamic moderation enabled to decide + * what to set the interrupt rate limit to via INTRL settings. In the case that + * dynamic moderation is disabled on both, write the value with the cached + * setting to make sure INTRL register matches the user visible value. + */ +void ice_set_q_vector_intrl(struct ice_q_vector *q_vector) +{ + if (ITR_IS_DYNAMIC(&q_vector->tx) || ITR_IS_DYNAMIC(&q_vector->rx)) { + /* in the case of dynamic enabled, cap each vector to no more + * than (4 us) 250,000 ints/sec, which allows low latency + * but still less than 500,000 interrupts per second, which + * reduces CPU a bit in the case of the lowest latency + * setting. The 4 here is a value in microseconds. + */ + ice_write_intrl(q_vector, 4); + } else { + ice_write_intrl(q_vector, q_vector->intrl); + } +} + /** * ice_vsi_cfg_msix - MSIX mode Interrupt Config in the HW * @vsi: the VSI being configured @@ -1941,7 +2060,7 @@ void ice_vsi_cfg_msix(struct ice_vsi *vsi) u16 txq = 0, rxq = 0; int i, q; - for (i = 0; i < vsi->num_q_vectors; i++) { + ice_for_each_q_vector(vsi, i) { struct ice_q_vector *q_vector = vsi->q_vectors[i]; u16 reg_idx = q_vector->reg_idx; @@ -2099,7 +2218,7 @@ int ice_vsi_stop_all_rx_rings(struct ice_vsi *vsi) */ static int ice_vsi_stop_tx_rings(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src, - u16 rel_vmvf_num, struct ice_ring **rings, u16 count) + u16 rel_vmvf_num, struct ice_tx_ring **rings, u16 count) { u16 q_idx; @@ -2221,10 +2340,14 @@ err_out: static void ice_vsi_set_tc_cfg(struct ice_vsi *vsi) { - struct ice_dcbx_cfg *cfg = &vsi->port_info->qos_cfg.local_dcbx_cfg; + if (!test_bit(ICE_FLAG_DCB_ENA, vsi->back->flags)) { + vsi->tc_cfg.ena_tc = ICE_DFLT_TRAFFIC_CLASS; + vsi->tc_cfg.numtc = 1; + return; + } - vsi->tc_cfg.ena_tc = ice_dcb_get_ena_tc(cfg); - vsi->tc_cfg.numtc = ice_dcb_get_num_tc(cfg); + /* set VSI TC information based on DCB config */ + ice_vsi_set_dcb_tc_cfg(vsi); } /** @@ -2337,6 +2460,7 @@ static void ice_set_agg_vsi(struct ice_vsi *vsi) switch (vsi->type) { case ICE_VSI_CTRL: + case ICE_VSI_CHNL: case ICE_VSI_LB: case ICE_VSI_PF: case ICE_VSI_SWITCHDEV_CTRL: @@ -2436,6 +2560,7 @@ static void ice_set_agg_vsi(struct ice_vsi *vsi) * @vf_id: defines VF ID to which this VSI connects. This field is meant to be * used only for ICE_VSI_VF VSI type. For other VSI types, should * fill-in ICE_INVAL_VFID as input. + * @ch: ptr to channel * * This allocates the sw VSI structure and its queue resources. * @@ -2444,7 +2569,7 @@ static void ice_set_agg_vsi(struct ice_vsi *vsi) */ struct ice_vsi * ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, - enum ice_vsi_type vsi_type, u16 vf_id) + enum ice_vsi_type vsi_type, u16 vf_id, struct ice_channel *ch) { u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 }; struct device *dev = ice_pf_to_dev(pf); @@ -2452,10 +2577,12 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, struct ice_vsi *vsi; int ret, i; - if (vsi_type == ICE_VSI_VF || vsi_type == ICE_VSI_CTRL) - vsi = ice_vsi_alloc(pf, vsi_type, vf_id); + if (vsi_type == ICE_VSI_CHNL) + vsi = ice_vsi_alloc(pf, vsi_type, ch, ICE_INVAL_VFID); + else if (vsi_type == ICE_VSI_VF || vsi_type == ICE_VSI_CTRL) + vsi = ice_vsi_alloc(pf, vsi_type, NULL, vf_id); else - vsi = ice_vsi_alloc(pf, vsi_type, ICE_INVAL_VFID); + vsi = ice_vsi_alloc(pf, vsi_type, NULL, ICE_INVAL_VFID); if (!vsi) { dev_err(dev, "could not allocate VSI\n"); @@ -2472,10 +2599,12 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, ice_alloc_fd_res(vsi); - if (ice_vsi_get_qs(vsi)) { - dev_err(dev, "Failed to allocate queues. vsi->idx = %d\n", - vsi->idx); - goto unroll_vsi_alloc; + if (vsi_type != ICE_VSI_CHNL) { + if (ice_vsi_get_qs(vsi)) { + dev_err(dev, "Failed to allocate queues. vsi->idx = %d\n", + vsi->idx); + goto unroll_vsi_alloc; + } } /* set RSS capabilities */ @@ -2534,6 +2663,12 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, } ice_init_arfs(vsi); break; + case ICE_VSI_CHNL: + if (test_bit(ICE_FLAG_RSS_ENA, pf->flags)) { + ice_vsi_cfg_rss_lut_key(vsi); + ice_vsi_set_rss_flow_fld(vsi); + } + break; case ICE_VSI_VF: /* VF driver will take care of creating netdev for this type and * map queues to vectors through Virtchnl, PF driver only @@ -2572,9 +2707,21 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, } /* configure VSI nodes based on number of queues and TC's */ - for (i = 0; i < vsi->tc_cfg.numtc; i++) - max_txqs[i] = vsi->alloc_txq; + ice_for_each_traffic_class(i) { + if (!(vsi->tc_cfg.ena_tc & BIT(i))) + continue; + if (vsi->type == ICE_VSI_CHNL) { + if (!vsi->alloc_txq && vsi->num_txq) + max_txqs[i] = vsi->num_txq; + else + max_txqs[i] = pf->num_lan_tx; + } else { + max_txqs[i] = vsi->alloc_txq; + } + } + + dev_dbg(dev, "vsi->tc_cfg.ena_tc = %d\n", vsi->tc_cfg.ena_tc); status = ice_cfg_vsi_lan(vsi->port_info, vsi->idx, vsi->tc_cfg.ena_tc, max_txqs); if (status) { @@ -2635,7 +2782,7 @@ static void ice_vsi_release_msix(struct ice_vsi *vsi) u32 rxq = 0; int i, q; - for (i = 0; i < vsi->num_q_vectors; i++) { + ice_for_each_q_vector(vsi, i) { struct ice_q_vector *q_vector = vsi->q_vectors[i]; ice_write_intrl(q_vector, 0); @@ -3087,7 +3234,7 @@ ice_vsi_rebuild_set_coalesce(struct ice_vsi *vsi, } vsi->q_vectors[i]->intrl = coalesce[i].intrl; - ice_write_intrl(vsi->q_vectors[i], coalesce[i].intrl); + ice_set_q_vector_intrl(vsi->q_vectors[i]); } /* the number of queue vectors increased so write whatever is in @@ -3105,7 +3252,7 @@ ice_vsi_rebuild_set_coalesce(struct ice_vsi *vsi, ice_write_itr(rc, rc->itr_setting); vsi->q_vectors[i]->intrl = coalesce[0].intrl; - ice_write_intrl(vsi->q_vectors[i], coalesce[0].intrl); + ice_set_q_vector_intrl(vsi->q_vectors[i]); } } @@ -3210,7 +3357,9 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, bool init_vsi) ice_vsi_map_rings_to_vectors(vsi); if (ice_is_xdp_ena_vsi(vsi)) { - vsi->num_xdp_txq = vsi->alloc_rxq; + ret = ice_vsi_determine_xdp_res(vsi); + if (ret) + goto err_vectors; ret = ice_prepare_xdp_rings(vsi, vsi->xdp_prog); if (ret) goto err_vectors; @@ -3237,6 +3386,12 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, bool init_vsi) if (ret) goto err_vectors; + break; + case ICE_VSI_CHNL: + if (test_bit(ICE_FLAG_RSS_ENA, pf->flags)) { + ice_vsi_cfg_rss_lut_key(vsi); + ice_vsi_set_rss_flow_fld(vsi); + } break; default: break; @@ -3244,14 +3399,30 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, bool init_vsi) /* configure VSI nodes based on number of queues and TC's */ for (i = 0; i < vsi->tc_cfg.numtc; i++) { - max_txqs[i] = vsi->alloc_txq; + /* configure VSI nodes based on number of queues and TC's. + * ADQ creates VSIs for each TC/Channel but doesn't + * allocate queues instead it reconfigures the PF queues + * as per the TC command. So max_txqs should point to the + * PF Tx queues. + */ + if (vtype == ICE_VSI_CHNL) + max_txqs[i] = pf->num_lan_tx; + else + max_txqs[i] = vsi->alloc_txq; if (ice_is_xdp_ena_vsi(vsi)) max_txqs[i] += vsi->num_xdp_txq; } - status = ice_cfg_vsi_lan(vsi->port_info, vsi->idx, vsi->tc_cfg.ena_tc, - max_txqs); + if (test_bit(ICE_FLAG_TC_MQPRIO, pf->flags)) + /* If MQPRIO is set, means channel code path, hence for main + * VSI's, use TC as 1 + */ + status = ice_cfg_vsi_lan(vsi->port_info, vsi->idx, 1, max_txqs); + else + status = ice_cfg_vsi_lan(vsi->port_info, vsi->idx, + vsi->tc_cfg.ena_tc, max_txqs); + if (status) { dev_err(ice_pf_to_dev(pf), "VSI %d failed lan queue config, error %s\n", vsi->vsi_num, ice_stat_str(status)); @@ -3323,7 +3494,6 @@ int ice_wait_for_reset(struct ice_pf *pf, unsigned long timeout) return 0; } -#ifdef CONFIG_DCB /** * ice_vsi_update_q_map - update our copy of the VSI info with new queue map * @vsi: VSI being configured @@ -3338,6 +3508,146 @@ static void ice_vsi_update_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctx) sizeof(vsi->info.tc_mapping)); } +/** + * ice_vsi_cfg_netdev_tc - Setup the netdev TC configuration + * @vsi: the VSI being configured + * @ena_tc: TC map to be enabled + */ +void ice_vsi_cfg_netdev_tc(struct ice_vsi *vsi, u8 ena_tc) +{ + struct net_device *netdev = vsi->netdev; + struct ice_pf *pf = vsi->back; + int numtc = vsi->tc_cfg.numtc; + struct ice_dcbx_cfg *dcbcfg; + u8 netdev_tc; + int i; + + if (!netdev) + return; + + /* CHNL VSI doesn't have it's own netdev, hence, no netdev_tc */ + if (vsi->type == ICE_VSI_CHNL) + return; + + if (!ena_tc) { + netdev_reset_tc(netdev); + return; + } + + if (vsi->type == ICE_VSI_PF && ice_is_adq_active(pf)) + numtc = vsi->all_numtc; + + if (netdev_set_num_tc(netdev, numtc)) + return; + + dcbcfg = &pf->hw.port_info->qos_cfg.local_dcbx_cfg; + + ice_for_each_traffic_class(i) + if (vsi->tc_cfg.ena_tc & BIT(i)) + netdev_set_tc_queue(netdev, + vsi->tc_cfg.tc_info[i].netdev_tc, + vsi->tc_cfg.tc_info[i].qcount_tx, + vsi->tc_cfg.tc_info[i].qoffset); + /* setup TC queue map for CHNL TCs */ + ice_for_each_chnl_tc(i) { + if (!(vsi->all_enatc & BIT(i))) + break; + if (!vsi->mqprio_qopt.qopt.count[i]) + break; + netdev_set_tc_queue(netdev, i, + vsi->mqprio_qopt.qopt.count[i], + vsi->mqprio_qopt.qopt.offset[i]); + } + + if (test_bit(ICE_FLAG_TC_MQPRIO, pf->flags)) + return; + + for (i = 0; i < ICE_MAX_USER_PRIORITY; i++) { + u8 ets_tc = dcbcfg->etscfg.prio_table[i]; + + /* Get the mapped netdev TC# for the UP */ + netdev_tc = vsi->tc_cfg.tc_info[ets_tc].netdev_tc; + netdev_set_prio_tc_map(netdev, i, netdev_tc); + } +} + +/** + * ice_vsi_setup_q_map_mqprio - Prepares mqprio based tc_config + * @vsi: the VSI being configured, + * @ctxt: VSI context structure + * @ena_tc: number of traffic classes to enable + * + * Prepares VSI tc_config to have queue configurations based on MQPRIO options. + */ +static void +ice_vsi_setup_q_map_mqprio(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt, + u8 ena_tc) +{ + u16 pow, offset = 0, qcount_tx = 0, qcount_rx = 0, qmap; + u16 tc0_offset = vsi->mqprio_qopt.qopt.offset[0]; + int tc0_qcount = vsi->mqprio_qopt.qopt.count[0]; + u8 netdev_tc = 0; + int i; + + vsi->tc_cfg.ena_tc = ena_tc ? ena_tc : 1; + + pow = order_base_2(tc0_qcount); + qmap = ((tc0_offset << ICE_AQ_VSI_TC_Q_OFFSET_S) & + ICE_AQ_VSI_TC_Q_OFFSET_M) | + ((pow << ICE_AQ_VSI_TC_Q_NUM_S) & ICE_AQ_VSI_TC_Q_NUM_M); + + ice_for_each_traffic_class(i) { + if (!(vsi->tc_cfg.ena_tc & BIT(i))) { + /* TC is not enabled */ + vsi->tc_cfg.tc_info[i].qoffset = 0; + vsi->tc_cfg.tc_info[i].qcount_rx = 1; + vsi->tc_cfg.tc_info[i].qcount_tx = 1; + vsi->tc_cfg.tc_info[i].netdev_tc = 0; + ctxt->info.tc_mapping[i] = 0; + continue; + } + + offset = vsi->mqprio_qopt.qopt.offset[i]; + qcount_rx = vsi->mqprio_qopt.qopt.count[i]; + qcount_tx = vsi->mqprio_qopt.qopt.count[i]; + vsi->tc_cfg.tc_info[i].qoffset = offset; + vsi->tc_cfg.tc_info[i].qcount_rx = qcount_rx; + vsi->tc_cfg.tc_info[i].qcount_tx = qcount_tx; + vsi->tc_cfg.tc_info[i].netdev_tc = netdev_tc++; + } + + if (vsi->all_numtc && vsi->all_numtc != vsi->tc_cfg.numtc) { + ice_for_each_chnl_tc(i) { + if (!(vsi->all_enatc & BIT(i))) + continue; + offset = vsi->mqprio_qopt.qopt.offset[i]; + qcount_rx = vsi->mqprio_qopt.qopt.count[i]; + qcount_tx = vsi->mqprio_qopt.qopt.count[i]; + } + } + + /* Set actual Tx/Rx queue pairs */ + vsi->num_txq = offset + qcount_tx; + vsi->num_rxq = offset + qcount_rx; + + /* Setup queue TC[0].qmap for given VSI context */ + ctxt->info.tc_mapping[0] = cpu_to_le16(qmap); + ctxt->info.q_mapping[0] = cpu_to_le16(vsi->rxq_map[0]); + ctxt->info.q_mapping[1] = cpu_to_le16(tc0_qcount); + + /* Find queue count available for channel VSIs and starting offset + * for channel VSIs + */ + if (tc0_qcount && tc0_qcount < vsi->num_rxq) { + vsi->cnt_q_avail = vsi->num_rxq - tc0_qcount; + vsi->next_base_q = tc0_qcount; + } + dev_dbg(ice_pf_to_dev(vsi->back), "vsi->num_txq = %d\n", vsi->num_txq); + dev_dbg(ice_pf_to_dev(vsi->back), "vsi->num_rxq = %d\n", vsi->num_rxq); + dev_dbg(ice_pf_to_dev(vsi->back), "all_numtc %u, all_enatc: 0x%04x, tc_cfg.numtc %u\n", + vsi->all_numtc, vsi->all_enatc, vsi->tc_cfg.numtc); +} + /** * ice_vsi_cfg_tc - Configure VSI Tx Sched for given TC map * @vsi: VSI to be configured @@ -3356,6 +3666,9 @@ int ice_vsi_cfg_tc(struct ice_vsi *vsi, u8 ena_tc) u8 num_tc = 0; dev = ice_pf_to_dev(pf); + if (vsi->tc_cfg.ena_tc == ena_tc && + vsi->mqprio_qopt.mode != TC_MQPRIO_MODE_CHANNEL) + return ret; ice_for_each_traffic_class(i) { /* build bitmap of enabled TCs */ @@ -3363,6 +3676,12 @@ int ice_vsi_cfg_tc(struct ice_vsi *vsi, u8 ena_tc) num_tc++; /* populate max_txqs per TC */ max_txqs[i] = vsi->alloc_txq; + /* Update max_txqs if it is CHNL VSI, because alloc_t[r]xq are + * zero for CHNL VSI, hence use num_txq instead as max_txqs + */ + if (vsi->type == ICE_VSI_CHNL && + test_bit(ICE_FLAG_TC_MQPRIO, pf->flags)) + max_txqs[i] = vsi->num_txq; } vsi->tc_cfg.ena_tc = ena_tc; @@ -3375,7 +3694,11 @@ int ice_vsi_cfg_tc(struct ice_vsi *vsi, u8 ena_tc) ctx->vf_num = 0; ctx->info = vsi->info; - ice_vsi_setup_q_map(vsi, ctx); + if (vsi->type == ICE_VSI_PF && + test_bit(ICE_FLAG_TC_MQPRIO, pf->flags)) + ice_vsi_setup_q_map_mqprio(vsi, ctx, ena_tc); + else + ice_vsi_setup_q_map(vsi, ctx); /* must to indicate which section of VSI context are being modified */ ctx->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_RXQ_MAP_VALID); @@ -3386,8 +3709,13 @@ int ice_vsi_cfg_tc(struct ice_vsi *vsi, u8 ena_tc) goto out; } - status = ice_cfg_vsi_lan(vsi->port_info, vsi->idx, vsi->tc_cfg.ena_tc, - max_txqs); + if (vsi->type == ICE_VSI_PF && + test_bit(ICE_FLAG_TC_MQPRIO, pf->flags)) + status = ice_cfg_vsi_lan(vsi->port_info, vsi->idx, 1, + max_txqs); + else + status = ice_cfg_vsi_lan(vsi->port_info, vsi->idx, + vsi->tc_cfg.ena_tc, max_txqs); if (status) { dev_err(dev, "VSI %d failed TC config, error %s\n", @@ -3403,20 +3731,19 @@ out: kfree(ctx); return ret; } -#endif /* CONFIG_DCB */ /** * ice_update_ring_stats - Update ring statistics - * @ring: ring to update + * @stats: stats to be updated * @pkts: number of processed packets * @bytes: number of processed bytes * * This function assumes that caller has acquired a u64_stats_sync lock. */ -static void ice_update_ring_stats(struct ice_ring *ring, u64 pkts, u64 bytes) +static void ice_update_ring_stats(struct ice_q_stats *stats, u64 pkts, u64 bytes) { - ring->stats.bytes += bytes; - ring->stats.pkts += pkts; + stats->bytes += bytes; + stats->pkts += pkts; } /** @@ -3425,10 +3752,10 @@ static void ice_update_ring_stats(struct ice_ring *ring, u64 pkts, u64 bytes) * @pkts: number of processed packets * @bytes: number of processed bytes */ -void ice_update_tx_ring_stats(struct ice_ring *tx_ring, u64 pkts, u64 bytes) +void ice_update_tx_ring_stats(struct ice_tx_ring *tx_ring, u64 pkts, u64 bytes) { u64_stats_update_begin(&tx_ring->syncp); - ice_update_ring_stats(tx_ring, pkts, bytes); + ice_update_ring_stats(&tx_ring->stats, pkts, bytes); u64_stats_update_end(&tx_ring->syncp); } @@ -3438,10 +3765,10 @@ void ice_update_tx_ring_stats(struct ice_ring *tx_ring, u64 pkts, u64 bytes) * @pkts: number of processed packets * @bytes: number of processed bytes */ -void ice_update_rx_ring_stats(struct ice_ring *rx_ring, u64 pkts, u64 bytes) +void ice_update_rx_ring_stats(struct ice_rx_ring *rx_ring, u64 pkts, u64 bytes) { u64_stats_update_begin(&rx_ring->syncp); - ice_update_ring_stats(rx_ring, pkts, bytes); + ice_update_ring_stats(&rx_ring->stats, pkts, bytes); u64_stats_update_end(&rx_ring->syncp); } @@ -3593,6 +3920,180 @@ int ice_clear_dflt_vsi(struct ice_sw *sw) return 0; } +/** + * ice_get_link_speed_mbps - get link speed in Mbps + * @vsi: the VSI whose link speed is being queried + * + * Return current VSI link speed and 0 if the speed is unknown. + */ +int ice_get_link_speed_mbps(struct ice_vsi *vsi) +{ + switch (vsi->port_info->phy.link_info.link_speed) { + case ICE_AQ_LINK_SPEED_100GB: + return SPEED_100000; + case ICE_AQ_LINK_SPEED_50GB: + return SPEED_50000; + case ICE_AQ_LINK_SPEED_40GB: + return SPEED_40000; + case ICE_AQ_LINK_SPEED_25GB: + return SPEED_25000; + case ICE_AQ_LINK_SPEED_20GB: + return SPEED_20000; + case ICE_AQ_LINK_SPEED_10GB: + return SPEED_10000; + case ICE_AQ_LINK_SPEED_5GB: + return SPEED_5000; + case ICE_AQ_LINK_SPEED_2500MB: + return SPEED_2500; + case ICE_AQ_LINK_SPEED_1000MB: + return SPEED_1000; + case ICE_AQ_LINK_SPEED_100MB: + return SPEED_100; + case ICE_AQ_LINK_SPEED_10MB: + return SPEED_10; + case ICE_AQ_LINK_SPEED_UNKNOWN: + default: + return 0; + } +} + +/** + * ice_get_link_speed_kbps - get link speed in Kbps + * @vsi: the VSI whose link speed is being queried + * + * Return current VSI link speed and 0 if the speed is unknown. + */ +int ice_get_link_speed_kbps(struct ice_vsi *vsi) +{ + int speed_mbps; + + speed_mbps = ice_get_link_speed_mbps(vsi); + + return speed_mbps * 1000; +} + +/** + * ice_set_min_bw_limit - setup minimum BW limit for Tx based on min_tx_rate + * @vsi: VSI to be configured + * @min_tx_rate: min Tx rate in Kbps to be configured as BW limit + * + * If the min_tx_rate is specified as 0 that means to clear the minimum BW limit + * profile, otherwise a non-zero value will force a minimum BW limit for the VSI + * on TC 0. + */ +int ice_set_min_bw_limit(struct ice_vsi *vsi, u64 min_tx_rate) +{ + struct ice_pf *pf = vsi->back; + enum ice_status status; + struct device *dev; + int speed; + + dev = ice_pf_to_dev(pf); + if (!vsi->port_info) { + dev_dbg(dev, "VSI %d, type %u specified doesn't have valid port_info\n", + vsi->idx, vsi->type); + return -EINVAL; + } + + speed = ice_get_link_speed_kbps(vsi); + if (min_tx_rate > (u64)speed) { + dev_err(dev, "invalid min Tx rate %llu Kbps specified for %s %d is greater than current link speed %u Kbps\n", + min_tx_rate, ice_vsi_type_str(vsi->type), vsi->idx, + speed); + return -EINVAL; + } + + /* Configure min BW for VSI limit */ + if (min_tx_rate) { + status = ice_cfg_vsi_bw_lmt_per_tc(vsi->port_info, vsi->idx, 0, + ICE_MIN_BW, min_tx_rate); + if (status) { + dev_err(dev, "failed to set min Tx rate(%llu Kbps) for %s %d\n", + min_tx_rate, ice_vsi_type_str(vsi->type), + vsi->idx); + return -EIO; + } + + dev_dbg(dev, "set min Tx rate(%llu Kbps) for %s\n", + min_tx_rate, ice_vsi_type_str(vsi->type)); + } else { + status = ice_cfg_vsi_bw_dflt_lmt_per_tc(vsi->port_info, + vsi->idx, 0, + ICE_MIN_BW); + if (status) { + dev_err(dev, "failed to clear min Tx rate configuration for %s %d\n", + ice_vsi_type_str(vsi->type), vsi->idx); + return -EIO; + } + + dev_dbg(dev, "cleared min Tx rate configuration for %s %d\n", + ice_vsi_type_str(vsi->type), vsi->idx); + } + + return 0; +} + +/** + * ice_set_max_bw_limit - setup maximum BW limit for Tx based on max_tx_rate + * @vsi: VSI to be configured + * @max_tx_rate: max Tx rate in Kbps to be configured as BW limit + * + * If the max_tx_rate is specified as 0 that means to clear the maximum BW limit + * profile, otherwise a non-zero value will force a maximum BW limit for the VSI + * on TC 0. + */ +int ice_set_max_bw_limit(struct ice_vsi *vsi, u64 max_tx_rate) +{ + struct ice_pf *pf = vsi->back; + enum ice_status status; + struct device *dev; + int speed; + + dev = ice_pf_to_dev(pf); + if (!vsi->port_info) { + dev_dbg(dev, "VSI %d, type %u specified doesn't have valid port_info\n", + vsi->idx, vsi->type); + return -EINVAL; + } + + speed = ice_get_link_speed_kbps(vsi); + if (max_tx_rate > (u64)speed) { + dev_err(dev, "invalid max Tx rate %llu Kbps specified for %s %d is greater than current link speed %u Kbps\n", + max_tx_rate, ice_vsi_type_str(vsi->type), vsi->idx, + speed); + return -EINVAL; + } + + /* Configure max BW for VSI limit */ + if (max_tx_rate) { + status = ice_cfg_vsi_bw_lmt_per_tc(vsi->port_info, vsi->idx, 0, + ICE_MAX_BW, max_tx_rate); + if (status) { + dev_err(dev, "failed setting max Tx rate(%llu Kbps) for %s %d\n", + max_tx_rate, ice_vsi_type_str(vsi->type), + vsi->idx); + return -EIO; + } + + dev_dbg(dev, "set max Tx rate(%llu Kbps) for %s %d\n", + max_tx_rate, ice_vsi_type_str(vsi->type), vsi->idx); + } else { + status = ice_cfg_vsi_bw_dflt_lmt_per_tc(vsi->port_info, + vsi->idx, 0, + ICE_MAX_BW); + if (status) { + dev_err(dev, "failed clearing max Tx rate configuration for %s %d\n", + ice_vsi_type_str(vsi->type), vsi->idx); + return -EIO; + } + + dev_dbg(dev, "cleared max Tx rate configuration for %s %d\n", + ice_vsi_type_str(vsi->type), vsi->idx); + } + + return 0; +} + /** * ice_set_link - turn on/off physical link * @vsi: VSI to modify physical link on @@ -3658,6 +4159,19 @@ static void ice_set_feature_support(struct ice_pf *pf, enum ice_feature f) set_bit(f, pf->features); } +/** + * ice_clear_feature_support + * @pf: pointer to the struct ice_pf instance + * @f: feature enum to clear + */ +void ice_clear_feature_support(struct ice_pf *pf, enum ice_feature f) +{ + if (f < 0 || f >= ICE_F_MAX) + return; + + clear_bit(f, pf->features); +} + /** * ice_init_feature_support * @pf: pointer to the struct ice_pf instance @@ -3671,6 +4185,8 @@ void ice_init_feature_support(struct ice_pf *pf) case ICE_DEV_ID_E810C_QSFP: case ICE_DEV_ID_E810C_SFP: ice_set_feature_support(pf, ICE_F_DSCP); + if (ice_is_e810t(&pf->hw)) + ice_set_feature_support(pf, ICE_F_SMA_CTRL); break; default: break; diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h index 3f3fef6551c0..e7f4ecbb8549 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_lib.h @@ -14,7 +14,7 @@ void ice_update_eth_stats(struct ice_vsi *vsi); int ice_vsi_cfg_single_rxq(struct ice_vsi *vsi, u16 q_idx); -int ice_vsi_cfg_single_txq(struct ice_vsi *vsi, struct ice_ring **tx_rings, u16 q_idx); +int ice_vsi_cfg_single_txq(struct ice_vsi *vsi, struct ice_tx_ring **tx_rings, u16 q_idx); int ice_vsi_cfg_rxqs(struct ice_vsi *vsi); @@ -51,13 +51,18 @@ void ice_cfg_sw_lldp(struct ice_vsi *vsi, bool tx, bool create); int ice_set_link(struct ice_vsi *vsi, bool ena); -#ifdef CONFIG_DCB +void ice_vsi_delete(struct ice_vsi *vsi); +int ice_vsi_clear(struct ice_vsi *vsi); + int ice_vsi_cfg_tc(struct ice_vsi *vsi, u8 ena_tc); -#endif /* CONFIG_DCB */ + +int ice_vsi_cfg_rss_lut_key(struct ice_vsi *vsi); + +void ice_vsi_cfg_netdev_tc(struct ice_vsi *vsi, u8 ena_tc); struct ice_vsi * ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, - enum ice_vsi_type vsi_type, u16 vf_id); + enum ice_vsi_type vsi_type, u16 vf_id, struct ice_channel *ch); void ice_napi_del(struct ice_vsi *vsi); @@ -93,9 +98,9 @@ void ice_vsi_free_tx_rings(struct ice_vsi *vsi); void ice_vsi_manage_rss_lut(struct ice_vsi *vsi, bool ena); -void ice_update_tx_ring_stats(struct ice_ring *ring, u64 pkts, u64 bytes); +void ice_update_tx_ring_stats(struct ice_tx_ring *ring, u64 pkts, u64 bytes); -void ice_update_rx_ring_stats(struct ice_ring *ring, u64 pkts, u64 bytes); +void ice_update_rx_ring_stats(struct ice_rx_ring *ring, u64 pkts, u64 bytes); void ice_vsi_cfg_frame_size(struct ice_vsi *vsi); @@ -103,6 +108,7 @@ int ice_status_to_errno(enum ice_status err); void ice_write_intrl(struct ice_q_vector *q_vector, u8 intrl); void ice_write_itr(struct ice_ring_container *rc, u16 itr); +void ice_set_q_vector_intrl(struct ice_q_vector *q_vector); enum ice_status ice_vsi_cfg_mac_fltr(struct ice_vsi *vsi, const u8 *macaddr, bool set); @@ -116,7 +122,10 @@ bool ice_is_vsi_dflt_vsi(struct ice_sw *sw, struct ice_vsi *vsi); int ice_set_dflt_vsi(struct ice_sw *sw, struct ice_vsi *vsi); int ice_clear_dflt_vsi(struct ice_sw *sw); - +int ice_set_min_bw_limit(struct ice_vsi *vsi, u64 min_tx_rate); +int ice_set_max_bw_limit(struct ice_vsi *vsi, u64 max_tx_rate); +int ice_get_link_speed_kbps(struct ice_vsi *vsi); +int ice_get_link_speed_mbps(struct ice_vsi *vsi); int ice_vsi_update_security(struct ice_vsi *vsi, void (*fill)(struct ice_vsi_ctx *)); @@ -129,5 +138,6 @@ void ice_vsi_ctx_set_allow_override(struct ice_vsi_ctx *ctx); void ice_vsi_ctx_clear_allow_override(struct ice_vsi_ctx *ctx); bool ice_is_feature_supported(struct ice_pf *pf, enum ice_feature f); +void ice_clear_feature_support(struct ice_pf *pf, enum ice_feature f); void ice_init_feature_support(struct ice_pf *pf); #endif /* !_ICE_LIB_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 63ed5564d792..9ba22778011d 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -20,6 +20,7 @@ #define CREATE_TRACE_POINTS #include "ice_trace.h" #include "ice_eswitch.h" +#include "ice_tc_lib.h" #define DRV_SUMMARY "Intel(R) Ethernet Connection E800 Series Linux Driver" static const char ice_driver_string[] = DRV_SUMMARY; @@ -43,6 +44,8 @@ MODULE_PARM_DESC(debug, "netif level (0=none,...,16=all)"); #endif /* !CONFIG_DYNAMIC_DEBUG */ static DEFINE_IDA(ice_aux_ida); +DEFINE_STATIC_KEY_FALSE(ice_xdp_locking_key); +EXPORT_SYMBOL(ice_xdp_locking_key); static struct workqueue_struct *ice_wq; static const struct net_device_ops ice_netdev_safe_mode_ops; @@ -52,6 +55,9 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type); static void ice_vsi_release_all(struct ice_pf *pf); +static int ice_rebuild_channels(struct ice_pf *pf); +static void ice_remove_q_channels(struct ice_vsi *vsi, bool rem_adv_fltr); + bool netif_is_ice(struct net_device *dev) { return dev && (dev->netdev_ops == &ice_netdev_ops); @@ -61,7 +67,7 @@ bool netif_is_ice(struct net_device *dev) * ice_get_tx_pending - returns number of Tx descriptors not processed * @ring: the ring of descriptors */ -static u16 ice_get_tx_pending(struct ice_ring *ring) +static u16 ice_get_tx_pending(struct ice_tx_ring *ring) { u16 head, tail; @@ -100,10 +106,15 @@ static void ice_check_for_hang_subtask(struct ice_pf *pf) hw = &vsi->back->hw; - for (i = 0; i < vsi->num_txq; i++) { - struct ice_ring *tx_ring = vsi->tx_rings[i]; + ice_for_each_txq(vsi, i) { + struct ice_tx_ring *tx_ring = vsi->tx_rings[i]; - if (tx_ring && tx_ring->desc) { + if (!tx_ring) + continue; + if (ice_ring_ch_enabled(tx_ring)) + continue; + + if (tx_ring->desc) { /* If packet counter has not changed the queue is * likely stalled, so force an interrupt for this * queue. @@ -455,17 +466,21 @@ static void ice_pf_dis_all_vsi(struct ice_pf *pf, bool locked) } /** - * ice_prepare_for_reset - prep for the core to reset + * ice_prepare_for_reset - prep for reset * @pf: board private structure + * @reset_type: reset type requested * * Inform or close all dependent features in prep for reset. */ static void -ice_prepare_for_reset(struct ice_pf *pf) +ice_prepare_for_reset(struct ice_pf *pf, enum ice_reset_req reset_type) { struct ice_hw *hw = &pf->hw; + struct ice_vsi *vsi; unsigned int i; + dev_dbg(ice_pf_to_dev(pf), "reset_type=%d\n", reset_type); + /* already prepared for reset */ if (test_bit(ICE_PREPARED_FOR_RESET, pf->state)) return; @@ -480,6 +495,38 @@ ice_prepare_for_reset(struct ice_pf *pf) ice_for_each_vf(pf, i) ice_set_vf_state_qs_dis(&pf->vf[i]); + /* release ADQ specific HW and SW resources */ + vsi = ice_get_main_vsi(pf); + if (!vsi) + goto skip; + + /* to be on safe side, reset orig_rss_size so that normal flow + * of deciding rss_size can take precedence + */ + vsi->orig_rss_size = 0; + + if (test_bit(ICE_FLAG_TC_MQPRIO, pf->flags)) { + if (reset_type == ICE_RESET_PFR) { + vsi->old_ena_tc = vsi->all_enatc; + vsi->old_numtc = vsi->all_numtc; + } else { + ice_remove_q_channels(vsi, true); + + /* for other reset type, do not support channel rebuild + * hence reset needed info + */ + vsi->old_ena_tc = 0; + vsi->all_enatc = 0; + vsi->old_numtc = 0; + vsi->all_numtc = 0; + vsi->req_txq = 0; + vsi->req_rxq = 0; + clear_bit(ICE_FLAG_TC_MQPRIO, pf->flags); + memset(&vsi->mqprio_qopt, 0, sizeof(vsi->mqprio_qopt)); + } + } +skip: + /* clear SW filtering DB */ ice_clear_hw_tbls(hw); /* disable the VSIs and their queues that are not already DOWN */ @@ -499,8 +546,7 @@ ice_prepare_for_reset(struct ice_pf *pf) /** * ice_do_reset - Initiate one of many types of resets * @pf: board private structure - * @reset_type: reset type requested - * before this function was called. + * @reset_type: reset type requested before this function was called. */ static void ice_do_reset(struct ice_pf *pf, enum ice_reset_req reset_type) { @@ -509,7 +555,7 @@ static void ice_do_reset(struct ice_pf *pf, enum ice_reset_req reset_type) dev_dbg(dev, "reset_type 0x%x requested\n", reset_type); - ice_prepare_for_reset(pf); + ice_prepare_for_reset(pf, reset_type); /* trigger the reset */ if (ice_reset(hw, reset_type)) { @@ -567,7 +613,7 @@ static void ice_reset_subtask(struct ice_pf *pf) /* return if no valid reset type requested */ if (reset_type == ICE_RESET_INVAL) return; - ice_prepare_for_reset(pf); + ice_prepare_for_reset(pf, reset_type); /* make sure we are ready to rebuild */ if (ice_check_reset(&pf->hw)) { @@ -2306,14 +2352,14 @@ static int ice_vsi_req_irq_msix(struct ice_vsi *vsi, char *basename) irq_num = pf->msix_entries[base + vector].vector; - if (q_vector->tx.ring && q_vector->rx.ring) { + if (q_vector->tx.tx_ring && q_vector->rx.rx_ring) { snprintf(q_vector->name, sizeof(q_vector->name) - 1, "%s-%s-%d", basename, "TxRx", rx_int_idx++); tx_int_idx++; - } else if (q_vector->rx.ring) { + } else if (q_vector->rx.rx_ring) { snprintf(q_vector->name, sizeof(q_vector->name) - 1, "%s-%s-%d", basename, "rx", rx_int_idx++); - } else if (q_vector->tx.ring) { + } else if (q_vector->tx.tx_ring) { snprintf(q_vector->name, sizeof(q_vector->name) - 1, "%s-%s-%d", basename, "tx", tx_int_idx++); } else { @@ -2371,11 +2417,12 @@ free_q_irqs: static int ice_xdp_alloc_setup_rings(struct ice_vsi *vsi) { struct device *dev = ice_pf_to_dev(vsi->back); - int i; + struct ice_tx_desc *tx_desc; + int i, j; - for (i = 0; i < vsi->num_xdp_txq; i++) { + ice_for_each_xdp_txq(vsi, i) { u16 xdp_q_idx = vsi->alloc_txq + i; - struct ice_ring *xdp_ring; + struct ice_tx_ring *xdp_ring; xdp_ring = kzalloc(sizeof(*xdp_ring), GFP_KERNEL); @@ -2384,16 +2431,29 @@ static int ice_xdp_alloc_setup_rings(struct ice_vsi *vsi) xdp_ring->q_index = xdp_q_idx; xdp_ring->reg_idx = vsi->txq_map[xdp_q_idx]; - xdp_ring->ring_active = false; xdp_ring->vsi = vsi; xdp_ring->netdev = NULL; + xdp_ring->next_dd = ICE_TX_THRESH - 1; + xdp_ring->next_rs = ICE_TX_THRESH - 1; xdp_ring->dev = dev; xdp_ring->count = vsi->num_tx_desc; WRITE_ONCE(vsi->xdp_rings[i], xdp_ring); if (ice_setup_tx_ring(xdp_ring)) goto free_xdp_rings; ice_set_ring_xdp(xdp_ring); - xdp_ring->xsk_pool = ice_xsk_pool(xdp_ring); + xdp_ring->xsk_pool = ice_tx_xsk_pool(xdp_ring); + spin_lock_init(&xdp_ring->tx_lock); + for (j = 0; j < xdp_ring->count; j++) { + tx_desc = ICE_TX_DESC(xdp_ring, j); + tx_desc->cmd_type_offset_bsz = cpu_to_le64(ICE_TX_DESC_DTYPE_DESC_DONE); + } + } + + ice_for_each_rxq(vsi, i) { + if (static_key_enabled(&ice_xdp_locking_key)) + vsi->rx_rings[i]->xdp_ring = vsi->xdp_rings[i % vsi->num_xdp_txq]; + else + vsi->rx_rings[i]->xdp_ring = vsi->xdp_rings[i]; } return 0; @@ -2459,6 +2519,10 @@ int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog) if (__ice_vsi_get_qs(&xdp_qs_cfg)) goto err_map_xdp; + if (static_key_enabled(&ice_xdp_locking_key)) + netdev_warn(vsi->netdev, + "Could not allocate one XDP Tx ring per CPU, XDP_TX/XDP_REDIRECT actions will be slower\n"); + if (ice_xdp_alloc_setup_rings(vsi)) goto clear_xdp_rings; @@ -2472,11 +2536,11 @@ int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog) q_base = vsi->num_xdp_txq - xdp_rings_rem; for (q_id = q_base; q_id < (q_base + xdp_rings_per_v); q_id++) { - struct ice_ring *xdp_ring = vsi->xdp_rings[q_id]; + struct ice_tx_ring *xdp_ring = vsi->xdp_rings[q_id]; xdp_ring->q_vector = q_vector; - xdp_ring->next = q_vector->tx.ring; - q_vector->tx.ring = xdp_ring; + xdp_ring->next = q_vector->tx.tx_ring; + q_vector->tx.tx_ring = xdp_ring; } xdp_rings_rem -= xdp_rings_per_v; } @@ -2505,7 +2569,7 @@ int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog) return 0; clear_xdp_rings: - for (i = 0; i < vsi->num_xdp_txq; i++) + ice_for_each_xdp_txq(vsi, i) if (vsi->xdp_rings[i]) { kfree_rcu(vsi->xdp_rings[i], rcu); vsi->xdp_rings[i] = NULL; @@ -2513,7 +2577,7 @@ clear_xdp_rings: err_map_xdp: mutex_lock(&pf->avail_q_mutex); - for (i = 0; i < vsi->num_xdp_txq; i++) { + ice_for_each_xdp_txq(vsi, i) { clear_bit(vsi->txq_map[i + vsi->alloc_txq], pf->avail_txqs); vsi->txq_map[i + vsi->alloc_txq] = ICE_INVAL_Q_INDEX; } @@ -2546,25 +2610,25 @@ int ice_destroy_xdp_rings(struct ice_vsi *vsi) ice_for_each_q_vector(vsi, v_idx) { struct ice_q_vector *q_vector = vsi->q_vectors[v_idx]; - struct ice_ring *ring; + struct ice_tx_ring *ring; - ice_for_each_ring(ring, q_vector->tx) + ice_for_each_tx_ring(ring, q_vector->tx) if (!ring->tx_buf || !ice_ring_is_xdp(ring)) break; /* restore the value of last node prior to XDP setup */ - q_vector->tx.ring = ring; + q_vector->tx.tx_ring = ring; } free_qmap: mutex_lock(&pf->avail_q_mutex); - for (i = 0; i < vsi->num_xdp_txq; i++) { + ice_for_each_xdp_txq(vsi, i) { clear_bit(vsi->txq_map[i + vsi->alloc_txq], pf->avail_txqs); vsi->txq_map[i + vsi->alloc_txq] = ICE_INVAL_Q_INDEX; } mutex_unlock(&pf->avail_q_mutex); - for (i = 0; i < vsi->num_xdp_txq; i++) + ice_for_each_xdp_txq(vsi, i) if (vsi->xdp_rings[i]) { if (vsi->xdp_rings[i]->desc) ice_free_tx_ring(vsi->xdp_rings[i]); @@ -2575,6 +2639,9 @@ free_qmap: devm_kfree(ice_pf_to_dev(pf), vsi->xdp_rings); vsi->xdp_rings = NULL; + if (static_key_enabled(&ice_xdp_locking_key)) + static_branch_dec(&ice_xdp_locking_key); + if (ice_is_reset_in_progress(pf->state) || !vsi->q_vectors[0]) return 0; @@ -2602,13 +2669,36 @@ static void ice_vsi_rx_napi_schedule(struct ice_vsi *vsi) int i; ice_for_each_rxq(vsi, i) { - struct ice_ring *rx_ring = vsi->rx_rings[i]; + struct ice_rx_ring *rx_ring = vsi->rx_rings[i]; if (rx_ring->xsk_pool) napi_schedule(&rx_ring->q_vector->napi); } } +/** + * ice_vsi_determine_xdp_res - figure out how many Tx qs can XDP have + * @vsi: VSI to determine the count of XDP Tx qs + * + * returns 0 if Tx qs count is higher than at least half of CPU count, + * -ENOMEM otherwise + */ +int ice_vsi_determine_xdp_res(struct ice_vsi *vsi) +{ + u16 avail = ice_get_avail_txq_count(vsi->back); + u16 cpus = num_possible_cpus(); + + if (avail < cpus / 2) + return -ENOMEM; + + vsi->num_xdp_txq = min_t(u16, avail, cpus); + + if (vsi->num_xdp_txq < cpus) + static_branch_inc(&ice_xdp_locking_key); + + return 0; +} + /** * ice_xdp_setup_prog - Add or remove XDP eBPF program * @vsi: VSI to setup XDP for @@ -2638,10 +2728,14 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog, } if (!ice_is_xdp_ena_vsi(vsi) && prog) { - vsi->num_xdp_txq = vsi->alloc_rxq; - xdp_ring_err = ice_prepare_xdp_rings(vsi, prog); - if (xdp_ring_err) - NL_SET_ERR_MSG_MOD(extack, "Setting up XDP Tx resources failed"); + xdp_ring_err = ice_vsi_determine_xdp_res(vsi); + if (xdp_ring_err) { + NL_SET_ERR_MSG_MOD(extack, "Not enough Tx resources for XDP"); + } else { + xdp_ring_err = ice_prepare_xdp_rings(vsi, prog); + if (xdp_ring_err) + NL_SET_ERR_MSG_MOD(extack, "Setting up XDP Tx resources failed"); + } } else if (ice_is_xdp_ena_vsi(vsi) && !prog) { xdp_ring_err = ice_destroy_xdp_rings(vsi); if (xdp_ring_err) @@ -3107,6 +3201,9 @@ static void ice_set_netdev_features(struct net_device *netdev) /* enable features */ netdev->features |= netdev->hw_features; + + netdev->hw_features |= NETIF_F_HW_TC; + /* encap and VLAN devices inherit default, csumo and tso features */ netdev->hw_enc_features |= dflt_features | csumo_features | tso_features; @@ -3186,7 +3283,14 @@ void ice_fill_rss_lut(u8 *lut, u16 rss_table_size, u16 rss_size) static struct ice_vsi * ice_pf_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi) { - return ice_vsi_setup(pf, pi, ICE_VSI_PF, ICE_INVAL_VFID); + return ice_vsi_setup(pf, pi, ICE_VSI_PF, ICE_INVAL_VFID, NULL); +} + +static struct ice_vsi * +ice_chnl_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, + struct ice_channel *ch) +{ + return ice_vsi_setup(pf, pi, ICE_VSI_CHNL, ICE_INVAL_VFID, ch); } /** @@ -3200,7 +3304,7 @@ ice_pf_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi) static struct ice_vsi * ice_ctrl_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi) { - return ice_vsi_setup(pf, pi, ICE_VSI_CTRL, ICE_INVAL_VFID); + return ice_vsi_setup(pf, pi, ICE_VSI_CTRL, ICE_INVAL_VFID, NULL); } /** @@ -3214,7 +3318,7 @@ ice_ctrl_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi) struct ice_vsi * ice_lb_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi) { - return ice_vsi_setup(pf, pi, ICE_VSI_LB, ICE_INVAL_VFID); + return ice_vsi_setup(pf, pi, ICE_VSI_LB, ICE_INVAL_VFID, NULL); } /** @@ -3307,6 +3411,9 @@ static int ice_setup_pf_sw(struct ice_pf *pf) if (!vsi) return -ENOMEM; + /* init channel list */ + INIT_LIST_HEAD(&vsi->ch_list); + status = ice_cfg_netdev(vsi); if (status) { status = -ENODEV; @@ -4906,7 +5013,7 @@ ice_pci_err_detected(struct pci_dev *pdev, pci_channel_state_t err) if (!test_bit(ICE_PREPARED_FOR_RESET, pf->state)) { set_bit(ICE_PFR_REQ, pf->state); - ice_prepare_for_reset(pf); + ice_prepare_for_reset(pf, ICE_RESET_PFR); } } @@ -4998,7 +5105,7 @@ static void ice_pci_err_reset_prepare(struct pci_dev *pdev) if (!test_bit(ICE_PREPARED_FOR_RESET, pf->state)) { set_bit(ICE_PFR_REQ, pf->state); - ice_prepare_for_reset(pf); + ice_prepare_for_reset(pf, ICE_RESET_PFR); } } } @@ -5154,6 +5261,12 @@ static int ice_set_mac_address(struct net_device *netdev, void *pi) return -EBUSY; } + if (ice_chnl_dmac_fltr_cnt(pf)) { + netdev_err(netdev, "can't set mac %pM. Device has tc-flower filters, delete all of them and try again\n", + mac); + return -EAGAIN; + } + netif_addr_lock_bh(netdev); ether_addr_copy(old_mac, netdev->dev_addr); /* change the netdev's MAC address */ @@ -5405,6 +5518,18 @@ ice_set_features(struct net_device *netdev, netdev_features_t features) ice_clear_arfs(vsi); } + /* don't turn off hw_tc_offload when ADQ is already enabled */ + if (!(features & NETIF_F_HW_TC) && ice_is_adq_active(pf)) { + dev_err(ice_pf_to_dev(pf), "ADQ is active, can't turn hw_tc_offload off\n"); + return -EACCES; + } + + if ((features & NETIF_F_HW_TC) && + !(netdev->features & NETIF_F_HW_TC)) + set_bit(ICE_FLAG_CLS_FLOWER, pf->flags); + else + clear_bit(ICE_FLAG_CLS_FLOWER, pf->flags); + return ret; } @@ -5454,77 +5579,59 @@ int ice_vsi_cfg(struct ice_vsi *vsi) } /* THEORY OF MODERATION: - * The below code creates custom DIM profiles for use by this driver, because - * the ice driver hardware works differently than the hardware that DIMLIB was + * The ice driver hardware works differently than the hardware that DIMLIB was * originally made for. ice hardware doesn't have packet count limits that * can trigger an interrupt, but it *does* have interrupt rate limit support, - * and this code adds that capability to be used by the driver when it's using - * DIMLIB. The DIMLIB code was always designed to be a suggestion to the driver - * for how to "respond" to traffic and interrupts, so this driver uses a - * slightly different set of moderation parameters to get best performance. + * which is hard-coded to a limit of 250,000 ints/second. + * If not using dynamic moderation, the INTRL value can be modified + * by ethtool rx-usecs-high. */ struct ice_dim { /* the throttle rate for interrupts, basically worst case delay before * an initial interrupt fires, value is stored in microseconds. */ u16 itr; - /* the rate limit for interrupts, which can cap a delay from a small - * ITR at a certain amount of interrupts per second. f.e. a 2us ITR - * could yield as much as 500,000 interrupts per second, but with a - * 10us rate limit, it limits to 100,000 interrupts per second. Value - * is stored in microseconds. - */ - u16 intrl; }; /* Make a different profile for Rx that doesn't allow quite so aggressive - * moderation at the high end (it maxes out at 128us or about 8k interrupts a - * second. The INTRL/rate parameters here are only useful to cap small ITR - * values, which is why for larger ITR's - like 128, which can only generate - * 8k interrupts per second, there is no point to rate limit and the values - * are set to zero. The rate limit values do affect latency, and so must - * be reasonably small so to not impact latency sensitive tests. + * moderation at the high end (it maxes out at 126us or about 8k interrupts a + * second. */ static const struct ice_dim rx_profile[] = { - {2, 10}, - {8, 16}, - {32, 0}, - {96, 0}, - {128, 0} + {2}, /* 500,000 ints/s, capped at 250K by INTRL */ + {8}, /* 125,000 ints/s */ + {16}, /* 62,500 ints/s */ + {62}, /* 16,129 ints/s */ + {126} /* 7,936 ints/s */ }; /* The transmit profile, which has the same sorts of values * as the previous struct */ static const struct ice_dim tx_profile[] = { - {2, 10}, - {8, 16}, - {64, 0}, - {128, 0}, - {256, 0} + {2}, /* 500,000 ints/s, capped at 250K by INTRL */ + {8}, /* 125,000 ints/s */ + {40}, /* 16,125 ints/s */ + {128}, /* 7,812 ints/s */ + {256} /* 3,906 ints/s */ }; static void ice_tx_dim_work(struct work_struct *work) { struct ice_ring_container *rc; - struct ice_q_vector *q_vector; struct dim *dim; - u16 itr, intrl; + u16 itr; dim = container_of(work, struct dim, work); - rc = container_of(dim, struct ice_ring_container, dim); - q_vector = container_of(rc, struct ice_q_vector, tx); + rc = (struct ice_ring_container *)dim->priv; - if (dim->profile_ix >= ARRAY_SIZE(tx_profile)) - dim->profile_ix = ARRAY_SIZE(tx_profile) - 1; + WARN_ON(dim->profile_ix >= ARRAY_SIZE(tx_profile)); /* look up the values in our local table */ itr = tx_profile[dim->profile_ix].itr; - intrl = tx_profile[dim->profile_ix].intrl; - ice_trace(tx_dim_work, q_vector, dim); + ice_trace(tx_dim_work, container_of(rc, struct ice_q_vector, tx), dim); ice_write_itr(rc, itr); - ice_write_intrl(q_vector, intrl); dim->state = DIM_START_MEASURE; } @@ -5532,28 +5639,65 @@ static void ice_tx_dim_work(struct work_struct *work) static void ice_rx_dim_work(struct work_struct *work) { struct ice_ring_container *rc; - struct ice_q_vector *q_vector; struct dim *dim; - u16 itr, intrl; + u16 itr; dim = container_of(work, struct dim, work); - rc = container_of(dim, struct ice_ring_container, dim); - q_vector = container_of(rc, struct ice_q_vector, rx); + rc = (struct ice_ring_container *)dim->priv; - if (dim->profile_ix >= ARRAY_SIZE(rx_profile)) - dim->profile_ix = ARRAY_SIZE(rx_profile) - 1; + WARN_ON(dim->profile_ix >= ARRAY_SIZE(rx_profile)); /* look up the values in our local table */ itr = rx_profile[dim->profile_ix].itr; - intrl = rx_profile[dim->profile_ix].intrl; - ice_trace(rx_dim_work, q_vector, dim); + ice_trace(rx_dim_work, container_of(rc, struct ice_q_vector, rx), dim); ice_write_itr(rc, itr); - ice_write_intrl(q_vector, intrl); dim->state = DIM_START_MEASURE; } +#define ICE_DIM_DEFAULT_PROFILE_IX 1 + +/** + * ice_init_moderation - set up interrupt moderation + * @q_vector: the vector containing rings to be configured + * + * Set up interrupt moderation registers, with the intent to do the right thing + * when called from reset or from probe, and whether or not dynamic moderation + * is enabled or not. Take special care to write all the registers in both + * dynamic moderation mode or not in order to make sure hardware is in a known + * state. + */ +static void ice_init_moderation(struct ice_q_vector *q_vector) +{ + struct ice_ring_container *rc; + bool tx_dynamic, rx_dynamic; + + rc = &q_vector->tx; + INIT_WORK(&rc->dim.work, ice_tx_dim_work); + rc->dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_EQE; + rc->dim.profile_ix = ICE_DIM_DEFAULT_PROFILE_IX; + rc->dim.priv = rc; + tx_dynamic = ITR_IS_DYNAMIC(rc); + + /* set the initial TX ITR to match the above */ + ice_write_itr(rc, tx_dynamic ? + tx_profile[rc->dim.profile_ix].itr : rc->itr_setting); + + rc = &q_vector->rx; + INIT_WORK(&rc->dim.work, ice_rx_dim_work); + rc->dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_EQE; + rc->dim.profile_ix = ICE_DIM_DEFAULT_PROFILE_IX; + rc->dim.priv = rc; + rx_dynamic = ITR_IS_DYNAMIC(rc); + + /* set the initial RX ITR to match the above */ + ice_write_itr(rc, rx_dynamic ? rx_profile[rc->dim.profile_ix].itr : + rc->itr_setting); + + ice_set_q_vector_intrl(q_vector); +} + /** * ice_napi_enable_all - Enable NAPI for all q_vectors in the VSI * @vsi: the VSI being configured @@ -5568,13 +5712,9 @@ static void ice_napi_enable_all(struct ice_vsi *vsi) ice_for_each_q_vector(vsi, q_idx) { struct ice_q_vector *q_vector = vsi->q_vectors[q_idx]; - INIT_WORK(&q_vector->tx.dim.work, ice_tx_dim_work); - q_vector->tx.dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_EQE; + ice_init_moderation(q_vector); - INIT_WORK(&q_vector->rx.dim.work, ice_rx_dim_work); - q_vector->rx.dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_EQE; - - if (q_vector->rx.ring || q_vector->tx.ring) + if (q_vector->rx.rx_ring || q_vector->tx.tx_ring) napi_enable(&q_vector->napi); } } @@ -5634,7 +5774,8 @@ int ice_up(struct ice_vsi *vsi) /** * ice_fetch_u64_stats_per_ring - get packets and bytes stats per ring - * @ring: Tx or Rx ring to read stats from + * @syncp: pointer to u64_stats_sync + * @stats: stats that pkts and bytes count will be taken from * @pkts: packets stats counter * @bytes: bytes stats counter * @@ -5642,19 +5783,16 @@ int ice_up(struct ice_vsi *vsi) * that needs to be performed to read u64 values in 32 bit machine. */ static void -ice_fetch_u64_stats_per_ring(struct ice_ring *ring, u64 *pkts, u64 *bytes) +ice_fetch_u64_stats_per_ring(struct u64_stats_sync *syncp, struct ice_q_stats stats, + u64 *pkts, u64 *bytes) { unsigned int start; - *pkts = 0; - *bytes = 0; - if (!ring) - return; do { - start = u64_stats_fetch_begin_irq(&ring->syncp); - *pkts = ring->stats.pkts; - *bytes = ring->stats.bytes; - } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); + start = u64_stats_fetch_begin_irq(syncp); + *pkts = stats.pkts; + *bytes = stats.bytes; + } while (u64_stats_fetch_retry_irq(syncp, start)); } /** @@ -5664,18 +5802,19 @@ ice_fetch_u64_stats_per_ring(struct ice_ring *ring, u64 *pkts, u64 *bytes) * @count: number of rings */ static void -ice_update_vsi_tx_ring_stats(struct ice_vsi *vsi, struct ice_ring **rings, +ice_update_vsi_tx_ring_stats(struct ice_vsi *vsi, struct ice_tx_ring **rings, u16 count) { struct rtnl_link_stats64 *vsi_stats = &vsi->net_stats; u16 i; for (i = 0; i < count; i++) { - struct ice_ring *ring; - u64 pkts, bytes; + struct ice_tx_ring *ring; + u64 pkts = 0, bytes = 0; ring = READ_ONCE(rings[i]); - ice_fetch_u64_stats_per_ring(ring, &pkts, &bytes); + if (ring) + ice_fetch_u64_stats_per_ring(&ring->syncp, ring->stats, &pkts, &bytes); vsi_stats->tx_packets += pkts; vsi_stats->tx_bytes += bytes; vsi->tx_restart += ring->tx_stats.restart_q; @@ -5714,9 +5853,9 @@ static void ice_update_vsi_ring_stats(struct ice_vsi *vsi) /* update Rx rings counters */ ice_for_each_rxq(vsi, i) { - struct ice_ring *ring = READ_ONCE(vsi->rx_rings[i]); + struct ice_rx_ring *ring = READ_ONCE(vsi->rx_rings[i]); - ice_fetch_u64_stats_per_ring(ring, &pkts, &bytes); + ice_fetch_u64_stats_per_ring(&ring->syncp, ring->stats, &pkts, &bytes); vsi_stats->rx_packets += pkts; vsi_stats->rx_bytes += bytes; vsi->rx_buf_failed += ring->rx_stats.alloc_buf_failed; @@ -5980,7 +6119,7 @@ static void ice_napi_disable_all(struct ice_vsi *vsi) ice_for_each_q_vector(vsi, q_idx) { struct ice_q_vector *q_vector = vsi->q_vectors[q_idx]; - if (q_vector->rx.ring || q_vector->tx.ring) + if (q_vector->rx.rx_ring || q_vector->tx.tx_ring) napi_disable(&q_vector->napi); cancel_work_sync(&q_vector->tx.dim.work); @@ -6065,7 +6204,7 @@ int ice_vsi_setup_tx_rings(struct ice_vsi *vsi) } ice_for_each_txq(vsi, i) { - struct ice_ring *ring = vsi->tx_rings[i]; + struct ice_tx_ring *ring = vsi->tx_rings[i]; if (!ring) return -EINVAL; @@ -6097,7 +6236,7 @@ int ice_vsi_setup_rx_rings(struct ice_vsi *vsi) } ice_for_each_rxq(vsi, i) { - struct ice_ring *ring = vsi->rx_rings[i]; + struct ice_rx_ring *ring = vsi->rx_rings[i]; if (!ring) return -EINVAL; @@ -6245,6 +6384,9 @@ static void ice_vsi_release_all(struct ice_pf *pf) if (!pf->vsi[i]) continue; + if (pf->vsi[i]->type == ICE_VSI_CHNL) + continue; + err = ice_vsi_release(pf->vsi[i]); if (err) dev_dbg(ice_pf_to_dev(pf), "Failed to release pf->vsi[%d], err %d, vsi_num = %d\n", @@ -6455,6 +6597,15 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) goto err_vsi_rebuild; } + if (reset_type == ICE_RESET_PFR) { + err = ice_rebuild_channels(pf); + if (err) { + dev_err(dev, "failed to rebuild and replay ADQ VSIs, err %d\n", + err); + goto err_vsi_rebuild; + } + } + /* If Flow Director is active */ if (test_bit(ICE_FLAG_FD_ENA, pf->flags)) { err = ice_vsi_rebuild_by_type(pf, ICE_VSI_CTRL); @@ -7001,7 +7152,7 @@ ice_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh, static void ice_tx_timeout(struct net_device *netdev, unsigned int txqueue) { struct ice_netdev_priv *np = netdev_priv(netdev); - struct ice_ring *tx_ring = NULL; + struct ice_tx_ring *tx_ring = NULL; struct ice_vsi *vsi = np->vsi; struct ice_pf *pf = vsi->back; u32 i; @@ -7019,7 +7170,7 @@ static void ice_tx_timeout(struct net_device *netdev, unsigned int txqueue) } /* now that we have an index, find the tx_ring struct */ - for (i = 0; i < vsi->num_txq; i++) + ice_for_each_txq(vsi, i) if (vsi->tx_rings[i] && vsi->tx_rings[i]->desc) if (txqueue == vsi->tx_rings[i]->q_index) { tx_ring = vsi->tx_rings[i]; @@ -7075,6 +7226,935 @@ static void ice_tx_timeout(struct net_device *netdev, unsigned int txqueue) pf->tx_timeout_recovery_level++; } +/** + * ice_setup_tc_cls_flower - flower classifier offloads + * @np: net device to configure + * @filter_dev: device on which filter is added + * @cls_flower: offload data + */ +static int +ice_setup_tc_cls_flower(struct ice_netdev_priv *np, + struct net_device *filter_dev, + struct flow_cls_offload *cls_flower) +{ + struct ice_vsi *vsi = np->vsi; + + if (cls_flower->common.chain_index) + return -EOPNOTSUPP; + + switch (cls_flower->command) { + case FLOW_CLS_REPLACE: + return ice_add_cls_flower(filter_dev, vsi, cls_flower); + case FLOW_CLS_DESTROY: + return ice_del_cls_flower(vsi, cls_flower); + default: + return -EINVAL; + } +} + +/** + * ice_setup_tc_block_cb - callback handler registered for TC block + * @type: TC SETUP type + * @type_data: TC flower offload data that contains user input + * @cb_priv: netdev private data + */ +static int +ice_setup_tc_block_cb(enum tc_setup_type type, void *type_data, void *cb_priv) +{ + struct ice_netdev_priv *np = cb_priv; + + switch (type) { + case TC_SETUP_CLSFLOWER: + return ice_setup_tc_cls_flower(np, np->vsi->netdev, + type_data); + default: + return -EOPNOTSUPP; + } +} + +/** + * ice_validate_mqprio_qopt - Validate TCF input parameters + * @vsi: Pointer to VSI + * @mqprio_qopt: input parameters for mqprio queue configuration + * + * This function validates MQPRIO params, such as qcount (power of 2 wherever + * needed), and make sure user doesn't specify qcount and BW rate limit + * for TCs, which are more than "num_tc" + */ +static int +ice_validate_mqprio_qopt(struct ice_vsi *vsi, + struct tc_mqprio_qopt_offload *mqprio_qopt) +{ + u64 sum_max_rate = 0, sum_min_rate = 0; + int non_power_of_2_qcount = 0; + struct ice_pf *pf = vsi->back; + int max_rss_q_cnt = 0; + struct device *dev; + int i, speed; + u8 num_tc; + + if (vsi->type != ICE_VSI_PF) + return -EINVAL; + + if (mqprio_qopt->qopt.offset[0] != 0 || + mqprio_qopt->qopt.num_tc < 1 || + mqprio_qopt->qopt.num_tc > ICE_CHNL_MAX_TC) + return -EINVAL; + + dev = ice_pf_to_dev(pf); + vsi->ch_rss_size = 0; + num_tc = mqprio_qopt->qopt.num_tc; + + for (i = 0; num_tc; i++) { + int qcount = mqprio_qopt->qopt.count[i]; + u64 max_rate, min_rate, rem; + + if (!qcount) + return -EINVAL; + + if (is_power_of_2(qcount)) { + if (non_power_of_2_qcount && + qcount > non_power_of_2_qcount) { + dev_err(dev, "qcount[%d] cannot be greater than non power of 2 qcount[%d]\n", + qcount, non_power_of_2_qcount); + return -EINVAL; + } + if (qcount > max_rss_q_cnt) + max_rss_q_cnt = qcount; + } else { + if (non_power_of_2_qcount && + qcount != non_power_of_2_qcount) { + dev_err(dev, "Only one non power of 2 qcount allowed[%d,%d]\n", + qcount, non_power_of_2_qcount); + return -EINVAL; + } + if (qcount < max_rss_q_cnt) { + dev_err(dev, "non power of 2 qcount[%d] cannot be less than other qcount[%d]\n", + qcount, max_rss_q_cnt); + return -EINVAL; + } + max_rss_q_cnt = qcount; + non_power_of_2_qcount = qcount; + } + + /* TC command takes input in K/N/Gbps or K/M/Gbit etc but + * converts the bandwidth rate limit into Bytes/s when + * passing it down to the driver. So convert input bandwidth + * from Bytes/s to Kbps + */ + max_rate = mqprio_qopt->max_rate[i]; + max_rate = div_u64(max_rate, ICE_BW_KBPS_DIVISOR); + sum_max_rate += max_rate; + + /* min_rate is minimum guaranteed rate and it can't be zero */ + min_rate = mqprio_qopt->min_rate[i]; + min_rate = div_u64(min_rate, ICE_BW_KBPS_DIVISOR); + sum_min_rate += min_rate; + + if (min_rate && min_rate < ICE_MIN_BW_LIMIT) { + dev_err(dev, "TC%d: min_rate(%llu Kbps) < %u Kbps\n", i, + min_rate, ICE_MIN_BW_LIMIT); + return -EINVAL; + } + + iter_div_u64_rem(min_rate, ICE_MIN_BW_LIMIT, &rem); + if (rem) { + dev_err(dev, "TC%d: Min Rate not multiple of %u Kbps", + i, ICE_MIN_BW_LIMIT); + return -EINVAL; + } + + iter_div_u64_rem(max_rate, ICE_MIN_BW_LIMIT, &rem); + if (rem) { + dev_err(dev, "TC%d: Max Rate not multiple of %u Kbps", + i, ICE_MIN_BW_LIMIT); + return -EINVAL; + } + + /* min_rate can't be more than max_rate, except when max_rate + * is zero (implies max_rate sought is max line rate). In such + * a case min_rate can be more than max. + */ + if (max_rate && min_rate > max_rate) { + dev_err(dev, "min_rate %llu Kbps can't be more than max_rate %llu Kbps\n", + min_rate, max_rate); + return -EINVAL; + } + + if (i >= mqprio_qopt->qopt.num_tc - 1) + break; + if (mqprio_qopt->qopt.offset[i + 1] != + (mqprio_qopt->qopt.offset[i] + qcount)) + return -EINVAL; + } + if (vsi->num_rxq < + (mqprio_qopt->qopt.offset[i] + mqprio_qopt->qopt.count[i])) + return -EINVAL; + if (vsi->num_txq < + (mqprio_qopt->qopt.offset[i] + mqprio_qopt->qopt.count[i])) + return -EINVAL; + + speed = ice_get_link_speed_kbps(vsi); + if (sum_max_rate && sum_max_rate > (u64)speed) { + dev_err(dev, "Invalid max Tx rate(%llu) Kbps > speed(%u) Kbps specified\n", + sum_max_rate, speed); + return -EINVAL; + } + if (sum_min_rate && sum_min_rate > (u64)speed) { + dev_err(dev, "Invalid min Tx rate(%llu) Kbps > speed (%u) Kbps specified\n", + sum_min_rate, speed); + return -EINVAL; + } + + /* make sure vsi->ch_rss_size is set correctly based on TC's qcount */ + vsi->ch_rss_size = max_rss_q_cnt; + + return 0; +} + +/** + * ice_add_channel - add a channel by adding VSI + * @pf: ptr to PF device + * @sw_id: underlying HW switching element ID + * @ch: ptr to channel structure + * + * Add a channel (VSI) using add_vsi and queue_map + */ +static int ice_add_channel(struct ice_pf *pf, u16 sw_id, struct ice_channel *ch) +{ + struct device *dev = ice_pf_to_dev(pf); + struct ice_vsi *vsi; + + if (ch->type != ICE_VSI_CHNL) { + dev_err(dev, "add new VSI failed, ch->type %d\n", ch->type); + return -EINVAL; + } + + vsi = ice_chnl_vsi_setup(pf, pf->hw.port_info, ch); + if (!vsi || vsi->type != ICE_VSI_CHNL) { + dev_err(dev, "create chnl VSI failure\n"); + return -EINVAL; + } + + ch->sw_id = sw_id; + ch->vsi_num = vsi->vsi_num; + ch->info.mapping_flags = vsi->info.mapping_flags; + ch->ch_vsi = vsi; + /* set the back pointer of channel for newly created VSI */ + vsi->ch = ch; + + memcpy(&ch->info.q_mapping, &vsi->info.q_mapping, + sizeof(vsi->info.q_mapping)); + memcpy(&ch->info.tc_mapping, vsi->info.tc_mapping, + sizeof(vsi->info.tc_mapping)); + + return 0; +} + +/** + * ice_chnl_cfg_res + * @vsi: the VSI being setup + * @ch: ptr to channel structure + * + * Configure channel specific resources such as rings, vector. + */ +static void ice_chnl_cfg_res(struct ice_vsi *vsi, struct ice_channel *ch) +{ + int i; + + for (i = 0; i < ch->num_txq; i++) { + struct ice_q_vector *tx_q_vector, *rx_q_vector; + struct ice_ring_container *rc; + struct ice_tx_ring *tx_ring; + struct ice_rx_ring *rx_ring; + + tx_ring = vsi->tx_rings[ch->base_q + i]; + rx_ring = vsi->rx_rings[ch->base_q + i]; + if (!tx_ring || !rx_ring) + continue; + + /* setup ring being channel enabled */ + tx_ring->ch = ch; + rx_ring->ch = ch; + + /* following code block sets up vector specific attributes */ + tx_q_vector = tx_ring->q_vector; + rx_q_vector = rx_ring->q_vector; + if (!tx_q_vector && !rx_q_vector) + continue; + + if (tx_q_vector) { + tx_q_vector->ch = ch; + /* setup Tx and Rx ITR setting if DIM is off */ + rc = &tx_q_vector->tx; + if (!ITR_IS_DYNAMIC(rc)) + ice_write_itr(rc, rc->itr_setting); + } + if (rx_q_vector) { + rx_q_vector->ch = ch; + /* setup Tx and Rx ITR setting if DIM is off */ + rc = &rx_q_vector->rx; + if (!ITR_IS_DYNAMIC(rc)) + ice_write_itr(rc, rc->itr_setting); + } + } + + /* it is safe to assume that, if channel has non-zero num_t[r]xq, then + * GLINT_ITR register would have written to perform in-context + * update, hence perform flush + */ + if (ch->num_txq || ch->num_rxq) + ice_flush(&vsi->back->hw); +} + +/** + * ice_cfg_chnl_all_res - configure channel resources + * @vsi: pte to main_vsi + * @ch: ptr to channel structure + * + * This function configures channel specific resources such as flow-director + * counter index, and other resources such as queues, vectors, ITR settings + */ +static void +ice_cfg_chnl_all_res(struct ice_vsi *vsi, struct ice_channel *ch) +{ + /* configure channel (aka ADQ) resources such as queues, vectors, + * ITR settings for channel specific vectors and anything else + */ + ice_chnl_cfg_res(vsi, ch); +} + +/** + * ice_setup_hw_channel - setup new channel + * @pf: ptr to PF device + * @vsi: the VSI being setup + * @ch: ptr to channel structure + * @sw_id: underlying HW switching element ID + * @type: type of channel to be created (VMDq2/VF) + * + * Setup new channel (VSI) based on specified type (VMDq2/VF) + * and configures Tx rings accordingly + */ +static int +ice_setup_hw_channel(struct ice_pf *pf, struct ice_vsi *vsi, + struct ice_channel *ch, u16 sw_id, u8 type) +{ + struct device *dev = ice_pf_to_dev(pf); + int ret; + + ch->base_q = vsi->next_base_q; + ch->type = type; + + ret = ice_add_channel(pf, sw_id, ch); + if (ret) { + dev_err(dev, "failed to add_channel using sw_id %u\n", sw_id); + return ret; + } + + /* configure/setup ADQ specific resources */ + ice_cfg_chnl_all_res(vsi, ch); + + /* make sure to update the next_base_q so that subsequent channel's + * (aka ADQ) VSI queue map is correct + */ + vsi->next_base_q = vsi->next_base_q + ch->num_rxq; + dev_dbg(dev, "added channel: vsi_num %u, num_rxq %u\n", ch->vsi_num, + ch->num_rxq); + + return 0; +} + +/** + * ice_setup_channel - setup new channel using uplink element + * @pf: ptr to PF device + * @vsi: the VSI being setup + * @ch: ptr to channel structure + * + * Setup new channel (VSI) based on specified type (VMDq2/VF) + * and uplink switching element + */ +static bool +ice_setup_channel(struct ice_pf *pf, struct ice_vsi *vsi, + struct ice_channel *ch) +{ + struct device *dev = ice_pf_to_dev(pf); + u16 sw_id; + int ret; + + if (vsi->type != ICE_VSI_PF) { + dev_err(dev, "unsupported parent VSI type(%d)\n", vsi->type); + return false; + } + + sw_id = pf->first_sw->sw_id; + + /* create channel (VSI) */ + ret = ice_setup_hw_channel(pf, vsi, ch, sw_id, ICE_VSI_CHNL); + if (ret) { + dev_err(dev, "failed to setup hw_channel\n"); + return false; + } + dev_dbg(dev, "successfully created channel()\n"); + + return ch->ch_vsi ? true : false; +} + +/** + * ice_set_bw_limit - setup BW limit for Tx traffic based on max_tx_rate + * @vsi: VSI to be configured + * @max_tx_rate: max Tx rate in Kbps to be configured as maximum BW limit + * @min_tx_rate: min Tx rate in Kbps to be configured as minimum BW limit + */ +static int +ice_set_bw_limit(struct ice_vsi *vsi, u64 max_tx_rate, u64 min_tx_rate) +{ + int err; + + err = ice_set_min_bw_limit(vsi, min_tx_rate); + if (err) + return err; + + return ice_set_max_bw_limit(vsi, max_tx_rate); +} + +/** + * ice_create_q_channel - function to create channel + * @vsi: VSI to be configured + * @ch: ptr to channel (it contains channel specific params) + * + * This function creates channel (VSI) using num_queues specified by user, + * reconfigs RSS if needed. + */ +static int ice_create_q_channel(struct ice_vsi *vsi, struct ice_channel *ch) +{ + struct ice_pf *pf = vsi->back; + struct device *dev; + + if (!ch) + return -EINVAL; + + dev = ice_pf_to_dev(pf); + if (!ch->num_txq || !ch->num_rxq) { + dev_err(dev, "Invalid num_queues requested: %d\n", ch->num_rxq); + return -EINVAL; + } + + if (!vsi->cnt_q_avail || vsi->cnt_q_avail < ch->num_txq) { + dev_err(dev, "cnt_q_avail (%u) less than num_queues %d\n", + vsi->cnt_q_avail, ch->num_txq); + return -EINVAL; + } + + if (!ice_setup_channel(pf, vsi, ch)) { + dev_info(dev, "Failed to setup channel\n"); + return -EINVAL; + } + /* configure BW rate limit */ + if (ch->ch_vsi && (ch->max_tx_rate || ch->min_tx_rate)) { + int ret; + + ret = ice_set_bw_limit(ch->ch_vsi, ch->max_tx_rate, + ch->min_tx_rate); + if (ret) + dev_err(dev, "failed to set Tx rate of %llu Kbps for VSI(%u)\n", + ch->max_tx_rate, ch->ch_vsi->vsi_num); + else + dev_dbg(dev, "set Tx rate of %llu Kbps for VSI(%u)\n", + ch->max_tx_rate, ch->ch_vsi->vsi_num); + } + + vsi->cnt_q_avail -= ch->num_txq; + + return 0; +} + +/** + * ice_rem_all_chnl_fltrs - removes all channel filters + * @pf: ptr to PF, TC-flower based filter are tracked at PF level + * + * Remove all advanced switch filters only if they are channel specific + * tc-flower based filter + */ +static void ice_rem_all_chnl_fltrs(struct ice_pf *pf) +{ + struct ice_tc_flower_fltr *fltr; + struct hlist_node *node; + + /* to remove all channel filters, iterate an ordered list of filters */ + hlist_for_each_entry_safe(fltr, node, + &pf->tc_flower_fltr_list, + tc_flower_node) { + struct ice_rule_query_data rule; + int status; + + /* for now process only channel specific filters */ + if (!ice_is_chnl_fltr(fltr)) + continue; + + rule.rid = fltr->rid; + rule.rule_id = fltr->rule_id; + rule.vsi_handle = fltr->dest_id; + status = ice_rem_adv_rule_by_id(&pf->hw, &rule); + if (status) { + if (status == -ENOENT) + dev_dbg(ice_pf_to_dev(pf), "TC flower filter (rule_id %u) does not exist\n", + rule.rule_id); + else + dev_err(ice_pf_to_dev(pf), "failed to delete TC flower filter, status %d\n", + status); + } else if (fltr->dest_vsi) { + /* update advanced switch filter count */ + if (fltr->dest_vsi->type == ICE_VSI_CHNL) { + u32 flags = fltr->flags; + + fltr->dest_vsi->num_chnl_fltr--; + if (flags & (ICE_TC_FLWR_FIELD_DST_MAC | + ICE_TC_FLWR_FIELD_ENC_DST_MAC)) + pf->num_dmac_chnl_fltrs--; + } + } + + hlist_del(&fltr->tc_flower_node); + kfree(fltr); + } +} + +/** + * ice_remove_q_channels - Remove queue channels for the TCs + * @vsi: VSI to be configured + * @rem_fltr: delete advanced switch filter or not + * + * Remove queue channels for the TCs + */ +static void ice_remove_q_channels(struct ice_vsi *vsi, bool rem_fltr) +{ + struct ice_channel *ch, *ch_tmp; + struct ice_pf *pf = vsi->back; + int i; + + /* remove all tc-flower based filter if they are channel filters only */ + if (rem_fltr) + ice_rem_all_chnl_fltrs(pf); + + /* perform cleanup for channels if they exist */ + list_for_each_entry_safe(ch, ch_tmp, &vsi->ch_list, list) { + struct ice_vsi *ch_vsi; + + list_del(&ch->list); + ch_vsi = ch->ch_vsi; + if (!ch_vsi) { + kfree(ch); + continue; + } + + /* Reset queue contexts */ + for (i = 0; i < ch->num_rxq; i++) { + struct ice_tx_ring *tx_ring; + struct ice_rx_ring *rx_ring; + + tx_ring = vsi->tx_rings[ch->base_q + i]; + rx_ring = vsi->rx_rings[ch->base_q + i]; + if (tx_ring) { + tx_ring->ch = NULL; + if (tx_ring->q_vector) + tx_ring->q_vector->ch = NULL; + } + if (rx_ring) { + rx_ring->ch = NULL; + if (rx_ring->q_vector) + rx_ring->q_vector->ch = NULL; + } + } + + /* clear the VSI from scheduler tree */ + ice_rm_vsi_lan_cfg(ch->ch_vsi->port_info, ch->ch_vsi->idx); + + /* Delete VSI from FW */ + ice_vsi_delete(ch->ch_vsi); + + /* Delete VSI from PF and HW VSI arrays */ + ice_vsi_clear(ch->ch_vsi); + + /* free the channel */ + kfree(ch); + } + + /* clear the channel VSI map which is stored in main VSI */ + ice_for_each_chnl_tc(i) + vsi->tc_map_vsi[i] = NULL; + + /* reset main VSI's all TC information */ + vsi->all_enatc = 0; + vsi->all_numtc = 0; +} + +/** + * ice_rebuild_channels - rebuild channel + * @pf: ptr to PF + * + * Recreate channel VSIs and replay filters + */ +static int ice_rebuild_channels(struct ice_pf *pf) +{ + struct device *dev = ice_pf_to_dev(pf); + struct ice_vsi *main_vsi; + bool rem_adv_fltr = true; + struct ice_channel *ch; + struct ice_vsi *vsi; + int tc_idx = 1; + int i, err; + + main_vsi = ice_get_main_vsi(pf); + if (!main_vsi) + return 0; + + if (!test_bit(ICE_FLAG_TC_MQPRIO, pf->flags) || + main_vsi->old_numtc == 1) + return 0; /* nothing to be done */ + + /* reconfigure main VSI based on old value of TC and cached values + * for MQPRIO opts + */ + err = ice_vsi_cfg_tc(main_vsi, main_vsi->old_ena_tc); + if (err) { + dev_err(dev, "failed configuring TC(ena_tc:0x%02x) for HW VSI=%u\n", + main_vsi->old_ena_tc, main_vsi->vsi_num); + return err; + } + + /* rebuild ADQ VSIs */ + ice_for_each_vsi(pf, i) { + enum ice_vsi_type type; + + vsi = pf->vsi[i]; + if (!vsi || vsi->type != ICE_VSI_CHNL) + continue; + + type = vsi->type; + + /* rebuild ADQ VSI */ + err = ice_vsi_rebuild(vsi, true); + if (err) { + dev_err(dev, "VSI (type:%s) at index %d rebuild failed, err %d\n", + ice_vsi_type_str(type), vsi->idx, err); + goto cleanup; + } + + /* Re-map HW VSI number, using VSI handle that has been + * previously validated in ice_replay_vsi() call above + */ + vsi->vsi_num = ice_get_hw_vsi_num(&pf->hw, vsi->idx); + + /* replay filters for the VSI */ + err = ice_replay_vsi(&pf->hw, vsi->idx); + if (err) { + dev_err(dev, "VSI (type:%s) replay failed, err %d, VSI index %d\n", + ice_vsi_type_str(type), err, vsi->idx); + rem_adv_fltr = false; + goto cleanup; + } + dev_info(dev, "VSI (type:%s) at index %d rebuilt successfully\n", + ice_vsi_type_str(type), vsi->idx); + + /* store ADQ VSI at correct TC index in main VSI's + * map of TC to VSI + */ + main_vsi->tc_map_vsi[tc_idx++] = vsi; + } + + /* ADQ VSI(s) has been rebuilt successfully, so setup + * channel for main VSI's Tx and Rx rings + */ + list_for_each_entry(ch, &main_vsi->ch_list, list) { + struct ice_vsi *ch_vsi; + + ch_vsi = ch->ch_vsi; + if (!ch_vsi) + continue; + + /* reconfig channel resources */ + ice_cfg_chnl_all_res(main_vsi, ch); + + /* replay BW rate limit if it is non-zero */ + if (!ch->max_tx_rate && !ch->min_tx_rate) + continue; + + err = ice_set_bw_limit(ch_vsi, ch->max_tx_rate, + ch->min_tx_rate); + if (err) + dev_err(dev, "failed (err:%d) to rebuild BW rate limit, max_tx_rate: %llu Kbps, min_tx_rate: %llu Kbps for VSI(%u)\n", + err, ch->max_tx_rate, ch->min_tx_rate, + ch_vsi->vsi_num); + else + dev_dbg(dev, "successfully rebuild BW rate limit, max_tx_rate: %llu Kbps, min_tx_rate: %llu Kbps for VSI(%u)\n", + ch->max_tx_rate, ch->min_tx_rate, + ch_vsi->vsi_num); + } + + /* reconfig RSS for main VSI */ + if (main_vsi->ch_rss_size) + ice_vsi_cfg_rss_lut_key(main_vsi); + + return 0; + +cleanup: + ice_remove_q_channels(main_vsi, rem_adv_fltr); + return err; +} + +/** + * ice_create_q_channels - Add queue channel for the given TCs + * @vsi: VSI to be configured + * + * Configures queue channel mapping to the given TCs + */ +static int ice_create_q_channels(struct ice_vsi *vsi) +{ + struct ice_pf *pf = vsi->back; + struct ice_channel *ch; + int ret = 0, i; + + ice_for_each_chnl_tc(i) { + if (!(vsi->all_enatc & BIT(i))) + continue; + + ch = kzalloc(sizeof(*ch), GFP_KERNEL); + if (!ch) { + ret = -ENOMEM; + goto err_free; + } + INIT_LIST_HEAD(&ch->list); + ch->num_rxq = vsi->mqprio_qopt.qopt.count[i]; + ch->num_txq = vsi->mqprio_qopt.qopt.count[i]; + ch->base_q = vsi->mqprio_qopt.qopt.offset[i]; + ch->max_tx_rate = vsi->mqprio_qopt.max_rate[i]; + ch->min_tx_rate = vsi->mqprio_qopt.min_rate[i]; + + /* convert to Kbits/s */ + if (ch->max_tx_rate) + ch->max_tx_rate = div_u64(ch->max_tx_rate, + ICE_BW_KBPS_DIVISOR); + if (ch->min_tx_rate) + ch->min_tx_rate = div_u64(ch->min_tx_rate, + ICE_BW_KBPS_DIVISOR); + + ret = ice_create_q_channel(vsi, ch); + if (ret) { + dev_err(ice_pf_to_dev(pf), + "failed creating channel TC:%d\n", i); + kfree(ch); + goto err_free; + } + list_add_tail(&ch->list, &vsi->ch_list); + vsi->tc_map_vsi[i] = ch->ch_vsi; + dev_dbg(ice_pf_to_dev(pf), + "successfully created channel: VSI %pK\n", ch->ch_vsi); + } + return 0; + +err_free: + ice_remove_q_channels(vsi, false); + + return ret; +} + +/** + * ice_setup_tc_mqprio_qdisc - configure multiple traffic classes + * @netdev: net device to configure + * @type_data: TC offload data + */ +static int ice_setup_tc_mqprio_qdisc(struct net_device *netdev, void *type_data) +{ + struct tc_mqprio_qopt_offload *mqprio_qopt = type_data; + struct ice_netdev_priv *np = netdev_priv(netdev); + struct ice_vsi *vsi = np->vsi; + struct ice_pf *pf = vsi->back; + u16 mode, ena_tc_qdisc = 0; + int cur_txq, cur_rxq; + u8 hw = 0, num_tcf; + struct device *dev; + int ret, i; + + dev = ice_pf_to_dev(pf); + num_tcf = mqprio_qopt->qopt.num_tc; + hw = mqprio_qopt->qopt.hw; + mode = mqprio_qopt->mode; + if (!hw) { + clear_bit(ICE_FLAG_TC_MQPRIO, pf->flags); + vsi->ch_rss_size = 0; + memcpy(&vsi->mqprio_qopt, mqprio_qopt, sizeof(*mqprio_qopt)); + goto config_tcf; + } + + /* Generate queue region map for number of TCF requested */ + for (i = 0; i < num_tcf; i++) + ena_tc_qdisc |= BIT(i); + + switch (mode) { + case TC_MQPRIO_MODE_CHANNEL: + + ret = ice_validate_mqprio_qopt(vsi, mqprio_qopt); + if (ret) { + netdev_err(netdev, "failed to validate_mqprio_qopt(), ret %d\n", + ret); + return ret; + } + memcpy(&vsi->mqprio_qopt, mqprio_qopt, sizeof(*mqprio_qopt)); + set_bit(ICE_FLAG_TC_MQPRIO, pf->flags); + /* don't assume state of hw_tc_offload during driver load + * and set the flag for TC flower filter if hw_tc_offload + * already ON + */ + if (vsi->netdev->features & NETIF_F_HW_TC) + set_bit(ICE_FLAG_CLS_FLOWER, pf->flags); + break; + default: + return -EINVAL; + } + +config_tcf: + + /* Requesting same TCF configuration as already enabled */ + if (ena_tc_qdisc == vsi->tc_cfg.ena_tc && + mode != TC_MQPRIO_MODE_CHANNEL) + return 0; + + /* Pause VSI queues */ + ice_dis_vsi(vsi, true); + + if (!hw && !test_bit(ICE_FLAG_TC_MQPRIO, pf->flags)) + ice_remove_q_channels(vsi, true); + + if (!hw && !test_bit(ICE_FLAG_TC_MQPRIO, pf->flags)) { + vsi->req_txq = min_t(int, ice_get_avail_txq_count(pf), + num_online_cpus()); + vsi->req_rxq = min_t(int, ice_get_avail_rxq_count(pf), + num_online_cpus()); + } else { + /* logic to rebuild VSI, same like ethtool -L */ + u16 offset = 0, qcount_tx = 0, qcount_rx = 0; + + for (i = 0; i < num_tcf; i++) { + if (!(ena_tc_qdisc & BIT(i))) + continue; + + offset = vsi->mqprio_qopt.qopt.offset[i]; + qcount_rx = vsi->mqprio_qopt.qopt.count[i]; + qcount_tx = vsi->mqprio_qopt.qopt.count[i]; + } + vsi->req_txq = offset + qcount_tx; + vsi->req_rxq = offset + qcount_rx; + + /* store away original rss_size info, so that it gets reused + * form ice_vsi_rebuild during tc-qdisc delete stage - to + * determine, what should be the rss_sizefor main VSI + */ + vsi->orig_rss_size = vsi->rss_size; + } + + /* save current values of Tx and Rx queues before calling VSI rebuild + * for fallback option + */ + cur_txq = vsi->num_txq; + cur_rxq = vsi->num_rxq; + + /* proceed with rebuild main VSI using correct number of queues */ + ret = ice_vsi_rebuild(vsi, false); + if (ret) { + /* fallback to current number of queues */ + dev_info(dev, "Rebuild failed with new queues, try with current number of queues\n"); + vsi->req_txq = cur_txq; + vsi->req_rxq = cur_rxq; + clear_bit(ICE_RESET_FAILED, pf->state); + if (ice_vsi_rebuild(vsi, false)) { + dev_err(dev, "Rebuild of main VSI failed again\n"); + return ret; + } + } + + vsi->all_numtc = num_tcf; + vsi->all_enatc = ena_tc_qdisc; + ret = ice_vsi_cfg_tc(vsi, ena_tc_qdisc); + if (ret) { + netdev_err(netdev, "failed configuring TC for VSI id=%d\n", + vsi->vsi_num); + goto exit; + } + + if (test_bit(ICE_FLAG_TC_MQPRIO, pf->flags)) { + u64 max_tx_rate = vsi->mqprio_qopt.max_rate[0]; + u64 min_tx_rate = vsi->mqprio_qopt.min_rate[0]; + + /* set TC0 rate limit if specified */ + if (max_tx_rate || min_tx_rate) { + /* convert to Kbits/s */ + if (max_tx_rate) + max_tx_rate = div_u64(max_tx_rate, ICE_BW_KBPS_DIVISOR); + if (min_tx_rate) + min_tx_rate = div_u64(min_tx_rate, ICE_BW_KBPS_DIVISOR); + + ret = ice_set_bw_limit(vsi, max_tx_rate, min_tx_rate); + if (!ret) { + dev_dbg(dev, "set Tx rate max %llu min %llu for VSI(%u)\n", + max_tx_rate, min_tx_rate, vsi->vsi_num); + } else { + dev_err(dev, "failed to set Tx rate max %llu min %llu for VSI(%u)\n", + max_tx_rate, min_tx_rate, vsi->vsi_num); + goto exit; + } + } + ret = ice_create_q_channels(vsi); + if (ret) { + netdev_err(netdev, "failed configuring queue channels\n"); + goto exit; + } else { + netdev_dbg(netdev, "successfully configured channels\n"); + } + } + + if (vsi->ch_rss_size) + ice_vsi_cfg_rss_lut_key(vsi); + +exit: + /* if error, reset the all_numtc and all_enatc */ + if (ret) { + vsi->all_numtc = 0; + vsi->all_enatc = 0; + } + /* resume VSI */ + ice_ena_vsi(vsi, true); + + return ret; +} + +static LIST_HEAD(ice_block_cb_list); + +static int +ice_setup_tc(struct net_device *netdev, enum tc_setup_type type, + void *type_data) +{ + struct ice_netdev_priv *np = netdev_priv(netdev); + struct ice_pf *pf = np->vsi->back; + int err; + + switch (type) { + case TC_SETUP_BLOCK: + return flow_block_cb_setup_simple(type_data, + &ice_block_cb_list, + ice_setup_tc_block_cb, + np, np, true); + case TC_SETUP_QDISC_MQPRIO: + /* setup traffic classifier for receive side */ + mutex_lock(&pf->tc_mutex); + err = ice_setup_tc_mqprio_qdisc(netdev, type_data); + mutex_unlock(&pf->tc_mutex); + return err; + default: + return -EOPNOTSUPP; + } + return -EOPNOTSUPP; +} + /** * ice_open - Called when a network interface becomes active * @netdev: network interface device structure @@ -7277,8 +8357,10 @@ static const struct net_device_ops ice_netdev_ops = { .ndo_set_vf_vlan = ice_set_vf_port_vlan, .ndo_set_vf_link_state = ice_set_vf_link_state, .ndo_get_vf_stats = ice_get_vf_stats, + .ndo_set_vf_rate = ice_set_vf_bw, .ndo_vlan_rx_add_vid = ice_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = ice_vlan_rx_kill_vid, + .ndo_setup_tc = ice_setup_tc, .ndo_set_features = ice_set_features, .ndo_bridge_getlink = ice_bridge_getlink, .ndo_bridge_setlink = ice_bridge_setlink, diff --git a/drivers/net/ethernet/intel/ice/ice_protocol_type.h b/drivers/net/ethernet/intel/ice/ice_protocol_type.h index 199aa5b71540..0b220dfa7457 100644 --- a/drivers/net/ethernet/intel/ice/ice_protocol_type.h +++ b/drivers/net/ethernet/intel/ice/ice_protocol_type.h @@ -3,6 +3,44 @@ #ifndef _ICE_PROTOCOL_TYPE_H_ #define _ICE_PROTOCOL_TYPE_H_ +#define ICE_IPV6_ADDR_LENGTH 16 + +/* Each recipe can match up to 5 different fields. Fields to match can be meta- + * data, values extracted from packet headers, or results from other recipes. + * One of the 5 fields is reserved for matching the switch ID. So, up to 4 + * recipes can provide intermediate results to another one through chaining, + * e.g. recipes 0, 1, 2, and 3 can provide intermediate results to recipe 4. + */ +#define ICE_NUM_WORDS_RECIPE 4 + +/* Max recipes that can be chained */ +#define ICE_MAX_CHAIN_RECIPE 5 + +/* 1 word reserved for switch ID from allowed 5 words. + * So a recipe can have max 4 words. And you can chain 5 such recipes + * together. So maximum words that can be programmed for look up is 5 * 4. + */ +#define ICE_MAX_CHAIN_WORDS (ICE_NUM_WORDS_RECIPE * ICE_MAX_CHAIN_RECIPE) + +/* Field vector index corresponding to chaining */ +#define ICE_CHAIN_FV_INDEX_START 47 + +enum ice_protocol_type { + ICE_MAC_OFOS = 0, + ICE_MAC_IL, + ICE_ETYPE_OL, + ICE_VLAN_OFOS, + ICE_IPV4_OFOS, + ICE_IPV4_IL, + ICE_IPV6_OFOS, + ICE_IPV6_IL, + ICE_TCP_IL, + ICE_UDP_OF, + ICE_UDP_ILOS, + ICE_SCTP_IL, + ICE_PROTOCOL_LAST +}; + /* Decoders for ice_prot_id: * - F: First * - I: Inner @@ -35,4 +73,135 @@ enum ice_prot_id { ICE_PROT_META_ID = 255, /* when offset == metadata */ ICE_PROT_INVALID = 255 /* when offset == ICE_FV_OFFSET_INVAL */ }; + +#define ICE_MAC_OFOS_HW 1 +#define ICE_MAC_IL_HW 4 +#define ICE_ETYPE_OL_HW 9 +#define ICE_VLAN_OF_HW 16 +#define ICE_VLAN_OL_HW 17 +#define ICE_IPV4_OFOS_HW 32 +#define ICE_IPV4_IL_HW 33 +#define ICE_IPV6_OFOS_HW 40 +#define ICE_IPV6_IL_HW 41 +#define ICE_TCP_IL_HW 49 +#define ICE_UDP_ILOS_HW 53 + +#define ICE_UDP_OF_HW 52 /* UDP Tunnels */ + +#define ICE_TUN_FLAG_FV_IND 2 + +/* Mapping of software defined protocol ID to hardware defined protocol ID */ +struct ice_protocol_entry { + enum ice_protocol_type type; + u8 protocol_id; +}; + +struct ice_ether_hdr { + u8 dst_addr[ETH_ALEN]; + u8 src_addr[ETH_ALEN]; +}; + +struct ice_ethtype_hdr { + __be16 ethtype_id; +}; + +struct ice_ether_vlan_hdr { + u8 dst_addr[ETH_ALEN]; + u8 src_addr[ETH_ALEN]; + __be32 vlan_id; +}; + +struct ice_vlan_hdr { + __be16 type; + __be16 vlan; +}; + +struct ice_ipv4_hdr { + u8 version; + u8 tos; + __be16 total_length; + __be16 id; + __be16 frag_off; + u8 time_to_live; + u8 protocol; + __be16 check; + __be32 src_addr; + __be32 dst_addr; +}; + +struct ice_ipv6_hdr { + __be32 be_ver_tc_flow; + __be16 payload_len; + u8 next_hdr; + u8 hop_limit; + u8 src_addr[ICE_IPV6_ADDR_LENGTH]; + u8 dst_addr[ICE_IPV6_ADDR_LENGTH]; +}; + +struct ice_sctp_hdr { + __be16 src_port; + __be16 dst_port; + __be32 verification_tag; + __be32 check; +}; + +struct ice_l4_hdr { + __be16 src_port; + __be16 dst_port; + __be16 len; + __be16 check; +}; + +union ice_prot_hdr { + struct ice_ether_hdr eth_hdr; + struct ice_ethtype_hdr ethertype; + struct ice_vlan_hdr vlan_hdr; + struct ice_ipv4_hdr ipv4_hdr; + struct ice_ipv6_hdr ipv6_hdr; + struct ice_l4_hdr l4_hdr; + struct ice_sctp_hdr sctp_hdr; +}; + +/* This is mapping table entry that maps every word within a given protocol + * structure to the real byte offset as per the specification of that + * protocol header. + * for e.g. dst address is 3 words in ethertype header and corresponding bytes + * are 0, 2, 3 in the actual packet header and src address is at 4, 6, 8 + */ +struct ice_prot_ext_tbl_entry { + enum ice_protocol_type prot_type; + /* Byte offset into header of given protocol type */ + u8 offs[sizeof(union ice_prot_hdr)]; +}; + +/* Extractions to be looked up for a given recipe */ +struct ice_prot_lkup_ext { + u16 prot_type; + u8 n_val_words; + /* create a buffer to hold max words per recipe */ + u16 field_off[ICE_MAX_CHAIN_WORDS]; + u16 field_mask[ICE_MAX_CHAIN_WORDS]; + + struct ice_fv_word fv_words[ICE_MAX_CHAIN_WORDS]; + + /* Indicate field offsets that have field vector indices assigned */ + DECLARE_BITMAP(done, ICE_MAX_CHAIN_WORDS); +}; + +struct ice_pref_recipe_group { + u8 n_val_pairs; /* Number of valid pairs */ + struct ice_fv_word pairs[ICE_NUM_WORDS_RECIPE]; + u16 mask[ICE_NUM_WORDS_RECIPE]; +}; + +struct ice_recp_grp_entry { + struct list_head l_entry; + +#define ICE_INVAL_CHAIN_IND 0xFF + u16 rid; + u8 chain_idx; + u16 fv_idx[ICE_NUM_WORDS_RECIPE]; + u16 fv_mask[ICE_NUM_WORDS_RECIPE]; + struct ice_pref_recipe_group r_group; +}; #endif /* _ICE_PROTOCOL_TYPE_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c index d1ef3d48a4b0..bf7247c6f58e 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp.c @@ -6,6 +6,252 @@ #define E810_OUT_PROP_DELAY_NS 1 +static const struct ptp_pin_desc ice_pin_desc_e810t[] = { + /* name idx func chan */ + { "GNSS", GNSS, PTP_PF_EXTTS, 0, { 0, } }, + { "SMA1", SMA1, PTP_PF_NONE, 1, { 0, } }, + { "U.FL1", UFL1, PTP_PF_NONE, 1, { 0, } }, + { "SMA2", SMA2, PTP_PF_NONE, 2, { 0, } }, + { "U.FL2", UFL2, PTP_PF_NONE, 2, { 0, } }, +}; + +/** + * ice_get_sma_config_e810t + * @hw: pointer to the hw struct + * @ptp_pins: pointer to the ptp_pin_desc struture + * + * Read the configuration of the SMA control logic and put it into the + * ptp_pin_desc structure + */ +static int +ice_get_sma_config_e810t(struct ice_hw *hw, struct ptp_pin_desc *ptp_pins) +{ + u8 data, i; + int status; + + /* Read initial pin state */ + status = ice_read_sma_ctrl_e810t(hw, &data); + if (status) + return status; + + /* initialize with defaults */ + for (i = 0; i < NUM_PTP_PINS_E810T; i++) { + snprintf(ptp_pins[i].name, sizeof(ptp_pins[i].name), + "%s", ice_pin_desc_e810t[i].name); + ptp_pins[i].index = ice_pin_desc_e810t[i].index; + ptp_pins[i].func = ice_pin_desc_e810t[i].func; + ptp_pins[i].chan = ice_pin_desc_e810t[i].chan; + } + + /* Parse SMA1/UFL1 */ + switch (data & ICE_SMA1_MASK_E810T) { + case ICE_SMA1_MASK_E810T: + default: + ptp_pins[SMA1].func = PTP_PF_NONE; + ptp_pins[UFL1].func = PTP_PF_NONE; + break; + case ICE_SMA1_DIR_EN_E810T: + ptp_pins[SMA1].func = PTP_PF_PEROUT; + ptp_pins[UFL1].func = PTP_PF_NONE; + break; + case ICE_SMA1_TX_EN_E810T: + ptp_pins[SMA1].func = PTP_PF_EXTTS; + ptp_pins[UFL1].func = PTP_PF_NONE; + break; + case 0: + ptp_pins[SMA1].func = PTP_PF_EXTTS; + ptp_pins[UFL1].func = PTP_PF_PEROUT; + break; + } + + /* Parse SMA2/UFL2 */ + switch (data & ICE_SMA2_MASK_E810T) { + case ICE_SMA2_MASK_E810T: + default: + ptp_pins[SMA2].func = PTP_PF_NONE; + ptp_pins[UFL2].func = PTP_PF_NONE; + break; + case (ICE_SMA2_TX_EN_E810T | ICE_SMA2_UFL2_RX_DIS_E810T): + ptp_pins[SMA2].func = PTP_PF_EXTTS; + ptp_pins[UFL2].func = PTP_PF_NONE; + break; + case (ICE_SMA2_DIR_EN_E810T | ICE_SMA2_UFL2_RX_DIS_E810T): + ptp_pins[SMA2].func = PTP_PF_PEROUT; + ptp_pins[UFL2].func = PTP_PF_NONE; + break; + case (ICE_SMA2_DIR_EN_E810T | ICE_SMA2_TX_EN_E810T): + ptp_pins[SMA2].func = PTP_PF_NONE; + ptp_pins[UFL2].func = PTP_PF_EXTTS; + break; + case ICE_SMA2_DIR_EN_E810T: + ptp_pins[SMA2].func = PTP_PF_PEROUT; + ptp_pins[UFL2].func = PTP_PF_EXTTS; + break; + } + + return 0; +} + +/** + * ice_ptp_set_sma_config_e810t + * @hw: pointer to the hw struct + * @ptp_pins: pointer to the ptp_pin_desc struture + * + * Set the configuration of the SMA control logic based on the configuration in + * num_pins parameter + */ +static int +ice_ptp_set_sma_config_e810t(struct ice_hw *hw, + const struct ptp_pin_desc *ptp_pins) +{ + int status; + u8 data; + + /* SMA1 and UFL1 cannot be set to TX at the same time */ + if (ptp_pins[SMA1].func == PTP_PF_PEROUT && + ptp_pins[UFL1].func == PTP_PF_PEROUT) + return -EINVAL; + + /* SMA2 and UFL2 cannot be set to RX at the same time */ + if (ptp_pins[SMA2].func == PTP_PF_EXTTS && + ptp_pins[UFL2].func == PTP_PF_EXTTS) + return -EINVAL; + + /* Read initial pin state value */ + status = ice_read_sma_ctrl_e810t(hw, &data); + if (status) + return status; + + /* Set the right sate based on the desired configuration */ + data &= ~ICE_SMA1_MASK_E810T; + if (ptp_pins[SMA1].func == PTP_PF_NONE && + ptp_pins[UFL1].func == PTP_PF_NONE) { + dev_info(ice_hw_to_dev(hw), "SMA1 + U.FL1 disabled"); + data |= ICE_SMA1_MASK_E810T; + } else if (ptp_pins[SMA1].func == PTP_PF_EXTTS && + ptp_pins[UFL1].func == PTP_PF_NONE) { + dev_info(ice_hw_to_dev(hw), "SMA1 RX"); + data |= ICE_SMA1_TX_EN_E810T; + } else if (ptp_pins[SMA1].func == PTP_PF_NONE && + ptp_pins[UFL1].func == PTP_PF_PEROUT) { + /* U.FL 1 TX will always enable SMA 1 RX */ + dev_info(ice_hw_to_dev(hw), "SMA1 RX + U.FL1 TX"); + } else if (ptp_pins[SMA1].func == PTP_PF_EXTTS && + ptp_pins[UFL1].func == PTP_PF_PEROUT) { + dev_info(ice_hw_to_dev(hw), "SMA1 RX + U.FL1 TX"); + } else if (ptp_pins[SMA1].func == PTP_PF_PEROUT && + ptp_pins[UFL1].func == PTP_PF_NONE) { + dev_info(ice_hw_to_dev(hw), "SMA1 TX"); + data |= ICE_SMA1_DIR_EN_E810T; + } + + data &= ~ICE_SMA2_MASK_E810T; + if (ptp_pins[SMA2].func == PTP_PF_NONE && + ptp_pins[UFL2].func == PTP_PF_NONE) { + dev_info(ice_hw_to_dev(hw), "SMA2 + U.FL2 disabled"); + data |= ICE_SMA2_MASK_E810T; + } else if (ptp_pins[SMA2].func == PTP_PF_EXTTS && + ptp_pins[UFL2].func == PTP_PF_NONE) { + dev_info(ice_hw_to_dev(hw), "SMA2 RX"); + data |= (ICE_SMA2_TX_EN_E810T | + ICE_SMA2_UFL2_RX_DIS_E810T); + } else if (ptp_pins[SMA2].func == PTP_PF_NONE && + ptp_pins[UFL2].func == PTP_PF_EXTTS) { + dev_info(ice_hw_to_dev(hw), "UFL2 RX"); + data |= (ICE_SMA2_DIR_EN_E810T | ICE_SMA2_TX_EN_E810T); + } else if (ptp_pins[SMA2].func == PTP_PF_PEROUT && + ptp_pins[UFL2].func == PTP_PF_NONE) { + dev_info(ice_hw_to_dev(hw), "SMA2 TX"); + data |= (ICE_SMA2_DIR_EN_E810T | + ICE_SMA2_UFL2_RX_DIS_E810T); + } else if (ptp_pins[SMA2].func == PTP_PF_PEROUT && + ptp_pins[UFL2].func == PTP_PF_EXTTS) { + dev_info(ice_hw_to_dev(hw), "SMA2 TX + U.FL2 RX"); + data |= ICE_SMA2_DIR_EN_E810T; + } + + return ice_write_sma_ctrl_e810t(hw, data); +} + +/** + * ice_ptp_set_sma_e810t + * @info: the driver's PTP info structure + * @pin: pin index in kernel structure + * @func: Pin function to be set (PTP_PF_NONE, PTP_PF_EXTTS or PTP_PF_PEROUT) + * + * Set the configuration of a single SMA pin + */ +static int +ice_ptp_set_sma_e810t(struct ptp_clock_info *info, unsigned int pin, + enum ptp_pin_function func) +{ + struct ptp_pin_desc ptp_pins[NUM_PTP_PINS_E810T]; + struct ice_pf *pf = ptp_info_to_pf(info); + struct ice_hw *hw = &pf->hw; + int err; + + if (pin < SMA1 || func > PTP_PF_PEROUT) + return -EOPNOTSUPP; + + err = ice_get_sma_config_e810t(hw, ptp_pins); + if (err) + return err; + + /* Disable the same function on the other pin sharing the channel */ + if (pin == SMA1 && ptp_pins[UFL1].func == func) + ptp_pins[UFL1].func = PTP_PF_NONE; + if (pin == UFL1 && ptp_pins[SMA1].func == func) + ptp_pins[SMA1].func = PTP_PF_NONE; + + if (pin == SMA2 && ptp_pins[UFL2].func == func) + ptp_pins[UFL2].func = PTP_PF_NONE; + if (pin == UFL2 && ptp_pins[SMA2].func == func) + ptp_pins[SMA2].func = PTP_PF_NONE; + + /* Set up new pin function in the temp table */ + ptp_pins[pin].func = func; + + return ice_ptp_set_sma_config_e810t(hw, ptp_pins); +} + +/** + * ice_verify_pin_e810t + * @info: the driver's PTP info structure + * @pin: Pin index + * @func: Assigned function + * @chan: Assigned channel + * + * Verify if pin supports requested pin function. If the Check pins consistency. + * Reconfigure the SMA logic attached to the given pin to enable its + * desired functionality + */ +static int +ice_verify_pin_e810t(struct ptp_clock_info *info, unsigned int pin, + enum ptp_pin_function func, unsigned int chan) +{ + /* Don't allow channel reassignment */ + if (chan != ice_pin_desc_e810t[pin].chan) + return -EOPNOTSUPP; + + /* Check if functions are properly assigned */ + switch (func) { + case PTP_PF_NONE: + break; + case PTP_PF_EXTTS: + if (pin == UFL1) + return -EOPNOTSUPP; + break; + case PTP_PF_PEROUT: + if (pin == UFL2 || pin == GNSS) + return -EOPNOTSUPP; + break; + case PTP_PF_PHYSYNC: + return -EOPNOTSUPP; + } + + return ice_ptp_set_sma_e810t(info, pin, func); +} + /** * ice_set_tx_tstamp - Enable or disable Tx timestamping * @pf: The PF pointer to search in @@ -735,17 +981,34 @@ ice_ptp_gpio_enable_e810(struct ptp_clock_info *info, { struct ice_pf *pf = ptp_info_to_pf(info); struct ice_perout_channel clk_cfg = {0}; + bool sma_pres = false; unsigned int chan; u32 gpio_pin; int err; + if (ice_is_feature_supported(pf, ICE_F_SMA_CTRL)) + sma_pres = true; + switch (rq->type) { case PTP_CLK_REQ_PEROUT: chan = rq->perout.index; - if (chan == PPS_CLK_GEN_CHAN) + if (sma_pres) { + if (chan == ice_pin_desc_e810t[SMA1].chan) + clk_cfg.gpio_pin = GPIO_20; + else if (chan == ice_pin_desc_e810t[SMA2].chan) + clk_cfg.gpio_pin = GPIO_22; + else + return -1; + } else if (ice_is_e810t(&pf->hw)) { + if (chan == 0) + clk_cfg.gpio_pin = GPIO_20; + else + clk_cfg.gpio_pin = GPIO_22; + } else if (chan == PPS_CLK_GEN_CHAN) { clk_cfg.gpio_pin = PPS_PIN_INDEX; - else + } else { clk_cfg.gpio_pin = chan; + } clk_cfg.period = ((rq->perout.period.sec * NSEC_PER_SEC) + rq->perout.period.nsec); @@ -757,7 +1020,19 @@ ice_ptp_gpio_enable_e810(struct ptp_clock_info *info, break; case PTP_CLK_REQ_EXTTS: chan = rq->extts.index; - gpio_pin = chan; + if (sma_pres) { + if (chan < ice_pin_desc_e810t[SMA2].chan) + gpio_pin = GPIO_21; + else + gpio_pin = GPIO_23; + } else if (ice_is_e810t(&pf->hw)) { + if (chan == 0) + gpio_pin = GPIO_21; + else + gpio_pin = GPIO_23; + } else { + gpio_pin = chan; + } err = ice_ptp_cfg_extts(pf, !!on, chan, gpio_pin, rq->extts.flags); @@ -1012,7 +1287,7 @@ int ice_ptp_set_ts_config(struct ice_pf *pf, struct ifreq *ifr) * The timestamp is in ns, so we must convert the result first. */ void -ice_ptp_rx_hwtstamp(struct ice_ring *rx_ring, +ice_ptp_rx_hwtstamp(struct ice_rx_ring *rx_ring, union ice_32b_rx_flex_desc *rx_desc, struct sk_buff *skb) { u32 ts_high; @@ -1037,14 +1312,94 @@ ice_ptp_rx_hwtstamp(struct ice_ring *rx_ring, } } +/** + * ice_ptp_disable_sma_pins_e810t - Disable E810-T SMA pins + * @pf: pointer to the PF structure + * @info: PTP clock info structure + * + * Disable the OS access to the SMA pins. Called to clear out the OS + * indications of pin support when we fail to setup the E810-T SMA control + * register. + */ +static void +ice_ptp_disable_sma_pins_e810t(struct ice_pf *pf, struct ptp_clock_info *info) +{ + struct device *dev = ice_pf_to_dev(pf); + + dev_warn(dev, "Failed to configure E810-T SMA pin control\n"); + + info->enable = NULL; + info->verify = NULL; + info->n_pins = 0; + info->n_ext_ts = 0; + info->n_per_out = 0; +} + +/** + * ice_ptp_setup_sma_pins_e810t - Setup the SMA pins + * @pf: pointer to the PF structure + * @info: PTP clock info structure + * + * Finish setting up the SMA pins by allocating pin_config, and setting it up + * according to the current status of the SMA. On failure, disable all of the + * extended SMA pin support. + */ +static void +ice_ptp_setup_sma_pins_e810t(struct ice_pf *pf, struct ptp_clock_info *info) +{ + struct device *dev = ice_pf_to_dev(pf); + int err; + + /* Allocate memory for kernel pins interface */ + info->pin_config = devm_kcalloc(dev, info->n_pins, + sizeof(*info->pin_config), GFP_KERNEL); + if (!info->pin_config) { + ice_ptp_disable_sma_pins_e810t(pf, info); + return; + } + + /* Read current SMA status */ + err = ice_get_sma_config_e810t(&pf->hw, info->pin_config); + if (err) + ice_ptp_disable_sma_pins_e810t(pf, info); +} + +/** + * ice_ptp_setup_pins_e810t - Setup PTP pins in sysfs + * @pf: pointer to the PF instance + * @info: PTP clock capabilities + */ +static void +ice_ptp_setup_pins_e810t(struct ice_pf *pf, struct ptp_clock_info *info) +{ + /* Check if SMA controller is in the netlist */ + if (ice_is_feature_supported(pf, ICE_F_SMA_CTRL) && + !ice_is_pca9575_present(&pf->hw)) + ice_clear_feature_support(pf, ICE_F_SMA_CTRL); + + if (!ice_is_feature_supported(pf, ICE_F_SMA_CTRL)) { + info->n_ext_ts = N_EXT_TS_E810_NO_SMA; + info->n_per_out = N_PER_OUT_E810T_NO_SMA; + return; + } + + info->n_per_out = N_PER_OUT_E810T; + info->n_ext_ts = N_EXT_TS_E810; + info->n_pins = NUM_PTP_PINS_E810T; + info->verify = ice_verify_pin_e810t; + + /* Complete setup of the SMA pins */ + ice_ptp_setup_sma_pins_e810t(pf, info); +} + /** * ice_ptp_setup_pins_e810 - Setup PTP pins in sysfs * @info: PTP clock capabilities */ static void ice_ptp_setup_pins_e810(struct ptp_clock_info *info) { - info->n_per_out = E810_N_PER_OUT; - info->n_ext_ts = E810_N_EXT_TS; + info->n_per_out = N_PER_OUT_E810; + info->n_ext_ts = N_EXT_TS_E810; } /** @@ -1062,7 +1417,10 @@ ice_ptp_set_funcs_e810(struct ice_pf *pf, struct ptp_clock_info *info) { info->enable = ice_ptp_gpio_enable_e810; - ice_ptp_setup_pins_e810(info); + if (ice_is_e810t(&pf->hw)) + ice_ptp_setup_pins_e810t(pf, info); + else + ice_ptp_setup_pins_e810(info); } /** diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.h b/drivers/net/ethernet/intel/ice/ice_ptp.h index e1c787bd5b96..f71ad317d6c8 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.h +++ b/drivers/net/ethernet/intel/ice/ice_ptp.h @@ -9,12 +9,21 @@ #include "ice_ptp_hw.h" -enum ice_ptp_pin { +enum ice_ptp_pin_e810 { GPIO_20 = 0, GPIO_21, GPIO_22, GPIO_23, - NUM_ICE_PTP_PIN + NUM_PTP_PIN_E810 +}; + +enum ice_ptp_pin_e810t { + GNSS = 0, + SMA1, + UFL1, + SMA2, + UFL2, + NUM_PTP_PINS_E810T }; struct ice_perout_channel { @@ -155,8 +164,11 @@ struct ice_ptp { #define PPS_CLK_SRC_CHAN 2 #define PPS_PIN_INDEX 5 #define TIME_SYNC_PIN_INDEX 4 -#define E810_N_EXT_TS 3 -#define E810_N_PER_OUT 4 +#define N_EXT_TS_E810 3 +#define N_PER_OUT_E810 4 +#define N_PER_OUT_E810T 3 +#define N_PER_OUT_E810T_NO_SMA 2 +#define N_EXT_TS_E810_NO_SMA 2 #if IS_ENABLED(CONFIG_PTP_1588_CLOCK) struct ice_pf; @@ -168,7 +180,7 @@ s8 ice_ptp_request_ts(struct ice_ptp_tx *tx, struct sk_buff *skb); void ice_ptp_process_ts(struct ice_pf *pf); void -ice_ptp_rx_hwtstamp(struct ice_ring *rx_ring, +ice_ptp_rx_hwtstamp(struct ice_rx_ring *rx_ring, union ice_32b_rx_flex_desc *rx_desc, struct sk_buff *skb); void ice_ptp_init(struct ice_pf *pf); void ice_ptp_release(struct ice_pf *pf); @@ -196,7 +208,7 @@ ice_ptp_request_ts(struct ice_ptp_tx *tx, struct sk_buff *skb) static inline void ice_ptp_process_ts(struct ice_pf *pf) { } static inline void -ice_ptp_rx_hwtstamp(struct ice_ring *rx_ring, +ice_ptp_rx_hwtstamp(struct ice_rx_ring *rx_ring, union ice_32b_rx_flex_desc *rx_desc, struct sk_buff *skb) { } static inline void ice_ptp_init(struct ice_pf *pf) { } static inline void ice_ptp_release(struct ice_pf *pf) { } diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c index 3eca0e4eab0b..29f947c0cd2e 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c @@ -649,3 +649,154 @@ int ice_clear_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx) { return ice_clear_phy_tstamp_e810(hw, block, idx); } + +/* E810T SMA functions + * + * The following functions operate specifically on E810T hardware and are used + * to access the extended GPIOs available. + */ + +/** + * ice_get_pca9575_handle + * @hw: pointer to the hw struct + * @pca9575_handle: GPIO controller's handle + * + * Find and return the GPIO controller's handle in the netlist. + * When found - the value will be cached in the hw structure and following calls + * will return cached value + */ +static int +ice_get_pca9575_handle(struct ice_hw *hw, u16 *pca9575_handle) +{ + struct ice_aqc_get_link_topo *cmd; + struct ice_aq_desc desc; + int status; + u8 idx; + + /* If handle was read previously return cached value */ + if (hw->io_expander_handle) { + *pca9575_handle = hw->io_expander_handle; + return 0; + } + + /* If handle was not detected read it from the netlist */ + cmd = &desc.params.get_link_topo; + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_link_topo); + + /* Set node type to GPIO controller */ + cmd->addr.topo_params.node_type_ctx = + (ICE_AQC_LINK_TOPO_NODE_TYPE_M & + ICE_AQC_LINK_TOPO_NODE_TYPE_GPIO_CTRL); + +#define SW_PCA9575_SFP_TOPO_IDX 2 +#define SW_PCA9575_QSFP_TOPO_IDX 1 + + /* Check if the SW IO expander controlling SMA exists in the netlist. */ + if (hw->device_id == ICE_DEV_ID_E810C_SFP) + idx = SW_PCA9575_SFP_TOPO_IDX; + else if (hw->device_id == ICE_DEV_ID_E810C_QSFP) + idx = SW_PCA9575_QSFP_TOPO_IDX; + else + return -EOPNOTSUPP; + + cmd->addr.topo_params.index = idx; + + status = ice_aq_send_cmd(hw, &desc, NULL, 0, NULL); + if (status) + return -EOPNOTSUPP; + + /* Verify if we found the right IO expander type */ + if (desc.params.get_link_topo.node_part_num != + ICE_AQC_GET_LINK_TOPO_NODE_NR_PCA9575) + return -EOPNOTSUPP; + + /* If present save the handle and return it */ + hw->io_expander_handle = + le16_to_cpu(desc.params.get_link_topo.addr.handle); + *pca9575_handle = hw->io_expander_handle; + + return 0; +} + +/** + * ice_read_sma_ctrl_e810t + * @hw: pointer to the hw struct + * @data: pointer to data to be read from the GPIO controller + * + * Read the SMA controller state. It is connected to pins 3-7 of Port 1 of the + * PCA9575 expander, so only bits 3-7 in data are valid. + */ +int ice_read_sma_ctrl_e810t(struct ice_hw *hw, u8 *data) +{ + int status; + u16 handle; + u8 i; + + status = ice_get_pca9575_handle(hw, &handle); + if (status) + return status; + + *data = 0; + + for (i = ICE_SMA_MIN_BIT_E810T; i <= ICE_SMA_MAX_BIT_E810T; i++) { + bool pin; + + status = ice_aq_get_gpio(hw, handle, i + ICE_PCA9575_P1_OFFSET, + &pin, NULL); + if (status) + break; + *data |= (u8)(!pin) << i; + } + + return status; +} + +/** + * ice_write_sma_ctrl_e810t + * @hw: pointer to the hw struct + * @data: data to be written to the GPIO controller + * + * Write the data to the SMA controller. It is connected to pins 3-7 of Port 1 + * of the PCA9575 expander, so only bits 3-7 in data are valid. + */ +int ice_write_sma_ctrl_e810t(struct ice_hw *hw, u8 data) +{ + int status; + u16 handle; + u8 i; + + status = ice_get_pca9575_handle(hw, &handle); + if (status) + return status; + + for (i = ICE_SMA_MIN_BIT_E810T; i <= ICE_SMA_MAX_BIT_E810T; i++) { + bool pin; + + pin = !(data & (1 << i)); + status = ice_aq_set_gpio(hw, handle, i + ICE_PCA9575_P1_OFFSET, + pin, NULL); + if (status) + break; + } + + return status; +} + +/** + * ice_is_pca9575_present + * @hw: pointer to the hw struct + * + * Check if the SW IO expander is present in the netlist + */ +bool ice_is_pca9575_present(struct ice_hw *hw) +{ + u16 handle = 0; + int status; + + if (!ice_is_e810t(hw)) + return false; + + status = ice_get_pca9575_handle(hw, &handle); + + return !status && handle; +} diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h index 55a414e87018..b2984b5c22c1 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h +++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h @@ -30,6 +30,9 @@ int ice_clear_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx); /* E810 family functions */ int ice_ptp_init_phy_e810(struct ice_hw *hw); +int ice_read_sma_ctrl_e810t(struct ice_hw *hw, u8 *data); +int ice_write_sma_ctrl_e810t(struct ice_hw *hw, u8 data); +bool ice_is_pca9575_present(struct ice_hw *hw); #define PFTSYN_SEM_BYTES 4 @@ -76,4 +79,23 @@ int ice_ptp_init_phy_e810(struct ice_hw *hw); #define LOW_TX_MEMORY_BANK_START 0x03090000 #define HIGH_TX_MEMORY_BANK_START 0x03090004 +/* E810T SMA controller pin control */ +#define ICE_SMA1_DIR_EN_E810T BIT(4) +#define ICE_SMA1_TX_EN_E810T BIT(5) +#define ICE_SMA2_UFL2_RX_DIS_E810T BIT(3) +#define ICE_SMA2_DIR_EN_E810T BIT(6) +#define ICE_SMA2_TX_EN_E810T BIT(7) + +#define ICE_SMA1_MASK_E810T (ICE_SMA1_DIR_EN_E810T | \ + ICE_SMA1_TX_EN_E810T) +#define ICE_SMA2_MASK_E810T (ICE_SMA2_UFL2_RX_DIS_E810T | \ + ICE_SMA2_DIR_EN_E810T | \ + ICE_SMA2_TX_EN_E810T) +#define ICE_ALL_SMA_MASK_E810T (ICE_SMA1_MASK_E810T | \ + ICE_SMA2_MASK_E810T) + +#define ICE_SMA_MIN_BIT_E810T 3 +#define ICE_SMA_MAX_BIT_E810T 7 +#define ICE_PCA9575_P1_OFFSET 8 + #endif /* _ICE_PTP_HW_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_repr.c b/drivers/net/ethernet/intel/ice/ice_repr.c index cb83f58d7c71..c49eeea7cb67 100644 --- a/drivers/net/ethernet/intel/ice/ice_repr.c +++ b/drivers/net/ethernet/intel/ice/ice_repr.c @@ -5,6 +5,7 @@ #include "ice_eswitch.h" #include "ice_devlink.h" #include "ice_virtchnl_pf.h" +#include "ice_tc_lib.h" /** * ice_repr_get_sw_port_id - get port ID associated with representor @@ -141,6 +142,55 @@ ice_repr_get_devlink_port(struct net_device *netdev) return &repr->vf->devlink_port; } +static int +ice_repr_setup_tc_cls_flower(struct ice_repr *repr, + struct flow_cls_offload *flower) +{ + switch (flower->command) { + case FLOW_CLS_REPLACE: + return ice_add_cls_flower(repr->netdev, repr->src_vsi, flower); + case FLOW_CLS_DESTROY: + return ice_del_cls_flower(repr->src_vsi, flower); + default: + return -EINVAL; + } +} + +static int +ice_repr_setup_tc_block_cb(enum tc_setup_type type, void *type_data, + void *cb_priv) +{ + struct flow_cls_offload *flower = (struct flow_cls_offload *)type_data; + struct ice_netdev_priv *np = (struct ice_netdev_priv *)cb_priv; + + switch (type) { + case TC_SETUP_CLSFLOWER: + return ice_repr_setup_tc_cls_flower(np->repr, flower); + default: + return -EOPNOTSUPP; + } +} + +static LIST_HEAD(ice_repr_block_cb_list); + +static int +ice_repr_setup_tc(struct net_device *netdev, enum tc_setup_type type, + void *type_data) +{ + struct ice_netdev_priv *np = netdev_priv(netdev); + + switch (type) { + case TC_SETUP_BLOCK: + return flow_block_cb_setup_simple((struct flow_block_offload *) + type_data, + &ice_repr_block_cb_list, + ice_repr_setup_tc_block_cb, + np, np, true); + default: + return -EOPNOTSUPP; + } +} + static const struct net_device_ops ice_repr_netdev_ops = { .ndo_get_phys_port_name = ice_repr_get_phys_port_name, .ndo_get_stats64 = ice_repr_get_stats64, @@ -148,6 +198,7 @@ static const struct net_device_ops ice_repr_netdev_ops = { .ndo_stop = ice_repr_stop, .ndo_start_xmit = ice_eswitch_port_start_xmit, .ndo_get_devlink_port = ice_repr_get_devlink_port, + .ndo_setup_tc = ice_repr_setup_tc, }; /** @@ -170,6 +221,8 @@ ice_repr_reg_netdev(struct net_device *netdev) netdev->netdev_ops = &ice_repr_netdev_ops; ice_set_ethtool_repr_ops(netdev); + netdev->hw_features |= NETIF_F_HW_TC; + netif_carrier_off(netdev); netif_tx_stop_all_queues(netdev); diff --git a/drivers/net/ethernet/intel/ice/ice_sched.c b/drivers/net/ethernet/intel/ice/ice_sched.c index 2d9b10277186..ce3c7bded4cb 100644 --- a/drivers/net/ethernet/intel/ice/ice_sched.c +++ b/drivers/net/ethernet/intel/ice/ice_sched.c @@ -3011,6 +3011,43 @@ static void ice_set_clear_shared_bw(struct ice_bw_type_info *bw_t_info, u32 bw) } } +/** + * ice_sched_save_vsi_bw - save VSI node's BW information + * @pi: port information structure + * @vsi_handle: sw VSI handle + * @tc: traffic class + * @rl_type: rate limit type min, max, or shared + * @bw: bandwidth in Kbps - Kilo bits per sec + * + * Save BW information of VSI type node for post replay use. + */ +static int +ice_sched_save_vsi_bw(struct ice_port_info *pi, u16 vsi_handle, u8 tc, + enum ice_rl_type rl_type, u32 bw) +{ + struct ice_vsi_ctx *vsi_ctx; + + if (!ice_is_vsi_valid(pi->hw, vsi_handle)) + return -EINVAL; + vsi_ctx = ice_get_vsi_ctx(pi->hw, vsi_handle); + if (!vsi_ctx) + return -EINVAL; + switch (rl_type) { + case ICE_MIN_BW: + ice_set_clear_cir_bw(&vsi_ctx->sched.bw_t_info[tc], bw); + break; + case ICE_MAX_BW: + ice_set_clear_eir_bw(&vsi_ctx->sched.bw_t_info[tc], bw); + break; + case ICE_SHARED_BW: + ice_set_clear_shared_bw(&vsi_ctx->sched.bw_t_info[tc], bw); + break; + default: + return -EINVAL; + } + return 0; +} + /** * ice_sched_calc_wakeup - calculate RL profile wakeup parameter * @hw: pointer to the HW struct @@ -3783,6 +3820,153 @@ ice_cfg_q_bw_dflt_lmt(struct ice_port_info *pi, u16 vsi_handle, u8 tc, ICE_SCHED_DFLT_BW); } +/** + * ice_sched_get_node_by_id_type - get node from ID type + * @pi: port information structure + * @id: identifier + * @agg_type: type of aggregator + * @tc: traffic class + * + * This function returns node identified by ID of type aggregator, and + * based on traffic class (TC). This function needs to be called with + * the scheduler lock held. + */ +static struct ice_sched_node * +ice_sched_get_node_by_id_type(struct ice_port_info *pi, u32 id, + enum ice_agg_type agg_type, u8 tc) +{ + struct ice_sched_node *node = NULL; + + switch (agg_type) { + case ICE_AGG_TYPE_VSI: { + struct ice_vsi_ctx *vsi_ctx; + u16 vsi_handle = (u16)id; + + if (!ice_is_vsi_valid(pi->hw, vsi_handle)) + break; + /* Get sched_vsi_info */ + vsi_ctx = ice_get_vsi_ctx(pi->hw, vsi_handle); + if (!vsi_ctx) + break; + node = vsi_ctx->sched.vsi_node[tc]; + break; + } + + case ICE_AGG_TYPE_AGG: { + struct ice_sched_node *tc_node; + + tc_node = ice_sched_get_tc_node(pi, tc); + if (tc_node) + node = ice_sched_get_agg_node(pi, tc_node, id); + break; + } + + default: + break; + } + + return node; +} + +/** + * ice_sched_set_node_bw_lmt_per_tc - set node BW limit per TC + * @pi: port information structure + * @id: ID (software VSI handle or AGG ID) + * @agg_type: aggregator type (VSI or AGG type node) + * @tc: traffic class + * @rl_type: min or max + * @bw: bandwidth in Kbps + * + * This function sets BW limit of VSI or Aggregator scheduling node + * based on TC information from passed in argument BW. + */ +static enum ice_status +ice_sched_set_node_bw_lmt_per_tc(struct ice_port_info *pi, u32 id, + enum ice_agg_type agg_type, u8 tc, + enum ice_rl_type rl_type, u32 bw) +{ + enum ice_status status = ICE_ERR_PARAM; + struct ice_sched_node *node; + + if (!pi) + return status; + + if (rl_type == ICE_UNKNOWN_BW) + return status; + + mutex_lock(&pi->sched_lock); + node = ice_sched_get_node_by_id_type(pi, id, agg_type, tc); + if (!node) { + ice_debug(pi->hw, ICE_DBG_SCHED, "Wrong id, agg type, or tc\n"); + goto exit_set_node_bw_lmt_per_tc; + } + if (bw == ICE_SCHED_DFLT_BW) + status = ice_sched_set_node_bw_dflt_lmt(pi, node, rl_type); + else + status = ice_sched_set_node_bw_lmt(pi, node, rl_type, bw); + +exit_set_node_bw_lmt_per_tc: + mutex_unlock(&pi->sched_lock); + return status; +} + +/** + * ice_cfg_vsi_bw_lmt_per_tc - configure VSI BW limit per TC + * @pi: port information structure + * @vsi_handle: software VSI handle + * @tc: traffic class + * @rl_type: min or max + * @bw: bandwidth in Kbps + * + * This function configures BW limit of VSI scheduling node based on TC + * information. + */ +enum ice_status +ice_cfg_vsi_bw_lmt_per_tc(struct ice_port_info *pi, u16 vsi_handle, u8 tc, + enum ice_rl_type rl_type, u32 bw) +{ + int status; + + status = ice_sched_set_node_bw_lmt_per_tc(pi, vsi_handle, + ICE_AGG_TYPE_VSI, + tc, rl_type, bw); + if (!status) { + mutex_lock(&pi->sched_lock); + status = ice_sched_save_vsi_bw(pi, vsi_handle, tc, rl_type, bw); + mutex_unlock(&pi->sched_lock); + } + return status; +} + +/** + * ice_cfg_vsi_bw_dflt_lmt_per_tc - configure default VSI BW limit per TC + * @pi: port information structure + * @vsi_handle: software VSI handle + * @tc: traffic class + * @rl_type: min or max + * + * This function configures default BW limit of VSI scheduling node based on TC + * information. + */ +enum ice_status +ice_cfg_vsi_bw_dflt_lmt_per_tc(struct ice_port_info *pi, u16 vsi_handle, u8 tc, + enum ice_rl_type rl_type) +{ + int status; + + status = ice_sched_set_node_bw_lmt_per_tc(pi, vsi_handle, + ICE_AGG_TYPE_VSI, + tc, rl_type, + ICE_SCHED_DFLT_BW); + if (!status) { + mutex_lock(&pi->sched_lock); + status = ice_sched_save_vsi_bw(pi, vsi_handle, tc, rl_type, + ICE_SCHED_DFLT_BW); + mutex_unlock(&pi->sched_lock); + } + return status; +} + /** * ice_cfg_rl_burst_size - Set burst size value * @hw: pointer to the HW struct diff --git a/drivers/net/ethernet/intel/ice/ice_sched.h b/drivers/net/ethernet/intel/ice/ice_sched.h index fdf7a5882f07..6bddcbecaf5e 100644 --- a/drivers/net/ethernet/intel/ice/ice_sched.h +++ b/drivers/net/ethernet/intel/ice/ice_sched.h @@ -58,6 +58,8 @@ struct ice_sched_agg_info { DECLARE_BITMAP(tc_bitmap, ICE_MAX_TRAFFIC_CLASS); u32 agg_id; enum ice_agg_type agg_type; + /* bw_t_info saves aggregator BW information */ + struct ice_bw_type_info bw_t_info[ICE_MAX_TRAFFIC_CLASS]; /* save aggregator TC bitmap */ DECLARE_BITMAP(replay_tc_bitmap, ICE_MAX_TRAFFIC_CLASS); }; @@ -104,6 +106,12 @@ ice_cfg_q_bw_lmt(struct ice_port_info *pi, u16 vsi_handle, u8 tc, enum ice_status ice_cfg_q_bw_dflt_lmt(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u16 q_handle, enum ice_rl_type rl_type); +enum ice_status +ice_cfg_vsi_bw_lmt_per_tc(struct ice_port_info *pi, u16 vsi_handle, u8 tc, + enum ice_rl_type rl_type, u32 bw); +enum ice_status +ice_cfg_vsi_bw_dflt_lmt_per_tc(struct ice_port_info *pi, u16 vsi_handle, u8 tc, + enum ice_rl_type rl_type); enum ice_status ice_cfg_rl_burst_size(struct ice_hw *hw, u32 bytes); void ice_sched_replay_agg_vsi_preinit(struct ice_hw *hw); void ice_sched_replay_agg(struct ice_hw *hw); diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c index 1e86a6dba454..2742e1c1e337 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.c +++ b/drivers/net/ethernet/intel/ice/ice_switch.c @@ -8,6 +8,7 @@ #define ICE_ETH_ETHTYPE_OFFSET 12 #define ICE_ETH_VLAN_TCI_OFFSET 14 #define ICE_MAX_VLAN_ID 0xFFF +#define ICE_IPV6_ETHER_ID 0x86DD /* Dummy ethernet header needed in the ice_aqc_sw_rules_elem * struct to configure any switch filter rules. @@ -29,6 +30,290 @@ static const u8 dummy_eth_header[DUMMY_ETH_HDR_LEN] = { 0x2, 0, 0, 0, 0, 0, 0x2, 0, 0, 0, 0, 0, 0x81, 0, 0, 0}; +struct ice_dummy_pkt_offsets { + enum ice_protocol_type type; + u16 offset; /* ICE_PROTOCOL_LAST indicates end of list */ +}; + +/* offset info for MAC + IPv4 + UDP dummy packet */ +static const struct ice_dummy_pkt_offsets dummy_udp_packet_offsets[] = { + { ICE_MAC_OFOS, 0 }, + { ICE_ETYPE_OL, 12 }, + { ICE_IPV4_OFOS, 14 }, + { ICE_UDP_ILOS, 34 }, + { ICE_PROTOCOL_LAST, 0 }, +}; + +/* Dummy packet for MAC + IPv4 + UDP */ +static const u8 dummy_udp_packet[] = { + 0x00, 0x00, 0x00, 0x00, /* ICE_MAC_OFOS 0 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x08, 0x00, /* ICE_ETYPE_OL 12 */ + + 0x45, 0x00, 0x00, 0x1c, /* ICE_IPV4_OFOS 14 */ + 0x00, 0x01, 0x00, 0x00, + 0x00, 0x11, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, 0x00, 0x00, /* ICE_UDP_ILOS 34 */ + 0x00, 0x08, 0x00, 0x00, + + 0x00, 0x00, /* 2 bytes for 4 byte alignment */ +}; + +/* offset info for MAC + VLAN + IPv4 + UDP dummy packet */ +static const struct ice_dummy_pkt_offsets dummy_vlan_udp_packet_offsets[] = { + { ICE_MAC_OFOS, 0 }, + { ICE_VLAN_OFOS, 12 }, + { ICE_ETYPE_OL, 16 }, + { ICE_IPV4_OFOS, 18 }, + { ICE_UDP_ILOS, 38 }, + { ICE_PROTOCOL_LAST, 0 }, +}; + +/* C-tag (801.1Q), IPv4:UDP dummy packet */ +static const u8 dummy_vlan_udp_packet[] = { + 0x00, 0x00, 0x00, 0x00, /* ICE_MAC_OFOS 0 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x81, 0x00, 0x00, 0x00, /* ICE_VLAN_OFOS 12 */ + + 0x08, 0x00, /* ICE_ETYPE_OL 16 */ + + 0x45, 0x00, 0x00, 0x1c, /* ICE_IPV4_OFOS 18 */ + 0x00, 0x01, 0x00, 0x00, + 0x00, 0x11, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, 0x00, 0x00, /* ICE_UDP_ILOS 38 */ + 0x00, 0x08, 0x00, 0x00, + + 0x00, 0x00, /* 2 bytes for 4 byte alignment */ +}; + +/* offset info for MAC + IPv4 + TCP dummy packet */ +static const struct ice_dummy_pkt_offsets dummy_tcp_packet_offsets[] = { + { ICE_MAC_OFOS, 0 }, + { ICE_ETYPE_OL, 12 }, + { ICE_IPV4_OFOS, 14 }, + { ICE_TCP_IL, 34 }, + { ICE_PROTOCOL_LAST, 0 }, +}; + +/* Dummy packet for MAC + IPv4 + TCP */ +static const u8 dummy_tcp_packet[] = { + 0x00, 0x00, 0x00, 0x00, /* ICE_MAC_OFOS 0 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x08, 0x00, /* ICE_ETYPE_OL 12 */ + + 0x45, 0x00, 0x00, 0x28, /* ICE_IPV4_OFOS 14 */ + 0x00, 0x01, 0x00, 0x00, + 0x00, 0x06, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, 0x00, 0x00, /* ICE_TCP_IL 34 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x50, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, /* 2 bytes for 4 byte alignment */ +}; + +/* offset info for MAC + VLAN (C-tag, 802.1Q) + IPv4 + TCP dummy packet */ +static const struct ice_dummy_pkt_offsets dummy_vlan_tcp_packet_offsets[] = { + { ICE_MAC_OFOS, 0 }, + { ICE_VLAN_OFOS, 12 }, + { ICE_ETYPE_OL, 16 }, + { ICE_IPV4_OFOS, 18 }, + { ICE_TCP_IL, 38 }, + { ICE_PROTOCOL_LAST, 0 }, +}; + +/* C-tag (801.1Q), IPv4:TCP dummy packet */ +static const u8 dummy_vlan_tcp_packet[] = { + 0x00, 0x00, 0x00, 0x00, /* ICE_MAC_OFOS 0 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x81, 0x00, 0x00, 0x00, /* ICE_VLAN_OFOS 12 */ + + 0x08, 0x00, /* ICE_ETYPE_OL 16 */ + + 0x45, 0x00, 0x00, 0x28, /* ICE_IPV4_OFOS 18 */ + 0x00, 0x01, 0x00, 0x00, + 0x00, 0x06, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, 0x00, 0x00, /* ICE_TCP_IL 38 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x50, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, /* 2 bytes for 4 byte alignment */ +}; + +static const struct ice_dummy_pkt_offsets dummy_tcp_ipv6_packet_offsets[] = { + { ICE_MAC_OFOS, 0 }, + { ICE_ETYPE_OL, 12 }, + { ICE_IPV6_OFOS, 14 }, + { ICE_TCP_IL, 54 }, + { ICE_PROTOCOL_LAST, 0 }, +}; + +static const u8 dummy_tcp_ipv6_packet[] = { + 0x00, 0x00, 0x00, 0x00, /* ICE_MAC_OFOS 0 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x86, 0xDD, /* ICE_ETYPE_OL 12 */ + + 0x60, 0x00, 0x00, 0x00, /* ICE_IPV6_OFOS 40 */ + 0x00, 0x14, 0x06, 0x00, /* Next header is TCP */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, 0x00, 0x00, /* ICE_TCP_IL 54 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x50, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, /* 2 bytes for 4 byte alignment */ +}; + +/* C-tag (802.1Q): IPv6 + TCP */ +static const struct ice_dummy_pkt_offsets +dummy_vlan_tcp_ipv6_packet_offsets[] = { + { ICE_MAC_OFOS, 0 }, + { ICE_VLAN_OFOS, 12 }, + { ICE_ETYPE_OL, 16 }, + { ICE_IPV6_OFOS, 18 }, + { ICE_TCP_IL, 58 }, + { ICE_PROTOCOL_LAST, 0 }, +}; + +/* C-tag (802.1Q), IPv6 + TCP dummy packet */ +static const u8 dummy_vlan_tcp_ipv6_packet[] = { + 0x00, 0x00, 0x00, 0x00, /* ICE_MAC_OFOS 0 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x81, 0x00, 0x00, 0x00, /* ICE_VLAN_OFOS 12 */ + + 0x86, 0xDD, /* ICE_ETYPE_OL 16 */ + + 0x60, 0x00, 0x00, 0x00, /* ICE_IPV6_OFOS 18 */ + 0x00, 0x14, 0x06, 0x00, /* Next header is TCP */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, 0x00, 0x00, /* ICE_TCP_IL 58 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x50, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, /* 2 bytes for 4 byte alignment */ +}; + +/* IPv6 + UDP */ +static const struct ice_dummy_pkt_offsets dummy_udp_ipv6_packet_offsets[] = { + { ICE_MAC_OFOS, 0 }, + { ICE_ETYPE_OL, 12 }, + { ICE_IPV6_OFOS, 14 }, + { ICE_UDP_ILOS, 54 }, + { ICE_PROTOCOL_LAST, 0 }, +}; + +/* IPv6 + UDP dummy packet */ +static const u8 dummy_udp_ipv6_packet[] = { + 0x00, 0x00, 0x00, 0x00, /* ICE_MAC_OFOS 0 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x86, 0xDD, /* ICE_ETYPE_OL 12 */ + + 0x60, 0x00, 0x00, 0x00, /* ICE_IPV6_OFOS 40 */ + 0x00, 0x10, 0x11, 0x00, /* Next header UDP */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, 0x00, 0x00, /* ICE_UDP_ILOS 54 */ + 0x00, 0x10, 0x00, 0x00, + + 0x00, 0x00, 0x00, 0x00, /* needed for ESP packets */ + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, /* 2 bytes for 4 byte alignment */ +}; + +/* C-tag (802.1Q): IPv6 + UDP */ +static const struct ice_dummy_pkt_offsets +dummy_vlan_udp_ipv6_packet_offsets[] = { + { ICE_MAC_OFOS, 0 }, + { ICE_VLAN_OFOS, 12 }, + { ICE_ETYPE_OL, 16 }, + { ICE_IPV6_OFOS, 18 }, + { ICE_UDP_ILOS, 58 }, + { ICE_PROTOCOL_LAST, 0 }, +}; + +/* C-tag (802.1Q), IPv6 + UDP dummy packet */ +static const u8 dummy_vlan_udp_ipv6_packet[] = { + 0x00, 0x00, 0x00, 0x00, /* ICE_MAC_OFOS 0 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x81, 0x00, 0x00, 0x00,/* ICE_VLAN_OFOS 12 */ + + 0x86, 0xDD, /* ICE_ETYPE_OL 16 */ + + 0x60, 0x00, 0x00, 0x00, /* ICE_IPV6_OFOS 18 */ + 0x00, 0x08, 0x11, 0x00, /* Next header UDP */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, 0x00, 0x00, /* ICE_UDP_ILOS 58 */ + 0x00, 0x08, 0x00, 0x00, + + 0x00, 0x00, /* 2 bytes for 4 byte alignment */ +}; + #define ICE_SW_RULE_RX_TX_ETH_HDR_SIZE \ (offsetof(struct ice_aqc_sw_rules_elem, pdata.lkup_tx_rx.hdr) + \ (DUMMY_ETH_HDR_LEN * \ @@ -42,6 +327,14 @@ static const u8 dummy_eth_header[DUMMY_ETH_HDR_LEN] = { 0x2, 0, 0, 0, 0, 0, (offsetof(struct ice_aqc_sw_rules_elem, pdata.vsi_list.vsi) + \ ((n) * sizeof(((struct ice_sw_rule_vsi_list *)0)->vsi[0]))) +/* this is a recipe to profile association bitmap */ +static DECLARE_BITMAP(recipe_to_profile[ICE_MAX_NUM_RECIPES], + ICE_MAX_NUM_PROFILES); + +/* this is a profile to recipe association bitmap */ +static DECLARE_BITMAP(profile_to_recipe[ICE_MAX_NUM_PROFILES], + ICE_MAX_NUM_RECIPES); + /** * ice_init_def_sw_recp - initialize the recipe book keeping tables * @hw: pointer to the HW struct @@ -59,10 +352,11 @@ enum ice_status ice_init_def_sw_recp(struct ice_hw *hw) if (!recps) return ICE_ERR_NO_MEMORY; - for (i = 0; i < ICE_SW_LKUP_LAST; i++) { + for (i = 0; i < ICE_MAX_NUM_RECIPES; i++) { recps[i].root_rid = i; INIT_LIST_HEAD(&recps[i].filt_rules); INIT_LIST_HEAD(&recps[i].filt_replay_rules); + INIT_LIST_HEAD(&recps[i].rg_list); mutex_init(&recps[i].filt_rule_lock); } @@ -543,6 +837,358 @@ ice_aq_sw_rules(struct ice_hw *hw, void *rule_list, u16 rule_list_sz, return status; } +/** + * ice_aq_add_recipe - add switch recipe + * @hw: pointer to the HW struct + * @s_recipe_list: pointer to switch rule population list + * @num_recipes: number of switch recipes in the list + * @cd: pointer to command details structure or NULL + * + * Add(0x0290) + */ +static enum ice_status +ice_aq_add_recipe(struct ice_hw *hw, + struct ice_aqc_recipe_data_elem *s_recipe_list, + u16 num_recipes, struct ice_sq_cd *cd) +{ + struct ice_aqc_add_get_recipe *cmd; + struct ice_aq_desc desc; + u16 buf_size; + + cmd = &desc.params.add_get_recipe; + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_add_recipe); + + cmd->num_sub_recipes = cpu_to_le16(num_recipes); + desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); + + buf_size = num_recipes * sizeof(*s_recipe_list); + + return ice_aq_send_cmd(hw, &desc, s_recipe_list, buf_size, cd); +} + +/** + * ice_aq_get_recipe - get switch recipe + * @hw: pointer to the HW struct + * @s_recipe_list: pointer to switch rule population list + * @num_recipes: pointer to the number of recipes (input and output) + * @recipe_root: root recipe number of recipe(s) to retrieve + * @cd: pointer to command details structure or NULL + * + * Get(0x0292) + * + * On input, *num_recipes should equal the number of entries in s_recipe_list. + * On output, *num_recipes will equal the number of entries returned in + * s_recipe_list. + * + * The caller must supply enough space in s_recipe_list to hold all possible + * recipes and *num_recipes must equal ICE_MAX_NUM_RECIPES. + */ +static enum ice_status +ice_aq_get_recipe(struct ice_hw *hw, + struct ice_aqc_recipe_data_elem *s_recipe_list, + u16 *num_recipes, u16 recipe_root, struct ice_sq_cd *cd) +{ + struct ice_aqc_add_get_recipe *cmd; + struct ice_aq_desc desc; + enum ice_status status; + u16 buf_size; + + if (*num_recipes != ICE_MAX_NUM_RECIPES) + return ICE_ERR_PARAM; + + cmd = &desc.params.add_get_recipe; + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_recipe); + + cmd->return_index = cpu_to_le16(recipe_root); + cmd->num_sub_recipes = 0; + + buf_size = *num_recipes * sizeof(*s_recipe_list); + + status = ice_aq_send_cmd(hw, &desc, s_recipe_list, buf_size, cd); + *num_recipes = le16_to_cpu(cmd->num_sub_recipes); + + return status; +} + +/** + * ice_aq_map_recipe_to_profile - Map recipe to packet profile + * @hw: pointer to the HW struct + * @profile_id: package profile ID to associate the recipe with + * @r_bitmap: Recipe bitmap filled in and need to be returned as response + * @cd: pointer to command details structure or NULL + * Recipe to profile association (0x0291) + */ +static enum ice_status +ice_aq_map_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u8 *r_bitmap, + struct ice_sq_cd *cd) +{ + struct ice_aqc_recipe_to_profile *cmd; + struct ice_aq_desc desc; + + cmd = &desc.params.recipe_to_profile; + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_recipe_to_profile); + cmd->profile_id = cpu_to_le16(profile_id); + /* Set the recipe ID bit in the bitmask to let the device know which + * profile we are associating the recipe to + */ + memcpy(cmd->recipe_assoc, r_bitmap, sizeof(cmd->recipe_assoc)); + + return ice_aq_send_cmd(hw, &desc, NULL, 0, cd); +} + +/** + * ice_aq_get_recipe_to_profile - Map recipe to packet profile + * @hw: pointer to the HW struct + * @profile_id: package profile ID to associate the recipe with + * @r_bitmap: Recipe bitmap filled in and need to be returned as response + * @cd: pointer to command details structure or NULL + * Associate profile ID with given recipe (0x0293) + */ +static enum ice_status +ice_aq_get_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u8 *r_bitmap, + struct ice_sq_cd *cd) +{ + struct ice_aqc_recipe_to_profile *cmd; + struct ice_aq_desc desc; + enum ice_status status; + + cmd = &desc.params.recipe_to_profile; + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_recipe_to_profile); + cmd->profile_id = cpu_to_le16(profile_id); + + status = ice_aq_send_cmd(hw, &desc, NULL, 0, cd); + if (!status) + memcpy(r_bitmap, cmd->recipe_assoc, sizeof(cmd->recipe_assoc)); + + return status; +} + +/** + * ice_alloc_recipe - add recipe resource + * @hw: pointer to the hardware structure + * @rid: recipe ID returned as response to AQ call + */ +static enum ice_status ice_alloc_recipe(struct ice_hw *hw, u16 *rid) +{ + struct ice_aqc_alloc_free_res_elem *sw_buf; + enum ice_status status; + u16 buf_len; + + buf_len = struct_size(sw_buf, elem, 1); + sw_buf = kzalloc(buf_len, GFP_KERNEL); + if (!sw_buf) + return ICE_ERR_NO_MEMORY; + + sw_buf->num_elems = cpu_to_le16(1); + sw_buf->res_type = cpu_to_le16((ICE_AQC_RES_TYPE_RECIPE << + ICE_AQC_RES_TYPE_S) | + ICE_AQC_RES_TYPE_FLAG_SHARED); + status = ice_aq_alloc_free_res(hw, 1, sw_buf, buf_len, + ice_aqc_opc_alloc_res, NULL); + if (!status) + *rid = le16_to_cpu(sw_buf->elem[0].e.sw_resp); + kfree(sw_buf); + + return status; +} + +/** + * ice_get_recp_to_prof_map - updates recipe to profile mapping + * @hw: pointer to hardware structure + * + * This function is used to populate recipe_to_profile matrix where index to + * this array is the recipe ID and the element is the mapping of which profiles + * is this recipe mapped to. + */ +static void ice_get_recp_to_prof_map(struct ice_hw *hw) +{ + DECLARE_BITMAP(r_bitmap, ICE_MAX_NUM_RECIPES); + u16 i; + + for (i = 0; i < hw->switch_info->max_used_prof_index + 1; i++) { + u16 j; + + bitmap_zero(profile_to_recipe[i], ICE_MAX_NUM_RECIPES); + bitmap_zero(r_bitmap, ICE_MAX_NUM_RECIPES); + if (ice_aq_get_recipe_to_profile(hw, i, (u8 *)r_bitmap, NULL)) + continue; + bitmap_copy(profile_to_recipe[i], r_bitmap, + ICE_MAX_NUM_RECIPES); + for_each_set_bit(j, r_bitmap, ICE_MAX_NUM_RECIPES) + set_bit(i, recipe_to_profile[j]); + } +} + +/** + * ice_collect_result_idx - copy result index values + * @buf: buffer that contains the result index + * @recp: the recipe struct to copy data into + */ +static void +ice_collect_result_idx(struct ice_aqc_recipe_data_elem *buf, + struct ice_sw_recipe *recp) +{ + if (buf->content.result_indx & ICE_AQ_RECIPE_RESULT_EN) + set_bit(buf->content.result_indx & ~ICE_AQ_RECIPE_RESULT_EN, + recp->res_idxs); +} + +/** + * ice_get_recp_frm_fw - update SW bookkeeping from FW recipe entries + * @hw: pointer to hardware structure + * @recps: struct that we need to populate + * @rid: recipe ID that we are populating + * @refresh_required: true if we should get recipe to profile mapping from FW + * + * This function is used to populate all the necessary entries into our + * bookkeeping so that we have a current list of all the recipes that are + * programmed in the firmware. + */ +static enum ice_status +ice_get_recp_frm_fw(struct ice_hw *hw, struct ice_sw_recipe *recps, u8 rid, + bool *refresh_required) +{ + DECLARE_BITMAP(result_bm, ICE_MAX_FV_WORDS); + struct ice_aqc_recipe_data_elem *tmp; + u16 num_recps = ICE_MAX_NUM_RECIPES; + struct ice_prot_lkup_ext *lkup_exts; + enum ice_status status; + u8 fv_word_idx = 0; + u16 sub_recps; + + bitmap_zero(result_bm, ICE_MAX_FV_WORDS); + + /* we need a buffer big enough to accommodate all the recipes */ + tmp = kcalloc(ICE_MAX_NUM_RECIPES, sizeof(*tmp), GFP_KERNEL); + if (!tmp) + return ICE_ERR_NO_MEMORY; + + tmp[0].recipe_indx = rid; + status = ice_aq_get_recipe(hw, tmp, &num_recps, rid, NULL); + /* non-zero status meaning recipe doesn't exist */ + if (status) + goto err_unroll; + + /* Get recipe to profile map so that we can get the fv from lkups that + * we read for a recipe from FW. Since we want to minimize the number of + * times we make this FW call, just make one call and cache the copy + * until a new recipe is added. This operation is only required the + * first time to get the changes from FW. Then to search existing + * entries we don't need to update the cache again until another recipe + * gets added. + */ + if (*refresh_required) { + ice_get_recp_to_prof_map(hw); + *refresh_required = false; + } + + /* Start populating all the entries for recps[rid] based on lkups from + * firmware. Note that we are only creating the root recipe in our + * database. + */ + lkup_exts = &recps[rid].lkup_exts; + + for (sub_recps = 0; sub_recps < num_recps; sub_recps++) { + struct ice_aqc_recipe_data_elem root_bufs = tmp[sub_recps]; + struct ice_recp_grp_entry *rg_entry; + u8 i, prof, idx, prot = 0; + bool is_root; + u16 off = 0; + + rg_entry = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*rg_entry), + GFP_KERNEL); + if (!rg_entry) { + status = ICE_ERR_NO_MEMORY; + goto err_unroll; + } + + idx = root_bufs.recipe_indx; + is_root = root_bufs.content.rid & ICE_AQ_RECIPE_ID_IS_ROOT; + + /* Mark all result indices in this chain */ + if (root_bufs.content.result_indx & ICE_AQ_RECIPE_RESULT_EN) + set_bit(root_bufs.content.result_indx & ~ICE_AQ_RECIPE_RESULT_EN, + result_bm); + + /* get the first profile that is associated with rid */ + prof = find_first_bit(recipe_to_profile[idx], + ICE_MAX_NUM_PROFILES); + for (i = 0; i < ICE_NUM_WORDS_RECIPE; i++) { + u8 lkup_indx = root_bufs.content.lkup_indx[i + 1]; + + rg_entry->fv_idx[i] = lkup_indx; + rg_entry->fv_mask[i] = + le16_to_cpu(root_bufs.content.mask[i + 1]); + + /* If the recipe is a chained recipe then all its + * child recipe's result will have a result index. + * To fill fv_words we should not use those result + * index, we only need the protocol ids and offsets. + * We will skip all the fv_idx which stores result + * index in them. We also need to skip any fv_idx which + * has ICE_AQ_RECIPE_LKUP_IGNORE or 0 since it isn't a + * valid offset value. + */ + if (test_bit(rg_entry->fv_idx[i], hw->switch_info->prof_res_bm[prof]) || + rg_entry->fv_idx[i] & ICE_AQ_RECIPE_LKUP_IGNORE || + rg_entry->fv_idx[i] == 0) + continue; + + ice_find_prot_off(hw, ICE_BLK_SW, prof, + rg_entry->fv_idx[i], &prot, &off); + lkup_exts->fv_words[fv_word_idx].prot_id = prot; + lkup_exts->fv_words[fv_word_idx].off = off; + lkup_exts->field_mask[fv_word_idx] = + rg_entry->fv_mask[i]; + fv_word_idx++; + } + /* populate rg_list with the data from the child entry of this + * recipe + */ + list_add(&rg_entry->l_entry, &recps[rid].rg_list); + + /* Propagate some data to the recipe database */ + recps[idx].is_root = !!is_root; + recps[idx].priority = root_bufs.content.act_ctrl_fwd_priority; + bitmap_zero(recps[idx].res_idxs, ICE_MAX_FV_WORDS); + if (root_bufs.content.result_indx & ICE_AQ_RECIPE_RESULT_EN) { + recps[idx].chain_idx = root_bufs.content.result_indx & + ~ICE_AQ_RECIPE_RESULT_EN; + set_bit(recps[idx].chain_idx, recps[idx].res_idxs); + } else { + recps[idx].chain_idx = ICE_INVAL_CHAIN_IND; + } + + if (!is_root) + continue; + + /* Only do the following for root recipes entries */ + memcpy(recps[idx].r_bitmap, root_bufs.recipe_bitmap, + sizeof(recps[idx].r_bitmap)); + recps[idx].root_rid = root_bufs.content.rid & + ~ICE_AQ_RECIPE_ID_IS_ROOT; + recps[idx].priority = root_bufs.content.act_ctrl_fwd_priority; + } + + /* Complete initialization of the root recipe entry */ + lkup_exts->n_val_words = fv_word_idx; + recps[rid].big_recp = (num_recps > 1); + recps[rid].n_grp_count = (u8)num_recps; + recps[rid].root_buf = devm_kmemdup(ice_hw_to_dev(hw), tmp, + recps[rid].n_grp_count * sizeof(*recps[rid].root_buf), + GFP_KERNEL); + if (!recps[rid].root_buf) + goto err_unroll; + + /* Copy result indexes */ + bitmap_copy(recps[rid].res_idxs, result_bm, ICE_MAX_FV_WORDS); + recps[rid].recp_created = true; + +err_unroll: + kfree(tmp); + return status; +} + /* ice_init_port_info - Initialize port_info with switch configuration data * @pi: pointer to port_info * @vsi_port_num: VSI number or port number @@ -1626,6 +2272,125 @@ exit: return status; } +/** + * ice_mac_fltr_exist - does this MAC filter exist for given VSI + * @hw: pointer to the hardware structure + * @mac: MAC address to be checked (for MAC filter) + * @vsi_handle: check MAC filter for this VSI + */ +bool ice_mac_fltr_exist(struct ice_hw *hw, u8 *mac, u16 vsi_handle) +{ + struct ice_fltr_mgmt_list_entry *entry; + struct list_head *rule_head; + struct ice_switch_info *sw; + struct mutex *rule_lock; /* Lock to protect filter rule list */ + u16 hw_vsi_id; + + if (!ice_is_vsi_valid(hw, vsi_handle)) + return false; + + hw_vsi_id = ice_get_hw_vsi_num(hw, vsi_handle); + sw = hw->switch_info; + rule_head = &sw->recp_list[ICE_SW_LKUP_MAC].filt_rules; + if (!rule_head) + return false; + + rule_lock = &sw->recp_list[ICE_SW_LKUP_MAC].filt_rule_lock; + mutex_lock(rule_lock); + list_for_each_entry(entry, rule_head, list_entry) { + struct ice_fltr_info *f_info = &entry->fltr_info; + u8 *mac_addr = &f_info->l_data.mac.mac_addr[0]; + + if (is_zero_ether_addr(mac_addr)) + continue; + + if (f_info->flag != ICE_FLTR_TX || + f_info->src_id != ICE_SRC_ID_VSI || + f_info->lkup_type != ICE_SW_LKUP_MAC || + f_info->fltr_act != ICE_FWD_TO_VSI || + hw_vsi_id != f_info->fwd_id.hw_vsi_id) + continue; + + if (ether_addr_equal(mac, mac_addr)) { + mutex_unlock(rule_lock); + return true; + } + } + mutex_unlock(rule_lock); + return false; +} + +/** + * ice_vlan_fltr_exist - does this VLAN filter exist for given VSI + * @hw: pointer to the hardware structure + * @vlan_id: VLAN ID + * @vsi_handle: check MAC filter for this VSI + */ +bool ice_vlan_fltr_exist(struct ice_hw *hw, u16 vlan_id, u16 vsi_handle) +{ + struct ice_fltr_mgmt_list_entry *entry; + struct list_head *rule_head; + struct ice_switch_info *sw; + struct mutex *rule_lock; /* Lock to protect filter rule list */ + u16 hw_vsi_id; + + if (vlan_id > ICE_MAX_VLAN_ID) + return false; + + if (!ice_is_vsi_valid(hw, vsi_handle)) + return false; + + hw_vsi_id = ice_get_hw_vsi_num(hw, vsi_handle); + sw = hw->switch_info; + rule_head = &sw->recp_list[ICE_SW_LKUP_VLAN].filt_rules; + if (!rule_head) + return false; + + rule_lock = &sw->recp_list[ICE_SW_LKUP_VLAN].filt_rule_lock; + mutex_lock(rule_lock); + list_for_each_entry(entry, rule_head, list_entry) { + struct ice_fltr_info *f_info = &entry->fltr_info; + u16 entry_vlan_id = f_info->l_data.vlan.vlan_id; + struct ice_vsi_list_map_info *map_info; + + if (entry_vlan_id > ICE_MAX_VLAN_ID) + continue; + + if (f_info->flag != ICE_FLTR_TX || + f_info->src_id != ICE_SRC_ID_VSI || + f_info->lkup_type != ICE_SW_LKUP_VLAN) + continue; + + /* Only allowed filter action are FWD_TO_VSI/_VSI_LIST */ + if (f_info->fltr_act != ICE_FWD_TO_VSI && + f_info->fltr_act != ICE_FWD_TO_VSI_LIST) + continue; + + if (f_info->fltr_act == ICE_FWD_TO_VSI) { + if (hw_vsi_id != f_info->fwd_id.hw_vsi_id) + continue; + } else if (f_info->fltr_act == ICE_FWD_TO_VSI_LIST) { + /* If filter_action is FWD_TO_VSI_LIST, make sure + * that VSI being checked is part of VSI list + */ + if (entry->vsi_count == 1 && + entry->vsi_list_info) { + map_info = entry->vsi_list_info; + if (!test_bit(vsi_handle, map_info->vsi_map)) + continue; + } + } + + if (vlan_id == entry_vlan_id) { + mutex_unlock(rule_lock); + return true; + } + } + mutex_unlock(rule_lock); + + return false; +} + /** * ice_add_mac - Add a MAC address based filter rule * @hw: pointer to the hardware structure @@ -2036,6 +2801,27 @@ ice_rem_sw_rule_info(struct ice_hw *hw, struct list_head *rule_head) } } +/** + * ice_rem_adv_rule_info + * @hw: pointer to the hardware structure + * @rule_head: pointer to the switch list structure that we want to delete + */ +static void +ice_rem_adv_rule_info(struct ice_hw *hw, struct list_head *rule_head) +{ + struct ice_adv_fltr_mgmt_list_entry *tmp_entry; + struct ice_adv_fltr_mgmt_list_entry *lst_itr; + + if (list_empty(rule_head)) + return; + + list_for_each_entry_safe(lst_itr, tmp_entry, rule_head, list_entry) { + list_del(&lst_itr->list_entry); + devm_kfree(ice_hw_to_dev(hw), lst_itr->lkups); + devm_kfree(ice_hw_to_dev(hw), lst_itr); + } +} + /** * ice_cfg_dflt_vsi - change state of VSI to set/clear default * @hw: pointer to the hardware structure @@ -2773,6 +3559,1459 @@ ice_free_res_cntr(struct ice_hw *hw, u8 type, u8 alloc_shared, u16 num_items, return status; } +/* This is mapping table entry that maps every word within a given protocol + * structure to the real byte offset as per the specification of that + * protocol header. + * for example dst address is 3 words in ethertype header and corresponding + * bytes are 0, 2, 3 in the actual packet header and src address is at 4, 6, 8 + * IMPORTANT: Every structure part of "ice_prot_hdr" union should have a + * matching entry describing its field. This needs to be updated if new + * structure is added to that union. + */ +static const struct ice_prot_ext_tbl_entry ice_prot_ext[ICE_PROTOCOL_LAST] = { + { ICE_MAC_OFOS, { 0, 2, 4, 6, 8, 10, 12 } }, + { ICE_MAC_IL, { 0, 2, 4, 6, 8, 10, 12 } }, + { ICE_ETYPE_OL, { 0 } }, + { ICE_VLAN_OFOS, { 2, 0 } }, + { ICE_IPV4_OFOS, { 0, 2, 4, 6, 8, 10, 12, 14, 16, 18 } }, + { ICE_IPV4_IL, { 0, 2, 4, 6, 8, 10, 12, 14, 16, 18 } }, + { ICE_IPV6_OFOS, { 0, 2, 4, 6, 8, 10, 12, 14, 16, 18, 20, 22, 24, + 26, 28, 30, 32, 34, 36, 38 } }, + { ICE_IPV6_IL, { 0, 2, 4, 6, 8, 10, 12, 14, 16, 18, 20, 22, 24, + 26, 28, 30, 32, 34, 36, 38 } }, + { ICE_TCP_IL, { 0, 2 } }, + { ICE_UDP_OF, { 0, 2 } }, + { ICE_UDP_ILOS, { 0, 2 } }, +}; + +static struct ice_protocol_entry ice_prot_id_tbl[ICE_PROTOCOL_LAST] = { + { ICE_MAC_OFOS, ICE_MAC_OFOS_HW }, + { ICE_MAC_IL, ICE_MAC_IL_HW }, + { ICE_ETYPE_OL, ICE_ETYPE_OL_HW }, + { ICE_VLAN_OFOS, ICE_VLAN_OL_HW }, + { ICE_IPV4_OFOS, ICE_IPV4_OFOS_HW }, + { ICE_IPV4_IL, ICE_IPV4_IL_HW }, + { ICE_IPV6_OFOS, ICE_IPV6_OFOS_HW }, + { ICE_IPV6_IL, ICE_IPV6_IL_HW }, + { ICE_TCP_IL, ICE_TCP_IL_HW }, + { ICE_UDP_OF, ICE_UDP_OF_HW }, + { ICE_UDP_ILOS, ICE_UDP_ILOS_HW }, +}; + +/** + * ice_find_recp - find a recipe + * @hw: pointer to the hardware structure + * @lkup_exts: extension sequence to match + * + * Returns index of matching recipe, or ICE_MAX_NUM_RECIPES if not found. + */ +static u16 ice_find_recp(struct ice_hw *hw, struct ice_prot_lkup_ext *lkup_exts) +{ + bool refresh_required = true; + struct ice_sw_recipe *recp; + u8 i; + + /* Walk through existing recipes to find a match */ + recp = hw->switch_info->recp_list; + for (i = 0; i < ICE_MAX_NUM_RECIPES; i++) { + /* If recipe was not created for this ID, in SW bookkeeping, + * check if FW has an entry for this recipe. If the FW has an + * entry update it in our SW bookkeeping and continue with the + * matching. + */ + if (!recp[i].recp_created) + if (ice_get_recp_frm_fw(hw, + hw->switch_info->recp_list, i, + &refresh_required)) + continue; + + /* Skip inverse action recipes */ + if (recp[i].root_buf && recp[i].root_buf->content.act_ctrl & + ICE_AQ_RECIPE_ACT_INV_ACT) + continue; + + /* if number of words we are looking for match */ + if (lkup_exts->n_val_words == recp[i].lkup_exts.n_val_words) { + struct ice_fv_word *ar = recp[i].lkup_exts.fv_words; + struct ice_fv_word *be = lkup_exts->fv_words; + u16 *cr = recp[i].lkup_exts.field_mask; + u16 *de = lkup_exts->field_mask; + bool found = true; + u8 pe, qr; + + /* ar, cr, and qr are related to the recipe words, while + * be, de, and pe are related to the lookup words + */ + for (pe = 0; pe < lkup_exts->n_val_words; pe++) { + for (qr = 0; qr < recp[i].lkup_exts.n_val_words; + qr++) { + if (ar[qr].off == be[pe].off && + ar[qr].prot_id == be[pe].prot_id && + cr[qr] == de[pe]) + /* Found the "pe"th word in the + * given recipe + */ + break; + } + /* After walking through all the words in the + * "i"th recipe if "p"th word was not found then + * this recipe is not what we are looking for. + * So break out from this loop and try the next + * recipe + */ + if (qr >= recp[i].lkup_exts.n_val_words) { + found = false; + break; + } + } + /* If for "i"th recipe the found was never set to false + * then it means we found our match + */ + if (found) + return i; /* Return the recipe ID */ + } + } + return ICE_MAX_NUM_RECIPES; +} + +/** + * ice_prot_type_to_id - get protocol ID from protocol type + * @type: protocol type + * @id: pointer to variable that will receive the ID + * + * Returns true if found, false otherwise + */ +static bool ice_prot_type_to_id(enum ice_protocol_type type, u8 *id) +{ + u8 i; + + for (i = 0; i < ARRAY_SIZE(ice_prot_id_tbl); i++) + if (ice_prot_id_tbl[i].type == type) { + *id = ice_prot_id_tbl[i].protocol_id; + return true; + } + return false; +} + +/** + * ice_fill_valid_words - count valid words + * @rule: advanced rule with lookup information + * @lkup_exts: byte offset extractions of the words that are valid + * + * calculate valid words in a lookup rule using mask value + */ +static u8 +ice_fill_valid_words(struct ice_adv_lkup_elem *rule, + struct ice_prot_lkup_ext *lkup_exts) +{ + u8 j, word, prot_id, ret_val; + + if (!ice_prot_type_to_id(rule->type, &prot_id)) + return 0; + + word = lkup_exts->n_val_words; + + for (j = 0; j < sizeof(rule->m_u) / sizeof(u16); j++) + if (((u16 *)&rule->m_u)[j] && + rule->type < ARRAY_SIZE(ice_prot_ext)) { + /* No more space to accommodate */ + if (word >= ICE_MAX_CHAIN_WORDS) + return 0; + lkup_exts->fv_words[word].off = + ice_prot_ext[rule->type].offs[j]; + lkup_exts->fv_words[word].prot_id = + ice_prot_id_tbl[rule->type].protocol_id; + lkup_exts->field_mask[word] = + be16_to_cpu(((__force __be16 *)&rule->m_u)[j]); + word++; + } + + ret_val = word - lkup_exts->n_val_words; + lkup_exts->n_val_words = word; + + return ret_val; +} + +/** + * ice_create_first_fit_recp_def - Create a recipe grouping + * @hw: pointer to the hardware structure + * @lkup_exts: an array of protocol header extractions + * @rg_list: pointer to a list that stores new recipe groups + * @recp_cnt: pointer to a variable that stores returned number of recipe groups + * + * Using first fit algorithm, take all the words that are still not done + * and start grouping them in 4-word groups. Each group makes up one + * recipe. + */ +static enum ice_status +ice_create_first_fit_recp_def(struct ice_hw *hw, + struct ice_prot_lkup_ext *lkup_exts, + struct list_head *rg_list, + u8 *recp_cnt) +{ + struct ice_pref_recipe_group *grp = NULL; + u8 j; + + *recp_cnt = 0; + + /* Walk through every word in the rule to check if it is not done. If so + * then this word needs to be part of a new recipe. + */ + for (j = 0; j < lkup_exts->n_val_words; j++) + if (!test_bit(j, lkup_exts->done)) { + if (!grp || + grp->n_val_pairs == ICE_NUM_WORDS_RECIPE) { + struct ice_recp_grp_entry *entry; + + entry = devm_kzalloc(ice_hw_to_dev(hw), + sizeof(*entry), + GFP_KERNEL); + if (!entry) + return ICE_ERR_NO_MEMORY; + list_add(&entry->l_entry, rg_list); + grp = &entry->r_group; + (*recp_cnt)++; + } + + grp->pairs[grp->n_val_pairs].prot_id = + lkup_exts->fv_words[j].prot_id; + grp->pairs[grp->n_val_pairs].off = + lkup_exts->fv_words[j].off; + grp->mask[grp->n_val_pairs] = lkup_exts->field_mask[j]; + grp->n_val_pairs++; + } + + return 0; +} + +/** + * ice_fill_fv_word_index - fill in the field vector indices for a recipe group + * @hw: pointer to the hardware structure + * @fv_list: field vector with the extraction sequence information + * @rg_list: recipe groupings with protocol-offset pairs + * + * Helper function to fill in the field vector indices for protocol-offset + * pairs. These indexes are then ultimately programmed into a recipe. + */ +static enum ice_status +ice_fill_fv_word_index(struct ice_hw *hw, struct list_head *fv_list, + struct list_head *rg_list) +{ + struct ice_sw_fv_list_entry *fv; + struct ice_recp_grp_entry *rg; + struct ice_fv_word *fv_ext; + + if (list_empty(fv_list)) + return 0; + + fv = list_first_entry(fv_list, struct ice_sw_fv_list_entry, + list_entry); + fv_ext = fv->fv_ptr->ew; + + list_for_each_entry(rg, rg_list, l_entry) { + u8 i; + + for (i = 0; i < rg->r_group.n_val_pairs; i++) { + struct ice_fv_word *pr; + bool found = false; + u16 mask; + u8 j; + + pr = &rg->r_group.pairs[i]; + mask = rg->r_group.mask[i]; + + for (j = 0; j < hw->blk[ICE_BLK_SW].es.fvw; j++) + if (fv_ext[j].prot_id == pr->prot_id && + fv_ext[j].off == pr->off) { + found = true; + + /* Store index of field vector */ + rg->fv_idx[i] = j; + rg->fv_mask[i] = mask; + break; + } + + /* Protocol/offset could not be found, caller gave an + * invalid pair + */ + if (!found) + return ICE_ERR_PARAM; + } + } + + return 0; +} + +/** + * ice_find_free_recp_res_idx - find free result indexes for recipe + * @hw: pointer to hardware structure + * @profiles: bitmap of profiles that will be associated with the new recipe + * @free_idx: pointer to variable to receive the free index bitmap + * + * The algorithm used here is: + * 1. When creating a new recipe, create a set P which contains all + * Profiles that will be associated with our new recipe + * + * 2. For each Profile p in set P: + * a. Add all recipes associated with Profile p into set R + * b. Optional : PossibleIndexes &= profile[p].possibleIndexes + * [initially PossibleIndexes should be 0xFFFFFFFFFFFFFFFF] + * i. Or just assume they all have the same possible indexes: + * 44, 45, 46, 47 + * i.e., PossibleIndexes = 0x0000F00000000000 + * + * 3. For each Recipe r in set R: + * a. UsedIndexes |= (bitwise or ) recipe[r].res_indexes + * b. FreeIndexes = UsedIndexes ^ PossibleIndexes + * + * FreeIndexes will contain the bits indicating the indexes free for use, + * then the code needs to update the recipe[r].used_result_idx_bits to + * indicate which indexes were selected for use by this recipe. + */ +static u16 +ice_find_free_recp_res_idx(struct ice_hw *hw, const unsigned long *profiles, + unsigned long *free_idx) +{ + DECLARE_BITMAP(possible_idx, ICE_MAX_FV_WORDS); + DECLARE_BITMAP(recipes, ICE_MAX_NUM_RECIPES); + DECLARE_BITMAP(used_idx, ICE_MAX_FV_WORDS); + u16 bit; + + bitmap_zero(possible_idx, ICE_MAX_FV_WORDS); + bitmap_zero(recipes, ICE_MAX_NUM_RECIPES); + bitmap_zero(used_idx, ICE_MAX_FV_WORDS); + bitmap_zero(free_idx, ICE_MAX_FV_WORDS); + + bitmap_set(possible_idx, 0, ICE_MAX_FV_WORDS); + + /* For each profile we are going to associate the recipe with, add the + * recipes that are associated with that profile. This will give us + * the set of recipes that our recipe may collide with. Also, determine + * what possible result indexes are usable given this set of profiles. + */ + for_each_set_bit(bit, profiles, ICE_MAX_NUM_PROFILES) { + bitmap_or(recipes, recipes, profile_to_recipe[bit], + ICE_MAX_NUM_RECIPES); + bitmap_and(possible_idx, possible_idx, + hw->switch_info->prof_res_bm[bit], + ICE_MAX_FV_WORDS); + } + + /* For each recipe that our new recipe may collide with, determine + * which indexes have been used. + */ + for_each_set_bit(bit, recipes, ICE_MAX_NUM_RECIPES) + bitmap_or(used_idx, used_idx, + hw->switch_info->recp_list[bit].res_idxs, + ICE_MAX_FV_WORDS); + + bitmap_xor(free_idx, used_idx, possible_idx, ICE_MAX_FV_WORDS); + + /* return number of free indexes */ + return (u16)bitmap_weight(free_idx, ICE_MAX_FV_WORDS); +} + +/** + * ice_add_sw_recipe - function to call AQ calls to create switch recipe + * @hw: pointer to hardware structure + * @rm: recipe management list entry + * @match_tun_mask: tunnel mask that needs to be programmed + * @profiles: bitmap of profiles that will be associated. + */ +static enum ice_status +ice_add_sw_recipe(struct ice_hw *hw, struct ice_sw_recipe *rm, + u16 match_tun_mask, unsigned long *profiles) +{ + DECLARE_BITMAP(result_idx_bm, ICE_MAX_FV_WORDS); + struct ice_aqc_recipe_data_elem *tmp; + struct ice_aqc_recipe_data_elem *buf; + struct ice_recp_grp_entry *entry; + enum ice_status status; + u16 free_res_idx; + u16 recipe_count; + u8 chain_idx; + u8 recps = 0; + + /* When more than one recipe are required, another recipe is needed to + * chain them together. Matching a tunnel metadata ID takes up one of + * the match fields in the chaining recipe reducing the number of + * chained recipes by one. + */ + /* check number of free result indices */ + bitmap_zero(result_idx_bm, ICE_MAX_FV_WORDS); + free_res_idx = ice_find_free_recp_res_idx(hw, profiles, result_idx_bm); + + ice_debug(hw, ICE_DBG_SW, "Result idx slots: %d, need %d\n", + free_res_idx, rm->n_grp_count); + + if (rm->n_grp_count > 1) { + if (rm->n_grp_count > free_res_idx) + return ICE_ERR_MAX_LIMIT; + + rm->n_grp_count++; + } + + if (rm->n_grp_count > ICE_MAX_CHAIN_RECIPE) + return ICE_ERR_MAX_LIMIT; + + tmp = kcalloc(ICE_MAX_NUM_RECIPES, sizeof(*tmp), GFP_KERNEL); + if (!tmp) + return ICE_ERR_NO_MEMORY; + + buf = devm_kcalloc(ice_hw_to_dev(hw), rm->n_grp_count, sizeof(*buf), + GFP_KERNEL); + if (!buf) { + status = ICE_ERR_NO_MEMORY; + goto err_mem; + } + + bitmap_zero(rm->r_bitmap, ICE_MAX_NUM_RECIPES); + recipe_count = ICE_MAX_NUM_RECIPES; + status = ice_aq_get_recipe(hw, tmp, &recipe_count, ICE_SW_LKUP_MAC, + NULL); + if (status || recipe_count == 0) + goto err_unroll; + + /* Allocate the recipe resources, and configure them according to the + * match fields from protocol headers and extracted field vectors. + */ + chain_idx = find_first_bit(result_idx_bm, ICE_MAX_FV_WORDS); + list_for_each_entry(entry, &rm->rg_list, l_entry) { + u8 i; + + status = ice_alloc_recipe(hw, &entry->rid); + if (status) + goto err_unroll; + + /* Clear the result index of the located recipe, as this will be + * updated, if needed, later in the recipe creation process. + */ + tmp[0].content.result_indx = 0; + + buf[recps] = tmp[0]; + buf[recps].recipe_indx = (u8)entry->rid; + /* if the recipe is a non-root recipe RID should be programmed + * as 0 for the rules to be applied correctly. + */ + buf[recps].content.rid = 0; + memset(&buf[recps].content.lkup_indx, 0, + sizeof(buf[recps].content.lkup_indx)); + + /* All recipes use look-up index 0 to match switch ID. */ + buf[recps].content.lkup_indx[0] = ICE_AQ_SW_ID_LKUP_IDX; + buf[recps].content.mask[0] = + cpu_to_le16(ICE_AQ_SW_ID_LKUP_MASK); + /* Setup lkup_indx 1..4 to INVALID/ignore and set the mask + * to be 0 + */ + for (i = 1; i <= ICE_NUM_WORDS_RECIPE; i++) { + buf[recps].content.lkup_indx[i] = 0x80; + buf[recps].content.mask[i] = 0; + } + + for (i = 0; i < entry->r_group.n_val_pairs; i++) { + buf[recps].content.lkup_indx[i + 1] = entry->fv_idx[i]; + buf[recps].content.mask[i + 1] = + cpu_to_le16(entry->fv_mask[i]); + } + + if (rm->n_grp_count > 1) { + /* Checks to see if there really is a valid result index + * that can be used. + */ + if (chain_idx >= ICE_MAX_FV_WORDS) { + ice_debug(hw, ICE_DBG_SW, "No chain index available\n"); + status = ICE_ERR_MAX_LIMIT; + goto err_unroll; + } + + entry->chain_idx = chain_idx; + buf[recps].content.result_indx = + ICE_AQ_RECIPE_RESULT_EN | + ((chain_idx << ICE_AQ_RECIPE_RESULT_DATA_S) & + ICE_AQ_RECIPE_RESULT_DATA_M); + clear_bit(chain_idx, result_idx_bm); + chain_idx = find_first_bit(result_idx_bm, + ICE_MAX_FV_WORDS); + } + + /* fill recipe dependencies */ + bitmap_zero((unsigned long *)buf[recps].recipe_bitmap, + ICE_MAX_NUM_RECIPES); + set_bit(buf[recps].recipe_indx, + (unsigned long *)buf[recps].recipe_bitmap); + buf[recps].content.act_ctrl_fwd_priority = rm->priority; + recps++; + } + + if (rm->n_grp_count == 1) { + rm->root_rid = buf[0].recipe_indx; + set_bit(buf[0].recipe_indx, rm->r_bitmap); + buf[0].content.rid = rm->root_rid | ICE_AQ_RECIPE_ID_IS_ROOT; + if (sizeof(buf[0].recipe_bitmap) >= sizeof(rm->r_bitmap)) { + memcpy(buf[0].recipe_bitmap, rm->r_bitmap, + sizeof(buf[0].recipe_bitmap)); + } else { + status = ICE_ERR_BAD_PTR; + goto err_unroll; + } + /* Applicable only for ROOT_RECIPE, set the fwd_priority for + * the recipe which is getting created if specified + * by user. Usually any advanced switch filter, which results + * into new extraction sequence, ended up creating a new recipe + * of type ROOT and usually recipes are associated with profiles + * Switch rule referreing newly created recipe, needs to have + * either/or 'fwd' or 'join' priority, otherwise switch rule + * evaluation will not happen correctly. In other words, if + * switch rule to be evaluated on priority basis, then recipe + * needs to have priority, otherwise it will be evaluated last. + */ + buf[0].content.act_ctrl_fwd_priority = rm->priority; + } else { + struct ice_recp_grp_entry *last_chain_entry; + u16 rid, i; + + /* Allocate the last recipe that will chain the outcomes of the + * other recipes together + */ + status = ice_alloc_recipe(hw, &rid); + if (status) + goto err_unroll; + + buf[recps].recipe_indx = (u8)rid; + buf[recps].content.rid = (u8)rid; + buf[recps].content.rid |= ICE_AQ_RECIPE_ID_IS_ROOT; + /* the new entry created should also be part of rg_list to + * make sure we have complete recipe + */ + last_chain_entry = devm_kzalloc(ice_hw_to_dev(hw), + sizeof(*last_chain_entry), + GFP_KERNEL); + if (!last_chain_entry) { + status = ICE_ERR_NO_MEMORY; + goto err_unroll; + } + last_chain_entry->rid = rid; + memset(&buf[recps].content.lkup_indx, 0, + sizeof(buf[recps].content.lkup_indx)); + /* All recipes use look-up index 0 to match switch ID. */ + buf[recps].content.lkup_indx[0] = ICE_AQ_SW_ID_LKUP_IDX; + buf[recps].content.mask[0] = + cpu_to_le16(ICE_AQ_SW_ID_LKUP_MASK); + for (i = 1; i <= ICE_NUM_WORDS_RECIPE; i++) { + buf[recps].content.lkup_indx[i] = + ICE_AQ_RECIPE_LKUP_IGNORE; + buf[recps].content.mask[i] = 0; + } + + i = 1; + /* update r_bitmap with the recp that is used for chaining */ + set_bit(rid, rm->r_bitmap); + /* this is the recipe that chains all the other recipes so it + * should not have a chaining ID to indicate the same + */ + last_chain_entry->chain_idx = ICE_INVAL_CHAIN_IND; + list_for_each_entry(entry, &rm->rg_list, l_entry) { + last_chain_entry->fv_idx[i] = entry->chain_idx; + buf[recps].content.lkup_indx[i] = entry->chain_idx; + buf[recps].content.mask[i++] = cpu_to_le16(0xFFFF); + set_bit(entry->rid, rm->r_bitmap); + } + list_add(&last_chain_entry->l_entry, &rm->rg_list); + if (sizeof(buf[recps].recipe_bitmap) >= + sizeof(rm->r_bitmap)) { + memcpy(buf[recps].recipe_bitmap, rm->r_bitmap, + sizeof(buf[recps].recipe_bitmap)); + } else { + status = ICE_ERR_BAD_PTR; + goto err_unroll; + } + buf[recps].content.act_ctrl_fwd_priority = rm->priority; + + /* To differentiate among different UDP tunnels, a meta data ID + * flag is used. + */ + if (match_tun_mask) { + buf[recps].content.lkup_indx[i] = ICE_TUN_FLAG_FV_IND; + buf[recps].content.mask[i] = + cpu_to_le16(match_tun_mask); + } + + recps++; + rm->root_rid = (u8)rid; + } + status = ice_acquire_change_lock(hw, ICE_RES_WRITE); + if (status) + goto err_unroll; + + status = ice_aq_add_recipe(hw, buf, rm->n_grp_count, NULL); + ice_release_change_lock(hw); + if (status) + goto err_unroll; + + /* Every recipe that just got created add it to the recipe + * book keeping list + */ + list_for_each_entry(entry, &rm->rg_list, l_entry) { + struct ice_switch_info *sw = hw->switch_info; + bool is_root, idx_found = false; + struct ice_sw_recipe *recp; + u16 idx, buf_idx = 0; + + /* find buffer index for copying some data */ + for (idx = 0; idx < rm->n_grp_count; idx++) + if (buf[idx].recipe_indx == entry->rid) { + buf_idx = idx; + idx_found = true; + } + + if (!idx_found) { + status = ICE_ERR_OUT_OF_RANGE; + goto err_unroll; + } + + recp = &sw->recp_list[entry->rid]; + is_root = (rm->root_rid == entry->rid); + recp->is_root = is_root; + + recp->root_rid = entry->rid; + recp->big_recp = (is_root && rm->n_grp_count > 1); + + memcpy(&recp->ext_words, entry->r_group.pairs, + entry->r_group.n_val_pairs * sizeof(struct ice_fv_word)); + + memcpy(recp->r_bitmap, buf[buf_idx].recipe_bitmap, + sizeof(recp->r_bitmap)); + + /* Copy non-result fv index values and masks to recipe. This + * call will also update the result recipe bitmask. + */ + ice_collect_result_idx(&buf[buf_idx], recp); + + /* for non-root recipes, also copy to the root, this allows + * easier matching of a complete chained recipe + */ + if (!is_root) + ice_collect_result_idx(&buf[buf_idx], + &sw->recp_list[rm->root_rid]); + + recp->n_ext_words = entry->r_group.n_val_pairs; + recp->chain_idx = entry->chain_idx; + recp->priority = buf[buf_idx].content.act_ctrl_fwd_priority; + recp->n_grp_count = rm->n_grp_count; + recp->recp_created = true; + } + rm->root_buf = buf; + kfree(tmp); + return status; + +err_unroll: +err_mem: + kfree(tmp); + devm_kfree(ice_hw_to_dev(hw), buf); + return status; +} + +/** + * ice_create_recipe_group - creates recipe group + * @hw: pointer to hardware structure + * @rm: recipe management list entry + * @lkup_exts: lookup elements + */ +static enum ice_status +ice_create_recipe_group(struct ice_hw *hw, struct ice_sw_recipe *rm, + struct ice_prot_lkup_ext *lkup_exts) +{ + enum ice_status status; + u8 recp_count = 0; + + rm->n_grp_count = 0; + + /* Create recipes for words that are marked not done by packing them + * as best fit. + */ + status = ice_create_first_fit_recp_def(hw, lkup_exts, + &rm->rg_list, &recp_count); + if (!status) { + rm->n_grp_count += recp_count; + rm->n_ext_words = lkup_exts->n_val_words; + memcpy(&rm->ext_words, lkup_exts->fv_words, + sizeof(rm->ext_words)); + memcpy(rm->word_masks, lkup_exts->field_mask, + sizeof(rm->word_masks)); + } + + return status; +} + +/** + * ice_get_fv - get field vectors/extraction sequences for spec. lookup types + * @hw: pointer to hardware structure + * @lkups: lookup elements or match criteria for the advanced recipe, one + * structure per protocol header + * @lkups_cnt: number of protocols + * @bm: bitmap of field vectors to consider + * @fv_list: pointer to a list that holds the returned field vectors + */ +static enum ice_status +ice_get_fv(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, u16 lkups_cnt, + unsigned long *bm, struct list_head *fv_list) +{ + enum ice_status status; + u8 *prot_ids; + u16 i; + + prot_ids = kcalloc(lkups_cnt, sizeof(*prot_ids), GFP_KERNEL); + if (!prot_ids) + return ICE_ERR_NO_MEMORY; + + for (i = 0; i < lkups_cnt; i++) + if (!ice_prot_type_to_id(lkups[i].type, &prot_ids[i])) { + status = ICE_ERR_CFG; + goto free_mem; + } + + /* Find field vectors that include all specified protocol types */ + status = ice_get_sw_fv_list(hw, prot_ids, lkups_cnt, bm, fv_list); + +free_mem: + kfree(prot_ids); + return status; +} + +/* ice_get_compat_fv_bitmap - Get compatible field vector bitmap for rule + * @hw: pointer to hardware structure + * @rinfo: other information regarding the rule e.g. priority and action info + * @bm: pointer to memory for returning the bitmap of field vectors + */ +static void +ice_get_compat_fv_bitmap(struct ice_hw *hw, struct ice_adv_rule_info *rinfo, + unsigned long *bm) +{ + bitmap_zero(bm, ICE_MAX_NUM_PROFILES); + + ice_get_sw_fv_bitmap(hw, ICE_PROF_NON_TUN, bm); +} + +/** + * ice_add_adv_recipe - Add an advanced recipe that is not part of the default + * @hw: pointer to hardware structure + * @lkups: lookup elements or match criteria for the advanced recipe, one + * structure per protocol header + * @lkups_cnt: number of protocols + * @rinfo: other information regarding the rule e.g. priority and action info + * @rid: return the recipe ID of the recipe created + */ +static enum ice_status +ice_add_adv_recipe(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, + u16 lkups_cnt, struct ice_adv_rule_info *rinfo, u16 *rid) +{ + DECLARE_BITMAP(fv_bitmap, ICE_MAX_NUM_PROFILES); + DECLARE_BITMAP(profiles, ICE_MAX_NUM_PROFILES); + struct ice_prot_lkup_ext *lkup_exts; + struct ice_recp_grp_entry *r_entry; + struct ice_sw_fv_list_entry *fvit; + struct ice_recp_grp_entry *r_tmp; + struct ice_sw_fv_list_entry *tmp; + enum ice_status status = 0; + struct ice_sw_recipe *rm; + u16 match_tun_mask = 0; + u8 i; + + if (!lkups_cnt) + return ICE_ERR_PARAM; + + lkup_exts = kzalloc(sizeof(*lkup_exts), GFP_KERNEL); + if (!lkup_exts) + return ICE_ERR_NO_MEMORY; + + /* Determine the number of words to be matched and if it exceeds a + * recipe's restrictions + */ + for (i = 0; i < lkups_cnt; i++) { + u16 count; + + if (lkups[i].type >= ICE_PROTOCOL_LAST) { + status = ICE_ERR_CFG; + goto err_free_lkup_exts; + } + + count = ice_fill_valid_words(&lkups[i], lkup_exts); + if (!count) { + status = ICE_ERR_CFG; + goto err_free_lkup_exts; + } + } + + rm = kzalloc(sizeof(*rm), GFP_KERNEL); + if (!rm) { + status = ICE_ERR_NO_MEMORY; + goto err_free_lkup_exts; + } + + /* Get field vectors that contain fields extracted from all the protocol + * headers being programmed. + */ + INIT_LIST_HEAD(&rm->fv_list); + INIT_LIST_HEAD(&rm->rg_list); + + /* Get bitmap of field vectors (profiles) that are compatible with the + * rule request; only these will be searched in the subsequent call to + * ice_get_fv. + */ + ice_get_compat_fv_bitmap(hw, rinfo, fv_bitmap); + + status = ice_get_fv(hw, lkups, lkups_cnt, fv_bitmap, &rm->fv_list); + if (status) + goto err_unroll; + + /* Group match words into recipes using preferred recipe grouping + * criteria. + */ + status = ice_create_recipe_group(hw, rm, lkup_exts); + if (status) + goto err_unroll; + + /* set the recipe priority if specified */ + rm->priority = (u8)rinfo->priority; + + /* Find offsets from the field vector. Pick the first one for all the + * recipes. + */ + status = ice_fill_fv_word_index(hw, &rm->fv_list, &rm->rg_list); + if (status) + goto err_unroll; + + /* get bitmap of all profiles the recipe will be associated with */ + bitmap_zero(profiles, ICE_MAX_NUM_PROFILES); + list_for_each_entry(fvit, &rm->fv_list, list_entry) { + ice_debug(hw, ICE_DBG_SW, "profile: %d\n", fvit->profile_id); + set_bit((u16)fvit->profile_id, profiles); + } + + /* Look for a recipe which matches our requested fv / mask list */ + *rid = ice_find_recp(hw, lkup_exts); + if (*rid < ICE_MAX_NUM_RECIPES) + /* Success if found a recipe that match the existing criteria */ + goto err_unroll; + + /* Recipe we need does not exist, add a recipe */ + status = ice_add_sw_recipe(hw, rm, match_tun_mask, profiles); + if (status) + goto err_unroll; + + /* Associate all the recipes created with all the profiles in the + * common field vector. + */ + list_for_each_entry(fvit, &rm->fv_list, list_entry) { + DECLARE_BITMAP(r_bitmap, ICE_MAX_NUM_RECIPES); + u16 j; + + status = ice_aq_get_recipe_to_profile(hw, fvit->profile_id, + (u8 *)r_bitmap, NULL); + if (status) + goto err_unroll; + + bitmap_or(r_bitmap, r_bitmap, rm->r_bitmap, + ICE_MAX_NUM_RECIPES); + status = ice_acquire_change_lock(hw, ICE_RES_WRITE); + if (status) + goto err_unroll; + + status = ice_aq_map_recipe_to_profile(hw, fvit->profile_id, + (u8 *)r_bitmap, + NULL); + ice_release_change_lock(hw); + + if (status) + goto err_unroll; + + /* Update profile to recipe bitmap array */ + bitmap_copy(profile_to_recipe[fvit->profile_id], r_bitmap, + ICE_MAX_NUM_RECIPES); + + /* Update recipe to profile bitmap array */ + for_each_set_bit(j, rm->r_bitmap, ICE_MAX_NUM_RECIPES) + set_bit((u16)fvit->profile_id, recipe_to_profile[j]); + } + + *rid = rm->root_rid; + memcpy(&hw->switch_info->recp_list[*rid].lkup_exts, lkup_exts, + sizeof(*lkup_exts)); +err_unroll: + list_for_each_entry_safe(r_entry, r_tmp, &rm->rg_list, l_entry) { + list_del(&r_entry->l_entry); + devm_kfree(ice_hw_to_dev(hw), r_entry); + } + + list_for_each_entry_safe(fvit, tmp, &rm->fv_list, list_entry) { + list_del(&fvit->list_entry); + devm_kfree(ice_hw_to_dev(hw), fvit); + } + + if (rm->root_buf) + devm_kfree(ice_hw_to_dev(hw), rm->root_buf); + + kfree(rm); + +err_free_lkup_exts: + kfree(lkup_exts); + + return status; +} + +/** + * ice_find_dummy_packet - find dummy packet + * + * @lkups: lookup elements or match criteria for the advanced recipe, one + * structure per protocol header + * @lkups_cnt: number of protocols + * @pkt: dummy packet to fill according to filter match criteria + * @pkt_len: packet length of dummy packet + * @offsets: pointer to receive the pointer to the offsets for the packet + */ +static void +ice_find_dummy_packet(struct ice_adv_lkup_elem *lkups, u16 lkups_cnt, + const u8 **pkt, u16 *pkt_len, + const struct ice_dummy_pkt_offsets **offsets) +{ + bool tcp = false, udp = false, ipv6 = false, vlan = false; + u16 i; + + for (i = 0; i < lkups_cnt; i++) { + if (lkups[i].type == ICE_UDP_ILOS) + udp = true; + else if (lkups[i].type == ICE_TCP_IL) + tcp = true; + else if (lkups[i].type == ICE_IPV6_OFOS) + ipv6 = true; + else if (lkups[i].type == ICE_VLAN_OFOS) + vlan = true; + else if (lkups[i].type == ICE_ETYPE_OL && + lkups[i].h_u.ethertype.ethtype_id == + cpu_to_be16(ICE_IPV6_ETHER_ID) && + lkups[i].m_u.ethertype.ethtype_id == + cpu_to_be16(0xFFFF)) + ipv6 = true; + } + + if (udp && !ipv6) { + if (vlan) { + *pkt = dummy_vlan_udp_packet; + *pkt_len = sizeof(dummy_vlan_udp_packet); + *offsets = dummy_vlan_udp_packet_offsets; + return; + } + *pkt = dummy_udp_packet; + *pkt_len = sizeof(dummy_udp_packet); + *offsets = dummy_udp_packet_offsets; + return; + } else if (udp && ipv6) { + if (vlan) { + *pkt = dummy_vlan_udp_ipv6_packet; + *pkt_len = sizeof(dummy_vlan_udp_ipv6_packet); + *offsets = dummy_vlan_udp_ipv6_packet_offsets; + return; + } + *pkt = dummy_udp_ipv6_packet; + *pkt_len = sizeof(dummy_udp_ipv6_packet); + *offsets = dummy_udp_ipv6_packet_offsets; + return; + } else if ((tcp && ipv6) || ipv6) { + if (vlan) { + *pkt = dummy_vlan_tcp_ipv6_packet; + *pkt_len = sizeof(dummy_vlan_tcp_ipv6_packet); + *offsets = dummy_vlan_tcp_ipv6_packet_offsets; + return; + } + *pkt = dummy_tcp_ipv6_packet; + *pkt_len = sizeof(dummy_tcp_ipv6_packet); + *offsets = dummy_tcp_ipv6_packet_offsets; + return; + } + + if (vlan) { + *pkt = dummy_vlan_tcp_packet; + *pkt_len = sizeof(dummy_vlan_tcp_packet); + *offsets = dummy_vlan_tcp_packet_offsets; + } else { + *pkt = dummy_tcp_packet; + *pkt_len = sizeof(dummy_tcp_packet); + *offsets = dummy_tcp_packet_offsets; + } +} + +/** + * ice_fill_adv_dummy_packet - fill a dummy packet with given match criteria + * + * @lkups: lookup elements or match criteria for the advanced recipe, one + * structure per protocol header + * @lkups_cnt: number of protocols + * @s_rule: stores rule information from the match criteria + * @dummy_pkt: dummy packet to fill according to filter match criteria + * @pkt_len: packet length of dummy packet + * @offsets: offset info for the dummy packet + */ +static enum ice_status +ice_fill_adv_dummy_packet(struct ice_adv_lkup_elem *lkups, u16 lkups_cnt, + struct ice_aqc_sw_rules_elem *s_rule, + const u8 *dummy_pkt, u16 pkt_len, + const struct ice_dummy_pkt_offsets *offsets) +{ + u8 *pkt; + u16 i; + + /* Start with a packet with a pre-defined/dummy content. Then, fill + * in the header values to be looked up or matched. + */ + pkt = s_rule->pdata.lkup_tx_rx.hdr; + + memcpy(pkt, dummy_pkt, pkt_len); + + for (i = 0; i < lkups_cnt; i++) { + enum ice_protocol_type type; + u16 offset = 0, len = 0, j; + bool found = false; + + /* find the start of this layer; it should be found since this + * was already checked when search for the dummy packet + */ + type = lkups[i].type; + for (j = 0; offsets[j].type != ICE_PROTOCOL_LAST; j++) { + if (type == offsets[j].type) { + offset = offsets[j].offset; + found = true; + break; + } + } + /* this should never happen in a correct calling sequence */ + if (!found) + return ICE_ERR_PARAM; + + switch (lkups[i].type) { + case ICE_MAC_OFOS: + case ICE_MAC_IL: + len = sizeof(struct ice_ether_hdr); + break; + case ICE_ETYPE_OL: + len = sizeof(struct ice_ethtype_hdr); + break; + case ICE_VLAN_OFOS: + len = sizeof(struct ice_vlan_hdr); + break; + case ICE_IPV4_OFOS: + case ICE_IPV4_IL: + len = sizeof(struct ice_ipv4_hdr); + break; + case ICE_IPV6_OFOS: + case ICE_IPV6_IL: + len = sizeof(struct ice_ipv6_hdr); + break; + case ICE_TCP_IL: + case ICE_UDP_OF: + case ICE_UDP_ILOS: + len = sizeof(struct ice_l4_hdr); + break; + case ICE_SCTP_IL: + len = sizeof(struct ice_sctp_hdr); + break; + default: + return ICE_ERR_PARAM; + } + + /* the length should be a word multiple */ + if (len % ICE_BYTES_PER_WORD) + return ICE_ERR_CFG; + + /* We have the offset to the header start, the length, the + * caller's header values and mask. Use this information to + * copy the data into the dummy packet appropriately based on + * the mask. Note that we need to only write the bits as + * indicated by the mask to make sure we don't improperly write + * over any significant packet data. + */ + for (j = 0; j < len / sizeof(u16); j++) + if (((u16 *)&lkups[i].m_u)[j]) + ((u16 *)(pkt + offset))[j] = + (((u16 *)(pkt + offset))[j] & + ~((u16 *)&lkups[i].m_u)[j]) | + (((u16 *)&lkups[i].h_u)[j] & + ((u16 *)&lkups[i].m_u)[j]); + } + + s_rule->pdata.lkup_tx_rx.hdr_len = cpu_to_le16(pkt_len); + + return 0; +} + +/** + * ice_find_adv_rule_entry - Search a rule entry + * @hw: pointer to the hardware structure + * @lkups: lookup elements or match criteria for the advanced recipe, one + * structure per protocol header + * @lkups_cnt: number of protocols + * @recp_id: recipe ID for which we are finding the rule + * @rinfo: other information regarding the rule e.g. priority and action info + * + * Helper function to search for a given advance rule entry + * Returns pointer to entry storing the rule if found + */ +static struct ice_adv_fltr_mgmt_list_entry * +ice_find_adv_rule_entry(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, + u16 lkups_cnt, u16 recp_id, + struct ice_adv_rule_info *rinfo) +{ + struct ice_adv_fltr_mgmt_list_entry *list_itr; + struct ice_switch_info *sw = hw->switch_info; + int i; + + list_for_each_entry(list_itr, &sw->recp_list[recp_id].filt_rules, + list_entry) { + bool lkups_matched = true; + + if (lkups_cnt != list_itr->lkups_cnt) + continue; + for (i = 0; i < list_itr->lkups_cnt; i++) + if (memcmp(&list_itr->lkups[i], &lkups[i], + sizeof(*lkups))) { + lkups_matched = false; + break; + } + if (rinfo->sw_act.flag == list_itr->rule_info.sw_act.flag && + lkups_matched) + return list_itr; + } + return NULL; +} + +/** + * ice_adv_add_update_vsi_list + * @hw: pointer to the hardware structure + * @m_entry: pointer to current adv filter management list entry + * @cur_fltr: filter information from the book keeping entry + * @new_fltr: filter information with the new VSI to be added + * + * Call AQ command to add or update previously created VSI list with new VSI. + * + * Helper function to do book keeping associated with adding filter information + * The algorithm to do the booking keeping is described below : + * When a VSI needs to subscribe to a given advanced filter + * if only one VSI has been added till now + * Allocate a new VSI list and add two VSIs + * to this list using switch rule command + * Update the previously created switch rule with the + * newly created VSI list ID + * if a VSI list was previously created + * Add the new VSI to the previously created VSI list set + * using the update switch rule command + */ +static enum ice_status +ice_adv_add_update_vsi_list(struct ice_hw *hw, + struct ice_adv_fltr_mgmt_list_entry *m_entry, + struct ice_adv_rule_info *cur_fltr, + struct ice_adv_rule_info *new_fltr) +{ + enum ice_status status; + u16 vsi_list_id = 0; + + if (cur_fltr->sw_act.fltr_act == ICE_FWD_TO_Q || + cur_fltr->sw_act.fltr_act == ICE_FWD_TO_QGRP || + cur_fltr->sw_act.fltr_act == ICE_DROP_PACKET) + return ICE_ERR_NOT_IMPL; + + if ((new_fltr->sw_act.fltr_act == ICE_FWD_TO_Q || + new_fltr->sw_act.fltr_act == ICE_FWD_TO_QGRP) && + (cur_fltr->sw_act.fltr_act == ICE_FWD_TO_VSI || + cur_fltr->sw_act.fltr_act == ICE_FWD_TO_VSI_LIST)) + return ICE_ERR_NOT_IMPL; + + if (m_entry->vsi_count < 2 && !m_entry->vsi_list_info) { + /* Only one entry existed in the mapping and it was not already + * a part of a VSI list. So, create a VSI list with the old and + * new VSIs. + */ + struct ice_fltr_info tmp_fltr; + u16 vsi_handle_arr[2]; + + /* A rule already exists with the new VSI being added */ + if (cur_fltr->sw_act.fwd_id.hw_vsi_id == + new_fltr->sw_act.fwd_id.hw_vsi_id) + return ICE_ERR_ALREADY_EXISTS; + + vsi_handle_arr[0] = cur_fltr->sw_act.vsi_handle; + vsi_handle_arr[1] = new_fltr->sw_act.vsi_handle; + status = ice_create_vsi_list_rule(hw, &vsi_handle_arr[0], 2, + &vsi_list_id, + ICE_SW_LKUP_LAST); + if (status) + return status; + + memset(&tmp_fltr, 0, sizeof(tmp_fltr)); + tmp_fltr.flag = m_entry->rule_info.sw_act.flag; + tmp_fltr.fltr_rule_id = cur_fltr->fltr_rule_id; + tmp_fltr.fltr_act = ICE_FWD_TO_VSI_LIST; + tmp_fltr.fwd_id.vsi_list_id = vsi_list_id; + tmp_fltr.lkup_type = ICE_SW_LKUP_LAST; + + /* Update the previous switch rule of "forward to VSI" to + * "fwd to VSI list" + */ + status = ice_update_pkt_fwd_rule(hw, &tmp_fltr); + if (status) + return status; + + cur_fltr->sw_act.fwd_id.vsi_list_id = vsi_list_id; + cur_fltr->sw_act.fltr_act = ICE_FWD_TO_VSI_LIST; + m_entry->vsi_list_info = + ice_create_vsi_list_map(hw, &vsi_handle_arr[0], 2, + vsi_list_id); + } else { + u16 vsi_handle = new_fltr->sw_act.vsi_handle; + + if (!m_entry->vsi_list_info) + return ICE_ERR_CFG; + + /* A rule already exists with the new VSI being added */ + if (test_bit(vsi_handle, m_entry->vsi_list_info->vsi_map)) + return 0; + + /* Update the previously created VSI list set with + * the new VSI ID passed in + */ + vsi_list_id = cur_fltr->sw_act.fwd_id.vsi_list_id; + + status = ice_update_vsi_list_rule(hw, &vsi_handle, 1, + vsi_list_id, false, + ice_aqc_opc_update_sw_rules, + ICE_SW_LKUP_LAST); + /* update VSI list mapping info with new VSI ID */ + if (!status) + set_bit(vsi_handle, m_entry->vsi_list_info->vsi_map); + } + if (!status) + m_entry->vsi_count++; + return status; +} + +/** + * ice_add_adv_rule - helper function to create an advanced switch rule + * @hw: pointer to the hardware structure + * @lkups: information on the words that needs to be looked up. All words + * together makes one recipe + * @lkups_cnt: num of entries in the lkups array + * @rinfo: other information related to the rule that needs to be programmed + * @added_entry: this will return recipe_id, rule_id and vsi_handle. should be + * ignored is case of error. + * + * This function can program only 1 rule at a time. The lkups is used to + * describe the all the words that forms the "lookup" portion of the recipe. + * These words can span multiple protocols. Callers to this function need to + * pass in a list of protocol headers with lookup information along and mask + * that determines which words are valid from the given protocol header. + * rinfo describes other information related to this rule such as forwarding + * IDs, priority of this rule, etc. + */ +enum ice_status +ice_add_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, + u16 lkups_cnt, struct ice_adv_rule_info *rinfo, + struct ice_rule_query_data *added_entry) +{ + struct ice_adv_fltr_mgmt_list_entry *m_entry, *adv_fltr = NULL; + u16 rid = 0, i, pkt_len, rule_buf_sz, vsi_handle; + const struct ice_dummy_pkt_offsets *pkt_offsets; + struct ice_aqc_sw_rules_elem *s_rule = NULL; + struct list_head *rule_head; + struct ice_switch_info *sw; + enum ice_status status; + const u8 *pkt = NULL; + u16 word_cnt; + u32 act = 0; + u8 q_rgn; + + /* Initialize profile to result index bitmap */ + if (!hw->switch_info->prof_res_bm_init) { + hw->switch_info->prof_res_bm_init = 1; + ice_init_prof_result_bm(hw); + } + + if (!lkups_cnt) + return ICE_ERR_PARAM; + + /* get # of words we need to match */ + word_cnt = 0; + for (i = 0; i < lkups_cnt; i++) { + u16 j, *ptr; + + ptr = (u16 *)&lkups[i].m_u; + for (j = 0; j < sizeof(lkups->m_u) / sizeof(u16); j++) + if (ptr[j] != 0) + word_cnt++; + } + + if (!word_cnt || word_cnt > ICE_MAX_CHAIN_WORDS) + return ICE_ERR_PARAM; + + /* make sure that we can locate a dummy packet */ + ice_find_dummy_packet(lkups, lkups_cnt, &pkt, &pkt_len, + &pkt_offsets); + if (!pkt) { + status = ICE_ERR_PARAM; + goto err_ice_add_adv_rule; + } + + if (!(rinfo->sw_act.fltr_act == ICE_FWD_TO_VSI || + rinfo->sw_act.fltr_act == ICE_FWD_TO_Q || + rinfo->sw_act.fltr_act == ICE_FWD_TO_QGRP || + rinfo->sw_act.fltr_act == ICE_DROP_PACKET)) + return ICE_ERR_CFG; + + vsi_handle = rinfo->sw_act.vsi_handle; + if (!ice_is_vsi_valid(hw, vsi_handle)) + return ICE_ERR_PARAM; + + if (rinfo->sw_act.fltr_act == ICE_FWD_TO_VSI) + rinfo->sw_act.fwd_id.hw_vsi_id = + ice_get_hw_vsi_num(hw, vsi_handle); + if (rinfo->sw_act.flag & ICE_FLTR_TX) + rinfo->sw_act.src = ice_get_hw_vsi_num(hw, vsi_handle); + + status = ice_add_adv_recipe(hw, lkups, lkups_cnt, rinfo, &rid); + if (status) + return status; + m_entry = ice_find_adv_rule_entry(hw, lkups, lkups_cnt, rid, rinfo); + if (m_entry) { + /* we have to add VSI to VSI_LIST and increment vsi_count. + * Also Update VSI list so that we can change forwarding rule + * if the rule already exists, we will check if it exists with + * same vsi_id, if not then add it to the VSI list if it already + * exists if not then create a VSI list and add the existing VSI + * ID and the new VSI ID to the list + * We will add that VSI to the list + */ + status = ice_adv_add_update_vsi_list(hw, m_entry, + &m_entry->rule_info, + rinfo); + if (added_entry) { + added_entry->rid = rid; + added_entry->rule_id = m_entry->rule_info.fltr_rule_id; + added_entry->vsi_handle = rinfo->sw_act.vsi_handle; + } + return status; + } + rule_buf_sz = ICE_SW_RULE_RX_TX_NO_HDR_SIZE + pkt_len; + s_rule = kzalloc(rule_buf_sz, GFP_KERNEL); + if (!s_rule) + return ICE_ERR_NO_MEMORY; + if (!rinfo->flags_info.act_valid) { + act |= ICE_SINGLE_ACT_LAN_ENABLE; + act |= ICE_SINGLE_ACT_LB_ENABLE; + } else { + act |= rinfo->flags_info.act & (ICE_SINGLE_ACT_LAN_ENABLE | + ICE_SINGLE_ACT_LB_ENABLE); + } + + switch (rinfo->sw_act.fltr_act) { + case ICE_FWD_TO_VSI: + act |= (rinfo->sw_act.fwd_id.hw_vsi_id << + ICE_SINGLE_ACT_VSI_ID_S) & ICE_SINGLE_ACT_VSI_ID_M; + act |= ICE_SINGLE_ACT_VSI_FORWARDING | ICE_SINGLE_ACT_VALID_BIT; + break; + case ICE_FWD_TO_Q: + act |= ICE_SINGLE_ACT_TO_Q; + act |= (rinfo->sw_act.fwd_id.q_id << ICE_SINGLE_ACT_Q_INDEX_S) & + ICE_SINGLE_ACT_Q_INDEX_M; + break; + case ICE_FWD_TO_QGRP: + q_rgn = rinfo->sw_act.qgrp_size > 0 ? + (u8)ilog2(rinfo->sw_act.qgrp_size) : 0; + act |= ICE_SINGLE_ACT_TO_Q; + act |= (rinfo->sw_act.fwd_id.q_id << ICE_SINGLE_ACT_Q_INDEX_S) & + ICE_SINGLE_ACT_Q_INDEX_M; + act |= (q_rgn << ICE_SINGLE_ACT_Q_REGION_S) & + ICE_SINGLE_ACT_Q_REGION_M; + break; + case ICE_DROP_PACKET: + act |= ICE_SINGLE_ACT_VSI_FORWARDING | ICE_SINGLE_ACT_DROP | + ICE_SINGLE_ACT_VALID_BIT; + break; + default: + status = ICE_ERR_CFG; + goto err_ice_add_adv_rule; + } + + /* set the rule LOOKUP type based on caller specified 'Rx' + * instead of hardcoding it to be either LOOKUP_TX/RX + * + * for 'Rx' set the source to be the port number + * for 'Tx' set the source to be the source HW VSI number (determined + * by caller) + */ + if (rinfo->rx) { + s_rule->type = cpu_to_le16(ICE_AQC_SW_RULES_T_LKUP_RX); + s_rule->pdata.lkup_tx_rx.src = + cpu_to_le16(hw->port_info->lport); + } else { + s_rule->type = cpu_to_le16(ICE_AQC_SW_RULES_T_LKUP_TX); + s_rule->pdata.lkup_tx_rx.src = cpu_to_le16(rinfo->sw_act.src); + } + + s_rule->pdata.lkup_tx_rx.recipe_id = cpu_to_le16(rid); + s_rule->pdata.lkup_tx_rx.act = cpu_to_le32(act); + + status = ice_fill_adv_dummy_packet(lkups, lkups_cnt, s_rule, pkt, + pkt_len, pkt_offsets); + if (status) + goto err_ice_add_adv_rule; + + status = ice_aq_sw_rules(hw, (struct ice_aqc_sw_rules *)s_rule, + rule_buf_sz, 1, ice_aqc_opc_add_sw_rules, + NULL); + if (status) + goto err_ice_add_adv_rule; + adv_fltr = devm_kzalloc(ice_hw_to_dev(hw), + sizeof(struct ice_adv_fltr_mgmt_list_entry), + GFP_KERNEL); + if (!adv_fltr) { + status = ICE_ERR_NO_MEMORY; + goto err_ice_add_adv_rule; + } + + adv_fltr->lkups = devm_kmemdup(ice_hw_to_dev(hw), lkups, + lkups_cnt * sizeof(*lkups), GFP_KERNEL); + if (!adv_fltr->lkups) { + status = ICE_ERR_NO_MEMORY; + goto err_ice_add_adv_rule; + } + + adv_fltr->lkups_cnt = lkups_cnt; + adv_fltr->rule_info = *rinfo; + adv_fltr->rule_info.fltr_rule_id = + le16_to_cpu(s_rule->pdata.lkup_tx_rx.index); + sw = hw->switch_info; + sw->recp_list[rid].adv_rule = true; + rule_head = &sw->recp_list[rid].filt_rules; + + if (rinfo->sw_act.fltr_act == ICE_FWD_TO_VSI) + adv_fltr->vsi_count = 1; + + /* Add rule entry to book keeping list */ + list_add(&adv_fltr->list_entry, rule_head); + if (added_entry) { + added_entry->rid = rid; + added_entry->rule_id = adv_fltr->rule_info.fltr_rule_id; + added_entry->vsi_handle = rinfo->sw_act.vsi_handle; + } +err_ice_add_adv_rule: + if (status && adv_fltr) { + devm_kfree(ice_hw_to_dev(hw), adv_fltr->lkups); + devm_kfree(ice_hw_to_dev(hw), adv_fltr); + } + + kfree(s_rule); + + return status; +} + /** * ice_replay_vsi_fltr - Replay filters for requested VSI * @hw: pointer to the hardware structure @@ -2830,6 +5069,229 @@ end: return status; } +/** + * ice_adv_rem_update_vsi_list + * @hw: pointer to the hardware structure + * @vsi_handle: VSI handle of the VSI to remove + * @fm_list: filter management entry for which the VSI list management needs to + * be done + */ +static enum ice_status +ice_adv_rem_update_vsi_list(struct ice_hw *hw, u16 vsi_handle, + struct ice_adv_fltr_mgmt_list_entry *fm_list) +{ + struct ice_vsi_list_map_info *vsi_list_info; + enum ice_sw_lkup_type lkup_type; + enum ice_status status; + u16 vsi_list_id; + + if (fm_list->rule_info.sw_act.fltr_act != ICE_FWD_TO_VSI_LIST || + fm_list->vsi_count == 0) + return ICE_ERR_PARAM; + + /* A rule with the VSI being removed does not exist */ + if (!test_bit(vsi_handle, fm_list->vsi_list_info->vsi_map)) + return ICE_ERR_DOES_NOT_EXIST; + + lkup_type = ICE_SW_LKUP_LAST; + vsi_list_id = fm_list->rule_info.sw_act.fwd_id.vsi_list_id; + status = ice_update_vsi_list_rule(hw, &vsi_handle, 1, vsi_list_id, true, + ice_aqc_opc_update_sw_rules, + lkup_type); + if (status) + return status; + + fm_list->vsi_count--; + clear_bit(vsi_handle, fm_list->vsi_list_info->vsi_map); + vsi_list_info = fm_list->vsi_list_info; + if (fm_list->vsi_count == 1) { + struct ice_fltr_info tmp_fltr; + u16 rem_vsi_handle; + + rem_vsi_handle = find_first_bit(vsi_list_info->vsi_map, + ICE_MAX_VSI); + if (!ice_is_vsi_valid(hw, rem_vsi_handle)) + return ICE_ERR_OUT_OF_RANGE; + + /* Make sure VSI list is empty before removing it below */ + status = ice_update_vsi_list_rule(hw, &rem_vsi_handle, 1, + vsi_list_id, true, + ice_aqc_opc_update_sw_rules, + lkup_type); + if (status) + return status; + + memset(&tmp_fltr, 0, sizeof(tmp_fltr)); + tmp_fltr.flag = fm_list->rule_info.sw_act.flag; + tmp_fltr.fltr_rule_id = fm_list->rule_info.fltr_rule_id; + fm_list->rule_info.sw_act.fltr_act = ICE_FWD_TO_VSI; + tmp_fltr.fltr_act = ICE_FWD_TO_VSI; + tmp_fltr.fwd_id.hw_vsi_id = + ice_get_hw_vsi_num(hw, rem_vsi_handle); + fm_list->rule_info.sw_act.fwd_id.hw_vsi_id = + ice_get_hw_vsi_num(hw, rem_vsi_handle); + fm_list->rule_info.sw_act.vsi_handle = rem_vsi_handle; + + /* Update the previous switch rule of "MAC forward to VSI" to + * "MAC fwd to VSI list" + */ + status = ice_update_pkt_fwd_rule(hw, &tmp_fltr); + if (status) { + ice_debug(hw, ICE_DBG_SW, "Failed to update pkt fwd rule to FWD_TO_VSI on HW VSI %d, error %d\n", + tmp_fltr.fwd_id.hw_vsi_id, status); + return status; + } + fm_list->vsi_list_info->ref_cnt--; + + /* Remove the VSI list since it is no longer used */ + status = ice_remove_vsi_list_rule(hw, vsi_list_id, lkup_type); + if (status) { + ice_debug(hw, ICE_DBG_SW, "Failed to remove VSI list %d, error %d\n", + vsi_list_id, status); + return status; + } + + list_del(&vsi_list_info->list_entry); + devm_kfree(ice_hw_to_dev(hw), vsi_list_info); + fm_list->vsi_list_info = NULL; + } + + return status; +} + +/** + * ice_rem_adv_rule - removes existing advanced switch rule + * @hw: pointer to the hardware structure + * @lkups: information on the words that needs to be looked up. All words + * together makes one recipe + * @lkups_cnt: num of entries in the lkups array + * @rinfo: Its the pointer to the rule information for the rule + * + * This function can be used to remove 1 rule at a time. The lkups is + * used to describe all the words that forms the "lookup" portion of the + * rule. These words can span multiple protocols. Callers to this function + * need to pass in a list of protocol headers with lookup information along + * and mask that determines which words are valid from the given protocol + * header. rinfo describes other information related to this rule such as + * forwarding IDs, priority of this rule, etc. + */ +static enum ice_status +ice_rem_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, + u16 lkups_cnt, struct ice_adv_rule_info *rinfo) +{ + struct ice_adv_fltr_mgmt_list_entry *list_elem; + struct ice_prot_lkup_ext lkup_exts; + enum ice_status status = 0; + bool remove_rule = false; + struct mutex *rule_lock; /* Lock to protect filter rule list */ + u16 i, rid, vsi_handle; + + memset(&lkup_exts, 0, sizeof(lkup_exts)); + for (i = 0; i < lkups_cnt; i++) { + u16 count; + + if (lkups[i].type >= ICE_PROTOCOL_LAST) + return ICE_ERR_CFG; + + count = ice_fill_valid_words(&lkups[i], &lkup_exts); + if (!count) + return ICE_ERR_CFG; + } + + rid = ice_find_recp(hw, &lkup_exts); + /* If did not find a recipe that match the existing criteria */ + if (rid == ICE_MAX_NUM_RECIPES) + return ICE_ERR_PARAM; + + rule_lock = &hw->switch_info->recp_list[rid].filt_rule_lock; + list_elem = ice_find_adv_rule_entry(hw, lkups, lkups_cnt, rid, rinfo); + /* the rule is already removed */ + if (!list_elem) + return 0; + mutex_lock(rule_lock); + if (list_elem->rule_info.sw_act.fltr_act != ICE_FWD_TO_VSI_LIST) { + remove_rule = true; + } else if (list_elem->vsi_count > 1) { + remove_rule = false; + vsi_handle = rinfo->sw_act.vsi_handle; + status = ice_adv_rem_update_vsi_list(hw, vsi_handle, list_elem); + } else { + vsi_handle = rinfo->sw_act.vsi_handle; + status = ice_adv_rem_update_vsi_list(hw, vsi_handle, list_elem); + if (status) { + mutex_unlock(rule_lock); + return status; + } + if (list_elem->vsi_count == 0) + remove_rule = true; + } + mutex_unlock(rule_lock); + if (remove_rule) { + struct ice_aqc_sw_rules_elem *s_rule; + u16 rule_buf_sz; + + rule_buf_sz = ICE_SW_RULE_RX_TX_NO_HDR_SIZE; + s_rule = kzalloc(rule_buf_sz, GFP_KERNEL); + if (!s_rule) + return ICE_ERR_NO_MEMORY; + s_rule->pdata.lkup_tx_rx.act = 0; + s_rule->pdata.lkup_tx_rx.index = + cpu_to_le16(list_elem->rule_info.fltr_rule_id); + s_rule->pdata.lkup_tx_rx.hdr_len = 0; + status = ice_aq_sw_rules(hw, (struct ice_aqc_sw_rules *)s_rule, + rule_buf_sz, 1, + ice_aqc_opc_remove_sw_rules, NULL); + if (!status || status == ICE_ERR_DOES_NOT_EXIST) { + struct ice_switch_info *sw = hw->switch_info; + + mutex_lock(rule_lock); + list_del(&list_elem->list_entry); + devm_kfree(ice_hw_to_dev(hw), list_elem->lkups); + devm_kfree(ice_hw_to_dev(hw), list_elem); + mutex_unlock(rule_lock); + if (list_empty(&sw->recp_list[rid].filt_rules)) + sw->recp_list[rid].adv_rule = false; + } + kfree(s_rule); + } + return status; +} + +/** + * ice_rem_adv_rule_by_id - removes existing advanced switch rule by ID + * @hw: pointer to the hardware structure + * @remove_entry: data struct which holds rule_id, VSI handle and recipe ID + * + * This function is used to remove 1 rule at a time. The removal is based on + * the remove_entry parameter. This function will remove rule for a given + * vsi_handle with a given rule_id which is passed as parameter in remove_entry + */ +enum ice_status +ice_rem_adv_rule_by_id(struct ice_hw *hw, + struct ice_rule_query_data *remove_entry) +{ + struct ice_adv_fltr_mgmt_list_entry *list_itr; + struct list_head *list_head; + struct ice_adv_rule_info rinfo; + struct ice_switch_info *sw; + + sw = hw->switch_info; + if (!sw->recp_list[remove_entry->rid].recp_created) + return ICE_ERR_PARAM; + list_head = &sw->recp_list[remove_entry->rid].filt_rules; + list_for_each_entry(list_itr, list_head, list_entry) { + if (list_itr->rule_info.fltr_rule_id == + remove_entry->rule_id) { + rinfo = list_itr->rule_info; + rinfo.sw_act.vsi_handle = remove_entry->vsi_handle; + return ice_rem_adv_rule(hw, list_itr->lkups, + list_itr->lkups_cnt, &rinfo); + } + } + /* either list is empty or unable to find rule */ + return ICE_ERR_DOES_NOT_EXIST; +} + /** * ice_replay_vsi_all_fltr - replay all filters stored in bookkeeping lists * @hw: pointer to the hardware structure @@ -2868,12 +5330,15 @@ void ice_rm_all_sw_replay_rule_info(struct ice_hw *hw) if (!sw) return; - for (i = 0; i < ICE_SW_LKUP_LAST; i++) { + for (i = 0; i < ICE_MAX_NUM_RECIPES; i++) { if (!list_empty(&sw->recp_list[i].filt_replay_rules)) { struct list_head *l_head; l_head = &sw->recp_list[i].filt_replay_rules; - ice_rem_sw_rule_info(hw, l_head); + if (!sw->recp_list[i].adv_rule) + ice_rem_sw_rule_info(hw, l_head); + else + ice_rem_adv_rule_info(hw, l_head); } } } diff --git a/drivers/net/ethernet/intel/ice/ice_switch.h b/drivers/net/ethernet/intel/ice/ice_switch.h index e6eeffb3dde9..c4dd2062c469 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.h +++ b/drivers/net/ethernet/intel/ice/ice_switch.h @@ -125,30 +125,121 @@ struct ice_fltr_info { u8 lan_en; /* Indicate if packet can be forwarded to the uplink */ }; +struct ice_adv_lkup_elem { + enum ice_protocol_type type; + union ice_prot_hdr h_u; /* Header values */ + union ice_prot_hdr m_u; /* Mask of header values to match */ +}; + +struct ice_sw_act_ctrl { + /* Source VSI for LOOKUP_TX or source port for LOOKUP_RX */ + u16 src; + u16 flag; + enum ice_sw_fwd_act_type fltr_act; + /* Depending on filter action */ + union { + /* This is a queue ID in case of ICE_FWD_TO_Q and starting + * queue ID in case of ICE_FWD_TO_QGRP. + */ + u16 q_id:11; + u16 vsi_id:10; + u16 hw_vsi_id:10; + u16 vsi_list_id:10; + } fwd_id; + /* software VSI handle */ + u16 vsi_handle; + u8 qgrp_size; +}; + +struct ice_rule_query_data { + /* Recipe ID for which the requested rule was added */ + u16 rid; + /* Rule ID that was added or is supposed to be removed */ + u16 rule_id; + /* vsi_handle for which Rule was added or is supposed to be removed */ + u16 vsi_handle; +}; + +/* This structure allows to pass info about lb_en and lan_en + * flags to ice_add_adv_rule. Values in act would be used + * only if act_valid was set to true, otherwise default + * values would be used. + */ +struct ice_adv_rule_flags_info { + u32 act; + u8 act_valid; /* indicate if flags in act are valid */ +}; + +struct ice_adv_rule_info { + struct ice_sw_act_ctrl sw_act; + u32 priority; + u8 rx; /* true means LOOKUP_RX otherwise LOOKUP_TX */ + u16 fltr_rule_id; + struct ice_adv_rule_flags_info flags_info; +}; + +/* A collection of one or more four word recipe */ struct ice_sw_recipe { - struct list_head l_entry; - - /* To protect modification of filt_rule list - * defined below + /* For a chained recipe the root recipe is what should be used for + * programming rules */ - struct mutex filt_rule_lock; + u8 is_root; + u8 root_rid; + u8 recp_created; - /* List of type ice_fltr_mgmt_list_entry */ + /* Number of extraction words */ + u8 n_ext_words; + /* Protocol ID and Offset pair (extraction word) to describe the + * recipe + */ + struct ice_fv_word ext_words[ICE_MAX_CHAIN_WORDS]; + u16 word_masks[ICE_MAX_CHAIN_WORDS]; + + /* if this recipe is a collection of other recipe */ + u8 big_recp; + + /* if this recipe is part of another bigger recipe then chain index + * corresponding to this recipe + */ + u8 chain_idx; + + /* if this recipe is a collection of other recipe then count of other + * recipes and recipe IDs of those recipes + */ + u8 n_grp_count; + + /* Bit map specifying the IDs associated with this group of recipe */ + DECLARE_BITMAP(r_bitmap, ICE_MAX_NUM_RECIPES); + + /* List of type ice_fltr_mgmt_list_entry or adv_rule */ + u8 adv_rule; struct list_head filt_rules; struct list_head filt_replay_rules; - /* linked list of type recipe_list_entry */ - struct list_head rg_list; - /* linked list of type ice_sw_fv_list_entry*/ - struct list_head fv_list; - struct ice_aqc_recipe_data_elem *r_buf; - u8 recp_count; - u8 root_rid; - u8 num_profs; - u8 *prof_ids; + struct mutex filt_rule_lock; /* protect filter rule structure */ - /* recipe bitmap: what all recipes makes this recipe */ - DECLARE_BITMAP(r_bitmap, ICE_MAX_NUM_RECIPES); + /* Profiles this recipe should be associated with */ + struct list_head fv_list; + + /* Profiles this recipe is associated with */ + u8 num_profs, *prof_ids; + + /* Bit map for possible result indexes */ + DECLARE_BITMAP(res_idxs, ICE_MAX_FV_WORDS); + + /* This allows user to specify the recipe priority. + * For now, this becomes 'fwd_priority' when recipe + * is created, usually recipes can have 'fwd' and 'join' + * priority. + */ + u8 priority; + + struct list_head rg_list; + + /* AQ buffer associated with this recipe */ + struct ice_aqc_recipe_data_elem *root_buf; + /* This struct saves the fv_words for a given lookup */ + struct ice_prot_lkup_ext lkup_exts; }; /* Bookkeeping structure to hold bitmap of VSIs corresponding to VSI list ID */ @@ -186,6 +277,16 @@ struct ice_fltr_mgmt_list_entry { u8 counter_index; }; +struct ice_adv_fltr_mgmt_list_entry { + struct list_head list_entry; + + struct ice_adv_lkup_elem *lkups; + struct ice_adv_rule_info rule_info; + u16 lkups_cnt; + struct ice_vsi_list_map_info *vsi_list_info; + u16 vsi_count; +}; + enum ice_promisc_flags { ICE_PROMISC_UCAST_RX = 0x1, ICE_PROMISC_UCAST_TX = 0x2, @@ -221,6 +322,10 @@ ice_free_res_cntr(struct ice_hw *hw, u8 type, u8 alloc_shared, u16 num_items, u16 counter_id); /* Switch/bridge related commands */ +enum ice_status +ice_add_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, + u16 lkups_cnt, struct ice_adv_rule_info *rinfo, + struct ice_rule_query_data *added_entry); enum ice_status ice_update_sw_rule_bridge_mode(struct ice_hw *hw); enum ice_status ice_add_mac(struct ice_hw *hw, struct list_head *m_lst); enum ice_status ice_remove_mac(struct ice_hw *hw, struct list_head *m_lst); @@ -230,6 +335,8 @@ enum ice_status ice_remove_eth_mac(struct ice_hw *hw, struct list_head *em_list); int ice_cfg_rdma_fltr(struct ice_hw *hw, u16 vsi_handle, bool enable); +bool ice_mac_fltr_exist(struct ice_hw *hw, u8 *mac, u16 vsi_handle); +bool ice_vlan_fltr_exist(struct ice_hw *hw, u16 vlan_id, u16 vsi_handle); void ice_remove_vsi_fltr(struct ice_hw *hw, u16 vsi_handle); enum ice_status ice_add_vlan(struct ice_hw *hw, struct list_head *m_list); @@ -248,6 +355,12 @@ enum ice_status ice_set_vlan_vsi_promisc(struct ice_hw *hw, u16 vsi_handle, u8 promisc_mask, bool rm_vlan_promisc); +enum ice_status +ice_rem_adv_rule_for_vsi(struct ice_hw *hw, u16 vsi_handle); +enum ice_status +ice_rem_adv_rule_by_id(struct ice_hw *hw, + struct ice_rule_query_data *remove_entry); + enum ice_status ice_init_def_sw_recp(struct ice_hw *hw); u16 ice_get_hw_vsi_num(struct ice_hw *hw, u16 vsi_handle); diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.c b/drivers/net/ethernet/intel/ice/ice_tc_lib.c new file mode 100644 index 000000000000..725caa160b13 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.c @@ -0,0 +1,1056 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2019-2021, Intel Corporation. */ + +#include "ice.h" +#include "ice_tc_lib.h" +#include "ice_lib.h" +#include "ice_fltr.h" + +/** + * ice_tc_count_lkups - determine lookup count for switch filter + * @flags: TC-flower flags + * @headers: Pointer to TC flower filter header structure + * @fltr: Pointer to outer TC filter structure + * + * Determine lookup count based on TC flower input for switch filter. + */ +static int +ice_tc_count_lkups(u32 flags, struct ice_tc_flower_lyr_2_4_hdrs *headers, + struct ice_tc_flower_fltr *fltr) +{ + int lkups_cnt = 0; + + if (flags & ICE_TC_FLWR_FIELD_ETH_TYPE_ID) + lkups_cnt++; + + /* are MAC fields specified? */ + if (flags & (ICE_TC_FLWR_FIELD_DST_MAC | ICE_TC_FLWR_FIELD_SRC_MAC)) + lkups_cnt++; + + /* is VLAN specified? */ + if (flags & ICE_TC_FLWR_FIELD_VLAN) + lkups_cnt++; + + /* are IPv[4|6] fields specified? */ + if (flags & (ICE_TC_FLWR_FIELD_DEST_IPV4 | ICE_TC_FLWR_FIELD_SRC_IPV4)) + lkups_cnt++; + else if (flags & (ICE_TC_FLWR_FIELD_DEST_IPV6 | + ICE_TC_FLWR_FIELD_SRC_IPV6)) + lkups_cnt++; + + /* is L4 (TCP/UDP/any other L4 protocol fields) specified? */ + if (flags & (ICE_TC_FLWR_FIELD_DEST_L4_PORT | + ICE_TC_FLWR_FIELD_SRC_L4_PORT)) + lkups_cnt++; + + return lkups_cnt; +} + +/** + * ice_tc_fill_rules - fill filter rules based on TC fltr + * @hw: pointer to HW structure + * @flags: tc flower field flags + * @tc_fltr: pointer to TC flower filter + * @list: list of advance rule elements + * @rule_info: pointer to information about rule + * @l4_proto: pointer to information such as L4 proto type + * + * Fill ice_adv_lkup_elem list based on TC flower flags and + * TC flower headers. This list should be used to add + * advance filter in hardware. + */ +static int +ice_tc_fill_rules(struct ice_hw *hw, u32 flags, + struct ice_tc_flower_fltr *tc_fltr, + struct ice_adv_lkup_elem *list, + struct ice_adv_rule_info *rule_info, + u16 *l4_proto) +{ + struct ice_tc_flower_lyr_2_4_hdrs *headers = &tc_fltr->outer_headers; + int i = 0; + + if (flags & ICE_TC_FLWR_FIELD_ETH_TYPE_ID) { + list[i].type = ICE_ETYPE_OL; + list[i].h_u.ethertype.ethtype_id = headers->l2_key.n_proto; + list[i].m_u.ethertype.ethtype_id = headers->l2_mask.n_proto; + i++; + } + + if (flags & (ICE_TC_FLWR_FIELD_DST_MAC | + ICE_TC_FLWR_FIELD_SRC_MAC)) { + struct ice_tc_l2_hdr *l2_key, *l2_mask; + + l2_key = &headers->l2_key; + l2_mask = &headers->l2_mask; + + list[i].type = ICE_MAC_OFOS; + if (flags & ICE_TC_FLWR_FIELD_DST_MAC) { + ether_addr_copy(list[i].h_u.eth_hdr.dst_addr, + l2_key->dst_mac); + ether_addr_copy(list[i].m_u.eth_hdr.dst_addr, + l2_mask->dst_mac); + } + if (flags & ICE_TC_FLWR_FIELD_SRC_MAC) { + ether_addr_copy(list[i].h_u.eth_hdr.src_addr, + l2_key->src_mac); + ether_addr_copy(list[i].m_u.eth_hdr.src_addr, + l2_mask->src_mac); + } + i++; + } + + /* copy VLAN info */ + if (flags & ICE_TC_FLWR_FIELD_VLAN) { + list[i].type = ICE_VLAN_OFOS; + list[i].h_u.vlan_hdr.vlan = headers->vlan_hdr.vlan_id; + list[i].m_u.vlan_hdr.vlan = cpu_to_be16(0xFFFF); + i++; + } + + /* copy L3 (IPv[4|6]: src, dest) address */ + if (flags & (ICE_TC_FLWR_FIELD_DEST_IPV4 | + ICE_TC_FLWR_FIELD_SRC_IPV4)) { + struct ice_tc_l3_hdr *l3_key, *l3_mask; + + list[i].type = ICE_IPV4_OFOS; + l3_key = &headers->l3_key; + l3_mask = &headers->l3_mask; + if (flags & ICE_TC_FLWR_FIELD_DEST_IPV4) { + list[i].h_u.ipv4_hdr.dst_addr = l3_key->dst_ipv4; + list[i].m_u.ipv4_hdr.dst_addr = l3_mask->dst_ipv4; + } + if (flags & ICE_TC_FLWR_FIELD_SRC_IPV4) { + list[i].h_u.ipv4_hdr.src_addr = l3_key->src_ipv4; + list[i].m_u.ipv4_hdr.src_addr = l3_mask->src_ipv4; + } + i++; + } else if (flags & (ICE_TC_FLWR_FIELD_DEST_IPV6 | + ICE_TC_FLWR_FIELD_SRC_IPV6)) { + struct ice_ipv6_hdr *ipv6_hdr, *ipv6_mask; + struct ice_tc_l3_hdr *l3_key, *l3_mask; + + list[i].type = ICE_IPV6_OFOS; + ipv6_hdr = &list[i].h_u.ipv6_hdr; + ipv6_mask = &list[i].m_u.ipv6_hdr; + l3_key = &headers->l3_key; + l3_mask = &headers->l3_mask; + + if (flags & ICE_TC_FLWR_FIELD_DEST_IPV6) { + memcpy(&ipv6_hdr->dst_addr, &l3_key->dst_ipv6_addr, + sizeof(l3_key->dst_ipv6_addr)); + memcpy(&ipv6_mask->dst_addr, &l3_mask->dst_ipv6_addr, + sizeof(l3_mask->dst_ipv6_addr)); + } + if (flags & ICE_TC_FLWR_FIELD_SRC_IPV6) { + memcpy(&ipv6_hdr->src_addr, &l3_key->src_ipv6_addr, + sizeof(l3_key->src_ipv6_addr)); + memcpy(&ipv6_mask->src_addr, &l3_mask->src_ipv6_addr, + sizeof(l3_mask->src_ipv6_addr)); + } + i++; + } + + /* copy L4 (src, dest) port */ + if (flags & (ICE_TC_FLWR_FIELD_DEST_L4_PORT | + ICE_TC_FLWR_FIELD_SRC_L4_PORT)) { + struct ice_tc_l4_hdr *l4_key, *l4_mask; + + l4_key = &headers->l4_key; + l4_mask = &headers->l4_mask; + if (headers->l3_key.ip_proto == IPPROTO_TCP) { + list[i].type = ICE_TCP_IL; + /* detected L4 proto is TCP */ + if (l4_proto) + *l4_proto = IPPROTO_TCP; + } else if (headers->l3_key.ip_proto == IPPROTO_UDP) { + list[i].type = ICE_UDP_ILOS; + /* detected L4 proto is UDP */ + if (l4_proto) + *l4_proto = IPPROTO_UDP; + } + if (flags & ICE_TC_FLWR_FIELD_DEST_L4_PORT) { + list[i].h_u.l4_hdr.dst_port = l4_key->dst_port; + list[i].m_u.l4_hdr.dst_port = l4_mask->dst_port; + } + if (flags & ICE_TC_FLWR_FIELD_SRC_L4_PORT) { + list[i].h_u.l4_hdr.src_port = l4_key->src_port; + list[i].m_u.l4_hdr.src_port = l4_mask->src_port; + } + i++; + } + + return i; +} + +static int +ice_eswitch_tc_parse_action(struct ice_tc_flower_fltr *fltr, + struct flow_action_entry *act) +{ + struct ice_repr *repr; + + switch (act->id) { + case FLOW_ACTION_DROP: + fltr->action.fltr_act = ICE_DROP_PACKET; + break; + + case FLOW_ACTION_REDIRECT: + fltr->action.fltr_act = ICE_FWD_TO_VSI; + + if (ice_is_port_repr_netdev(act->dev)) { + repr = ice_netdev_to_repr(act->dev); + + fltr->dest_vsi = repr->src_vsi; + fltr->direction = ICE_ESWITCH_FLTR_INGRESS; + } else if (netif_is_ice(act->dev)) { + struct ice_netdev_priv *np = netdev_priv(act->dev); + + fltr->dest_vsi = np->vsi; + fltr->direction = ICE_ESWITCH_FLTR_EGRESS; + } else { + NL_SET_ERR_MSG_MOD(fltr->extack, "Unsupported netdevice in switchdev mode"); + return -EINVAL; + } + + break; + + default: + NL_SET_ERR_MSG_MOD(fltr->extack, "Unsupported action in switchdev mode"); + return -EINVAL; + } + + return 0; +} + +static int +ice_eswitch_add_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr) +{ + struct ice_tc_flower_lyr_2_4_hdrs *headers = &fltr->outer_headers; + struct ice_adv_rule_info rule_info = { 0 }; + struct ice_rule_query_data rule_added; + struct ice_hw *hw = &vsi->back->hw; + struct ice_adv_lkup_elem *list; + u32 flags = fltr->flags; + enum ice_status status; + int lkups_cnt; + int ret = 0; + int i; + + if (!flags || (flags & (ICE_TC_FLWR_FIELD_ENC_DEST_IPV4 | + ICE_TC_FLWR_FIELD_ENC_SRC_IPV4 | + ICE_TC_FLWR_FIELD_ENC_DEST_IPV6 | + ICE_TC_FLWR_FIELD_ENC_SRC_IPV6 | + ICE_TC_FLWR_FIELD_ENC_SRC_L4_PORT))) { + NL_SET_ERR_MSG_MOD(fltr->extack, "Unsupported encap field(s)"); + return -EOPNOTSUPP; + } + + lkups_cnt = ice_tc_count_lkups(flags, headers, fltr); + list = kcalloc(lkups_cnt, sizeof(*list), GFP_ATOMIC); + if (!list) + return -ENOMEM; + + i = ice_tc_fill_rules(hw, flags, fltr, list, &rule_info, NULL); + if (i != lkups_cnt) { + ret = -EINVAL; + goto exit; + } + + rule_info.sw_act.fltr_act = fltr->action.fltr_act; + if (fltr->action.fltr_act != ICE_DROP_PACKET) + rule_info.sw_act.vsi_handle = fltr->dest_vsi->idx; + /* For now, making priority to be highest, and it also becomes + * the priority for recipe which will get created as a result of + * new extraction sequence based on input set. + * Priority '7' is max val for switch recipe, higher the number + * results into order of switch rule evaluation. + */ + rule_info.priority = 7; + + if (fltr->direction == ICE_ESWITCH_FLTR_INGRESS) { + rule_info.sw_act.flag |= ICE_FLTR_RX; + rule_info.sw_act.src = hw->pf_id; + rule_info.rx = true; + } else { + rule_info.sw_act.flag |= ICE_FLTR_TX; + rule_info.sw_act.src = vsi->idx; + rule_info.rx = false; + rule_info.flags_info.act = ICE_SINGLE_ACT_LAN_ENABLE; + rule_info.flags_info.act_valid = true; + } + + /* specify the cookie as filter_rule_id */ + rule_info.fltr_rule_id = fltr->cookie; + + status = ice_add_adv_rule(hw, list, lkups_cnt, &rule_info, &rule_added); + if (status == ICE_ERR_ALREADY_EXISTS) { + NL_SET_ERR_MSG_MOD(fltr->extack, "Unable to add filter because it already exist"); + ret = -EINVAL; + goto exit; + } else if (status) { + NL_SET_ERR_MSG_MOD(fltr->extack, "Unable to add filter due to error"); + ret = -EIO; + goto exit; + } + + /* store the output params, which are needed later for removing + * advanced switch filter + */ + fltr->rid = rule_added.rid; + fltr->rule_id = rule_added.rule_id; + +exit: + kfree(list); + return ret; +} + +/** + * ice_add_tc_flower_adv_fltr - add appropriate filter rules + * @vsi: Pointer to VSI + * @tc_fltr: Pointer to TC flower filter structure + * + * based on filter parameters using Advance recipes supported + * by OS package. + */ +static int +ice_add_tc_flower_adv_fltr(struct ice_vsi *vsi, + struct ice_tc_flower_fltr *tc_fltr) +{ + struct ice_tc_flower_lyr_2_4_hdrs *headers = &tc_fltr->outer_headers; + struct ice_adv_rule_info rule_info = {0}; + struct ice_rule_query_data rule_added; + struct ice_adv_lkup_elem *list; + struct ice_pf *pf = vsi->back; + struct ice_hw *hw = &pf->hw; + u32 flags = tc_fltr->flags; + struct ice_vsi *ch_vsi; + struct device *dev; + u16 lkups_cnt = 0; + u16 l4_proto = 0; + int ret = 0; + u16 i = 0; + + dev = ice_pf_to_dev(pf); + if (ice_is_safe_mode(pf)) { + NL_SET_ERR_MSG_MOD(tc_fltr->extack, "Unable to add filter because driver is in safe mode"); + return -EOPNOTSUPP; + } + + if (!flags || (flags & (ICE_TC_FLWR_FIELD_ENC_DEST_IPV4 | + ICE_TC_FLWR_FIELD_ENC_SRC_IPV4 | + ICE_TC_FLWR_FIELD_ENC_DEST_IPV6 | + ICE_TC_FLWR_FIELD_ENC_SRC_IPV6 | + ICE_TC_FLWR_FIELD_ENC_SRC_L4_PORT))) { + NL_SET_ERR_MSG_MOD(tc_fltr->extack, "Unsupported encap field(s)"); + return -EOPNOTSUPP; + } + + /* get the channel (aka ADQ VSI) */ + if (tc_fltr->dest_vsi) + ch_vsi = tc_fltr->dest_vsi; + else + ch_vsi = vsi->tc_map_vsi[tc_fltr->action.tc_class]; + + lkups_cnt = ice_tc_count_lkups(flags, headers, tc_fltr); + list = kcalloc(lkups_cnt, sizeof(*list), GFP_ATOMIC); + if (!list) + return -ENOMEM; + + i = ice_tc_fill_rules(hw, flags, tc_fltr, list, &rule_info, &l4_proto); + if (i != lkups_cnt) { + ret = -EINVAL; + goto exit; + } + + rule_info.sw_act.fltr_act = tc_fltr->action.fltr_act; + if (tc_fltr->action.tc_class >= ICE_CHNL_START_TC) { + if (!ch_vsi) { + NL_SET_ERR_MSG_MOD(tc_fltr->extack, "Unable to add filter because specified destination doesn't exist"); + ret = -EINVAL; + goto exit; + } + + rule_info.sw_act.fltr_act = ICE_FWD_TO_VSI; + rule_info.sw_act.vsi_handle = ch_vsi->idx; + rule_info.priority = 7; + rule_info.sw_act.src = hw->pf_id; + rule_info.rx = true; + dev_dbg(dev, "add switch rule for TC:%u vsi_idx:%u, lkups_cnt:%u\n", + tc_fltr->action.tc_class, + rule_info.sw_act.vsi_handle, lkups_cnt); + } else { + rule_info.sw_act.flag |= ICE_FLTR_TX; + rule_info.sw_act.src = vsi->idx; + rule_info.rx = false; + } + + /* specify the cookie as filter_rule_id */ + rule_info.fltr_rule_id = tc_fltr->cookie; + + ret = ice_add_adv_rule(hw, list, lkups_cnt, &rule_info, &rule_added); + if (ret == -EEXIST) { + NL_SET_ERR_MSG_MOD(tc_fltr->extack, + "Unable to add filter because it already exist"); + ret = -EINVAL; + goto exit; + } else if (ret) { + NL_SET_ERR_MSG_MOD(tc_fltr->extack, + "Unable to add filter due to error"); + ret = -EIO; + goto exit; + } + + /* store the output params, which are needed later for removing + * advanced switch filter + */ + tc_fltr->rid = rule_added.rid; + tc_fltr->rule_id = rule_added.rule_id; + if (tc_fltr->action.tc_class > 0 && ch_vsi) { + /* For PF ADQ, VSI type is set as ICE_VSI_CHNL, and + * for PF ADQ filter, it is not yet set in tc_fltr, + * hence store the dest_vsi ptr in tc_fltr + */ + if (ch_vsi->type == ICE_VSI_CHNL) + tc_fltr->dest_vsi = ch_vsi; + /* keep track of advanced switch filter for + * destination VSI (channel VSI) + */ + ch_vsi->num_chnl_fltr++; + /* in this case, dest_id is VSI handle (sw handle) */ + tc_fltr->dest_id = rule_added.vsi_handle; + + /* keeps track of channel filters for PF VSI */ + if (vsi->type == ICE_VSI_PF && + (flags & (ICE_TC_FLWR_FIELD_DST_MAC | + ICE_TC_FLWR_FIELD_ENC_DST_MAC))) + pf->num_dmac_chnl_fltrs++; + } + dev_dbg(dev, "added switch rule (lkups_cnt %u, flags 0x%x) for TC %u, rid %u, rule_id %u, vsi_idx %u\n", + lkups_cnt, flags, + tc_fltr->action.tc_class, rule_added.rid, + rule_added.rule_id, rule_added.vsi_handle); +exit: + kfree(list); + return ret; +} + +/** + * ice_tc_set_ipv4 - Parse IPv4 addresses from TC flower filter + * @match: Pointer to flow match structure + * @fltr: Pointer to filter structure + * @headers: inner or outer header fields + */ +static int +ice_tc_set_ipv4(struct flow_match_ipv4_addrs *match, + struct ice_tc_flower_fltr *fltr, + struct ice_tc_flower_lyr_2_4_hdrs *headers) +{ + if (match->key->dst) { + fltr->flags |= ICE_TC_FLWR_FIELD_DEST_IPV4; + headers->l3_key.dst_ipv4 = match->key->dst; + headers->l3_mask.dst_ipv4 = match->mask->dst; + } + if (match->key->src) { + fltr->flags |= ICE_TC_FLWR_FIELD_SRC_IPV4; + headers->l3_key.src_ipv4 = match->key->src; + headers->l3_mask.src_ipv4 = match->mask->src; + } + return 0; +} + +/** + * ice_tc_set_ipv6 - Parse IPv6 addresses from TC flower filter + * @match: Pointer to flow match structure + * @fltr: Pointer to filter structure + * @headers: inner or outer header fields + */ +static int +ice_tc_set_ipv6(struct flow_match_ipv6_addrs *match, + struct ice_tc_flower_fltr *fltr, + struct ice_tc_flower_lyr_2_4_hdrs *headers) +{ + struct ice_tc_l3_hdr *l3_key, *l3_mask; + + /* src and dest IPV6 address should not be LOOPBACK + * (0:0:0:0:0:0:0:1), which can be represented as ::1 + */ + if (ipv6_addr_loopback(&match->key->dst) || + ipv6_addr_loopback(&match->key->src)) { + NL_SET_ERR_MSG_MOD(fltr->extack, "Bad IPv6, addr is LOOPBACK"); + return -EINVAL; + } + /* if src/dest IPv6 address is *,* error */ + if (ipv6_addr_any(&match->mask->dst) && + ipv6_addr_any(&match->mask->src)) { + NL_SET_ERR_MSG_MOD(fltr->extack, "Bad src/dest IPv6, addr is any"); + return -EINVAL; + } + if (!ipv6_addr_any(&match->mask->dst)) + fltr->flags |= ICE_TC_FLWR_FIELD_DEST_IPV6; + if (!ipv6_addr_any(&match->mask->src)) + fltr->flags |= ICE_TC_FLWR_FIELD_SRC_IPV6; + + l3_key = &headers->l3_key; + l3_mask = &headers->l3_mask; + + if (fltr->flags & ICE_TC_FLWR_FIELD_SRC_IPV6) { + memcpy(&l3_key->src_ipv6_addr, &match->key->src.s6_addr, + sizeof(match->key->src.s6_addr)); + memcpy(&l3_mask->src_ipv6_addr, &match->mask->src.s6_addr, + sizeof(match->mask->src.s6_addr)); + } + if (fltr->flags & ICE_TC_FLWR_FIELD_DEST_IPV6) { + memcpy(&l3_key->dst_ipv6_addr, &match->key->dst.s6_addr, + sizeof(match->key->dst.s6_addr)); + memcpy(&l3_mask->dst_ipv6_addr, &match->mask->dst.s6_addr, + sizeof(match->mask->dst.s6_addr)); + } + + return 0; +} + +/** + * ice_tc_set_port - Parse ports from TC flower filter + * @match: Flow match structure + * @fltr: Pointer to filter structure + * @headers: inner or outer header fields + */ +static int +ice_tc_set_port(struct flow_match_ports match, + struct ice_tc_flower_fltr *fltr, + struct ice_tc_flower_lyr_2_4_hdrs *headers) +{ + if (match.key->dst) { + fltr->flags |= ICE_TC_FLWR_FIELD_DEST_L4_PORT; + headers->l4_key.dst_port = match.key->dst; + headers->l4_mask.dst_port = match.mask->dst; + } + if (match.key->src) { + fltr->flags |= ICE_TC_FLWR_FIELD_SRC_L4_PORT; + headers->l4_key.src_port = match.key->src; + headers->l4_mask.src_port = match.mask->src; + } + return 0; +} + +/** + * ice_parse_cls_flower - Parse TC flower filters provided by kernel + * @vsi: Pointer to the VSI + * @filter_dev: Pointer to device on which filter is being added + * @f: Pointer to struct flow_cls_offload + * @fltr: Pointer to filter structure + */ +static int +ice_parse_cls_flower(struct net_device *filter_dev, struct ice_vsi *vsi, + struct flow_cls_offload *f, + struct ice_tc_flower_fltr *fltr) +{ + struct ice_tc_flower_lyr_2_4_hdrs *headers = &fltr->outer_headers; + struct flow_rule *rule = flow_cls_offload_flow_rule(f); + u16 n_proto_mask = 0, n_proto_key = 0, addr_type = 0; + struct flow_dissector *dissector; + + dissector = rule->match.dissector; + + if (dissector->used_keys & + ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) | + BIT(FLOW_DISSECTOR_KEY_BASIC) | + BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) | + BIT(FLOW_DISSECTOR_KEY_VLAN) | + BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | + BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | + BIT(FLOW_DISSECTOR_KEY_ENC_CONTROL) | + BIT(FLOW_DISSECTOR_KEY_ENC_IP) | + BIT(FLOW_DISSECTOR_KEY_PORTS))) { + NL_SET_ERR_MSG_MOD(fltr->extack, "Unsupported key used"); + return -EOPNOTSUPP; + } + + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) { + struct flow_match_basic match; + + flow_rule_match_basic(rule, &match); + + n_proto_key = ntohs(match.key->n_proto); + n_proto_mask = ntohs(match.mask->n_proto); + + if (n_proto_key == ETH_P_ALL || n_proto_key == 0) { + n_proto_key = 0; + n_proto_mask = 0; + } else { + fltr->flags |= ICE_TC_FLWR_FIELD_ETH_TYPE_ID; + } + + headers->l2_key.n_proto = cpu_to_be16(n_proto_key); + headers->l2_mask.n_proto = cpu_to_be16(n_proto_mask); + headers->l3_key.ip_proto = match.key->ip_proto; + } + + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { + struct flow_match_eth_addrs match; + + flow_rule_match_eth_addrs(rule, &match); + + if (!is_zero_ether_addr(match.key->dst)) { + ether_addr_copy(headers->l2_key.dst_mac, + match.key->dst); + ether_addr_copy(headers->l2_mask.dst_mac, + match.mask->dst); + fltr->flags |= ICE_TC_FLWR_FIELD_DST_MAC; + } + + if (!is_zero_ether_addr(match.key->src)) { + ether_addr_copy(headers->l2_key.src_mac, + match.key->src); + ether_addr_copy(headers->l2_mask.src_mac, + match.mask->src); + fltr->flags |= ICE_TC_FLWR_FIELD_SRC_MAC; + } + } + + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN) || + is_vlan_dev(filter_dev)) { + struct flow_dissector_key_vlan mask; + struct flow_dissector_key_vlan key; + struct flow_match_vlan match; + + if (is_vlan_dev(filter_dev)) { + match.key = &key; + match.key->vlan_id = vlan_dev_vlan_id(filter_dev); + match.key->vlan_priority = 0; + match.mask = &mask; + memset(match.mask, 0xff, sizeof(*match.mask)); + match.mask->vlan_priority = 0; + } else { + flow_rule_match_vlan(rule, &match); + } + + if (match.mask->vlan_id) { + if (match.mask->vlan_id == VLAN_VID_MASK) { + fltr->flags |= ICE_TC_FLWR_FIELD_VLAN; + } else { + NL_SET_ERR_MSG_MOD(fltr->extack, "Bad VLAN mask"); + return -EINVAL; + } + } + + headers->vlan_hdr.vlan_id = + cpu_to_be16(match.key->vlan_id & VLAN_VID_MASK); + if (match.mask->vlan_priority) + headers->vlan_hdr.vlan_prio = match.key->vlan_priority; + } + + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL)) { + struct flow_match_control match; + + flow_rule_match_control(rule, &match); + + addr_type = match.key->addr_type; + } + + if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { + struct flow_match_ipv4_addrs match; + + flow_rule_match_ipv4_addrs(rule, &match); + if (ice_tc_set_ipv4(&match, fltr, headers)) + return -EINVAL; + } + + if (addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) { + struct flow_match_ipv6_addrs match; + + flow_rule_match_ipv6_addrs(rule, &match); + if (ice_tc_set_ipv6(&match, fltr, headers)) + return -EINVAL; + } + + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_PORTS)) { + struct flow_match_ports match; + + flow_rule_match_ports(rule, &match); + if (ice_tc_set_port(match, fltr, headers)) + return -EINVAL; + switch (headers->l3_key.ip_proto) { + case IPPROTO_TCP: + case IPPROTO_UDP: + break; + default: + NL_SET_ERR_MSG_MOD(fltr->extack, "Only UDP and TCP transport are supported"); + return -EINVAL; + } + } + return 0; +} + +/** + * ice_add_switch_fltr - Add TC flower filters + * @vsi: Pointer to VSI + * @fltr: Pointer to struct ice_tc_flower_fltr + * + * Add filter in HW switch block + */ +static int +ice_add_switch_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr) +{ + if (fltr->action.fltr_act == ICE_FWD_TO_QGRP) + return -EOPNOTSUPP; + + if (ice_is_eswitch_mode_switchdev(vsi->back)) + return ice_eswitch_add_tc_fltr(vsi, fltr); + + return ice_add_tc_flower_adv_fltr(vsi, fltr); +} + +/** + * ice_handle_tclass_action - Support directing to a traffic class + * @vsi: Pointer to VSI + * @cls_flower: Pointer to TC flower offload structure + * @fltr: Pointer to TC flower filter structure + * + * Support directing traffic to a traffic class + */ +static int +ice_handle_tclass_action(struct ice_vsi *vsi, + struct flow_cls_offload *cls_flower, + struct ice_tc_flower_fltr *fltr) +{ + int tc = tc_classid_to_hwtc(vsi->netdev, cls_flower->classid); + struct ice_vsi *main_vsi; + + if (tc < 0) { + NL_SET_ERR_MSG_MOD(fltr->extack, "Unable to add filter because specified destination is invalid"); + return -EINVAL; + } + if (!tc) { + NL_SET_ERR_MSG_MOD(fltr->extack, "Unable to add filter because of invalid destination"); + return -EINVAL; + } + + if (!(vsi->all_enatc & BIT(tc))) { + NL_SET_ERR_MSG_MOD(fltr->extack, "Unable to add filter because of non-existence destination"); + return -EINVAL; + } + + /* Redirect to a TC class or Queue Group */ + main_vsi = ice_get_main_vsi(vsi->back); + if (!main_vsi || !main_vsi->netdev) { + NL_SET_ERR_MSG_MOD(fltr->extack, + "Unable to add filter because of invalid netdevice"); + return -EINVAL; + } + + if ((fltr->flags & ICE_TC_FLWR_FIELD_TENANT_ID) && + (fltr->flags & (ICE_TC_FLWR_FIELD_DST_MAC | + ICE_TC_FLWR_FIELD_SRC_MAC))) { + NL_SET_ERR_MSG_MOD(fltr->extack, + "Unable to add filter because filter using tunnel key and inner MAC is unsupported combination"); + return -EOPNOTSUPP; + } + + /* For ADQ, filter must include dest MAC address, otherwise unwanted + * packets with unrelated MAC address get delivered to ADQ VSIs as long + * as remaining filter criteria is satisfied such as dest IP address + * and dest/src L4 port. Following code is trying to handle: + * 1. For non-tunnel, if user specify MAC addresses, use them (means + * this code won't do anything + * 2. For non-tunnel, if user didn't specify MAC address, add implicit + * dest MAC to be lower netdev's active unicast MAC address + */ + if (!(fltr->flags & ICE_TC_FLWR_FIELD_DST_MAC)) { + ether_addr_copy(fltr->outer_headers.l2_key.dst_mac, + main_vsi->netdev->dev_addr); + eth_broadcast_addr(fltr->outer_headers.l2_mask.dst_mac); + fltr->flags |= ICE_TC_FLWR_FIELD_DST_MAC; + } + + /* validate specified dest MAC address, make sure either it belongs to + * lower netdev or any of MACVLAN. MACVLANs MAC address are added as + * unicast MAC filter destined to main VSI. + */ + if (!ice_mac_fltr_exist(&main_vsi->back->hw, + fltr->outer_headers.l2_key.dst_mac, + main_vsi->idx)) { + NL_SET_ERR_MSG_MOD(fltr->extack, + "Unable to add filter because legacy MAC filter for specified destination doesn't exist"); + return -EINVAL; + } + + /* Make sure VLAN is already added to main VSI, before allowing ADQ to + * add a VLAN based filter such as MAC + VLAN + L4 port. + */ + if (fltr->flags & ICE_TC_FLWR_FIELD_VLAN) { + u16 vlan_id = be16_to_cpu(fltr->outer_headers.vlan_hdr.vlan_id); + + if (!ice_vlan_fltr_exist(&main_vsi->back->hw, vlan_id, + main_vsi->idx)) { + NL_SET_ERR_MSG_MOD(fltr->extack, + "Unable to add filter because legacy VLAN filter for specified destination doesn't exist"); + return -EINVAL; + } + } + fltr->action.fltr_act = ICE_FWD_TO_VSI; + fltr->action.tc_class = tc; + + return 0; +} + +/** + * ice_parse_tc_flower_actions - Parse the actions for a TC filter + * @vsi: Pointer to VSI + * @cls_flower: Pointer to TC flower offload structure + * @fltr: Pointer to TC flower filter structure + * + * Parse the actions for a TC filter + */ +static int +ice_parse_tc_flower_actions(struct ice_vsi *vsi, + struct flow_cls_offload *cls_flower, + struct ice_tc_flower_fltr *fltr) +{ + struct flow_rule *rule = flow_cls_offload_flow_rule(cls_flower); + struct flow_action *flow_action = &rule->action; + struct flow_action_entry *act; + int i; + + if (cls_flower->classid) + return ice_handle_tclass_action(vsi, cls_flower, fltr); + + if (!flow_action_has_entries(flow_action)) + return -EINVAL; + + flow_action_for_each(i, act, flow_action) { + if (ice_is_eswitch_mode_switchdev(vsi->back)) { + int err = ice_eswitch_tc_parse_action(fltr, act); + + if (err) + return err; + continue; + } + /* Allow only one rule per filter */ + + /* Drop action */ + if (act->id == FLOW_ACTION_DROP) { + NL_SET_ERR_MSG_MOD(fltr->extack, "Unsupported action DROP"); + return -EINVAL; + } + fltr->action.fltr_act = ICE_FWD_TO_VSI; + } + return 0; +} + +/** + * ice_del_tc_fltr - deletes a filter from HW table + * @vsi: Pointer to VSI + * @fltr: Pointer to struct ice_tc_flower_fltr + * + * This function deletes a filter from HW table and manages book-keeping + */ +static int ice_del_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr) +{ + struct ice_rule_query_data rule_rem; + struct ice_pf *pf = vsi->back; + int err; + + rule_rem.rid = fltr->rid; + rule_rem.rule_id = fltr->rule_id; + rule_rem.vsi_handle = fltr->dest_id; + err = ice_rem_adv_rule_by_id(&pf->hw, &rule_rem); + if (err) { + if (err == ICE_ERR_DOES_NOT_EXIST) { + NL_SET_ERR_MSG_MOD(fltr->extack, "Filter does not exist"); + return -ENOENT; + } + NL_SET_ERR_MSG_MOD(fltr->extack, "Failed to delete TC flower filter"); + return -EIO; + } + + /* update advanced switch filter count for destination + * VSI if filter destination was VSI + */ + if (fltr->dest_vsi) { + if (fltr->dest_vsi->type == ICE_VSI_CHNL) { + fltr->dest_vsi->num_chnl_fltr--; + + /* keeps track of channel filters for PF VSI */ + if (vsi->type == ICE_VSI_PF && + (fltr->flags & (ICE_TC_FLWR_FIELD_DST_MAC | + ICE_TC_FLWR_FIELD_ENC_DST_MAC))) + pf->num_dmac_chnl_fltrs--; + } + } + return 0; +} + +/** + * ice_add_tc_fltr - adds a TC flower filter + * @netdev: Pointer to netdev + * @vsi: Pointer to VSI + * @f: Pointer to flower offload structure + * @__fltr: Pointer to struct ice_tc_flower_fltr + * + * This function parses TC-flower input fields, parses action, + * and adds a filter. + */ +static int +ice_add_tc_fltr(struct net_device *netdev, struct ice_vsi *vsi, + struct flow_cls_offload *f, + struct ice_tc_flower_fltr **__fltr) +{ + struct ice_tc_flower_fltr *fltr; + int err; + + /* by default, set output to be INVALID */ + *__fltr = NULL; + + fltr = kzalloc(sizeof(*fltr), GFP_KERNEL); + if (!fltr) + return -ENOMEM; + + fltr->cookie = f->cookie; + fltr->extack = f->common.extack; + fltr->src_vsi = vsi; + INIT_HLIST_NODE(&fltr->tc_flower_node); + + err = ice_parse_cls_flower(netdev, vsi, f, fltr); + if (err < 0) + goto err; + + err = ice_parse_tc_flower_actions(vsi, f, fltr); + if (err < 0) + goto err; + + err = ice_add_switch_fltr(vsi, fltr); + if (err < 0) + goto err; + + /* return the newly created filter */ + *__fltr = fltr; + + return 0; +err: + kfree(fltr); + return err; +} + +/** + * ice_find_tc_flower_fltr - Find the TC flower filter in the list + * @pf: Pointer to PF + * @cookie: filter specific cookie + */ +static struct ice_tc_flower_fltr * +ice_find_tc_flower_fltr(struct ice_pf *pf, unsigned long cookie) +{ + struct ice_tc_flower_fltr *fltr; + + hlist_for_each_entry(fltr, &pf->tc_flower_fltr_list, tc_flower_node) + if (cookie == fltr->cookie) + return fltr; + + return NULL; +} + +/** + * ice_add_cls_flower - add TC flower filters + * @netdev: Pointer to filter device + * @vsi: Pointer to VSI + * @cls_flower: Pointer to flower offload structure + */ +int +ice_add_cls_flower(struct net_device *netdev, struct ice_vsi *vsi, + struct flow_cls_offload *cls_flower) +{ + struct netlink_ext_ack *extack = cls_flower->common.extack; + struct net_device *vsi_netdev = vsi->netdev; + struct ice_tc_flower_fltr *fltr; + struct ice_pf *pf = vsi->back; + int err; + + if (ice_is_reset_in_progress(pf->state)) + return -EBUSY; + if (test_bit(ICE_FLAG_FW_LLDP_AGENT, pf->flags)) + return -EINVAL; + + if (ice_is_port_repr_netdev(netdev)) + vsi_netdev = netdev; + + if (!(vsi_netdev->features & NETIF_F_HW_TC) && + !test_bit(ICE_FLAG_CLS_FLOWER, pf->flags)) { + /* Based on TC indirect notifications from kernel, all ice + * devices get an instance of rule from higher level device. + * Avoid triggering explicit error in this case. + */ + if (netdev == vsi_netdev) + NL_SET_ERR_MSG_MOD(extack, "can't apply TC flower filters, turn ON hw-tc-offload and try again"); + return -EINVAL; + } + + /* avoid duplicate entries, if exists - return error */ + fltr = ice_find_tc_flower_fltr(pf, cls_flower->cookie); + if (fltr) { + NL_SET_ERR_MSG_MOD(extack, "filter cookie already exists, ignoring"); + return -EEXIST; + } + + /* prep and add TC-flower filter in HW */ + err = ice_add_tc_fltr(netdev, vsi, cls_flower, &fltr); + if (err) + return err; + + /* add filter into an ordered list */ + hlist_add_head(&fltr->tc_flower_node, &pf->tc_flower_fltr_list); + return 0; +} + +/** + * ice_del_cls_flower - delete TC flower filters + * @vsi: Pointer to VSI + * @cls_flower: Pointer to struct flow_cls_offload + */ +int +ice_del_cls_flower(struct ice_vsi *vsi, struct flow_cls_offload *cls_flower) +{ + struct ice_tc_flower_fltr *fltr; + struct ice_pf *pf = vsi->back; + int err; + + /* find filter */ + fltr = ice_find_tc_flower_fltr(pf, cls_flower->cookie); + if (!fltr) { + if (!test_bit(ICE_FLAG_TC_MQPRIO, pf->flags) && + hlist_empty(&pf->tc_flower_fltr_list)) + return 0; + + NL_SET_ERR_MSG_MOD(cls_flower->common.extack, "failed to delete TC flower filter because unable to find it"); + return -EINVAL; + } + + fltr->extack = cls_flower->common.extack; + /* delete filter from HW */ + err = ice_del_tc_fltr(vsi, fltr); + if (err) + return err; + + /* delete filter from an ordered list */ + hlist_del(&fltr->tc_flower_node); + + /* free the filter node */ + kfree(fltr); + + return 0; +} + +/** + * ice_replay_tc_fltrs - replay TC filters + * @pf: pointer to PF struct + */ +void ice_replay_tc_fltrs(struct ice_pf *pf) +{ + struct ice_tc_flower_fltr *fltr; + struct hlist_node *node; + + hlist_for_each_entry_safe(fltr, node, + &pf->tc_flower_fltr_list, + tc_flower_node) { + fltr->extack = NULL; + ice_add_switch_fltr(fltr->src_vsi, fltr); + } +} diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.h b/drivers/net/ethernet/intel/ice/ice_tc_lib.h new file mode 100644 index 000000000000..ee9b284fcc02 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.h @@ -0,0 +1,152 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2019-2021, Intel Corporation. */ + +#ifndef _ICE_TC_LIB_H_ +#define _ICE_TC_LIB_H_ + +#define ICE_TC_FLWR_FIELD_DST_MAC BIT(0) +#define ICE_TC_FLWR_FIELD_SRC_MAC BIT(1) +#define ICE_TC_FLWR_FIELD_VLAN BIT(2) +#define ICE_TC_FLWR_FIELD_DEST_IPV4 BIT(3) +#define ICE_TC_FLWR_FIELD_SRC_IPV4 BIT(4) +#define ICE_TC_FLWR_FIELD_DEST_IPV6 BIT(5) +#define ICE_TC_FLWR_FIELD_SRC_IPV6 BIT(6) +#define ICE_TC_FLWR_FIELD_DEST_L4_PORT BIT(7) +#define ICE_TC_FLWR_FIELD_SRC_L4_PORT BIT(8) +#define ICE_TC_FLWR_FIELD_TENANT_ID BIT(9) +#define ICE_TC_FLWR_FIELD_ENC_DEST_IPV4 BIT(10) +#define ICE_TC_FLWR_FIELD_ENC_SRC_IPV4 BIT(11) +#define ICE_TC_FLWR_FIELD_ENC_DEST_IPV6 BIT(12) +#define ICE_TC_FLWR_FIELD_ENC_SRC_IPV6 BIT(13) +#define ICE_TC_FLWR_FIELD_ENC_DEST_L4_PORT BIT(14) +#define ICE_TC_FLWR_FIELD_ENC_SRC_L4_PORT BIT(15) +#define ICE_TC_FLWR_FIELD_ENC_DST_MAC BIT(16) +#define ICE_TC_FLWR_FIELD_ETH_TYPE_ID BIT(17) + +struct ice_tc_flower_action { + u32 tc_class; + enum ice_sw_fwd_act_type fltr_act; +}; + +struct ice_tc_vlan_hdr { + __be16 vlan_id; /* Only last 12 bits valid */ + u16 vlan_prio; /* Only last 3 bits valid (valid values: 0..7) */ +}; + +struct ice_tc_l2_hdr { + u8 dst_mac[ETH_ALEN]; + u8 src_mac[ETH_ALEN]; + __be16 n_proto; /* Ethernet Protocol */ +}; + +struct ice_tc_l3_hdr { + u8 ip_proto; /* IPPROTO value */ + union { + struct { + struct in_addr dst_ip; + struct in_addr src_ip; + } v4; + struct { + struct in6_addr dst_ip6; + struct in6_addr src_ip6; + } v6; + } ip; +#define dst_ipv6 ip.v6.dst_ip6.s6_addr32 +#define dst_ipv6_addr ip.v6.dst_ip6.s6_addr +#define src_ipv6 ip.v6.src_ip6.s6_addr32 +#define src_ipv6_addr ip.v6.src_ip6.s6_addr +#define dst_ipv4 ip.v4.dst_ip.s_addr +#define src_ipv4 ip.v4.src_ip.s_addr + + u8 tos; + u8 ttl; +}; + +struct ice_tc_l4_hdr { + __be16 dst_port; + __be16 src_port; +}; + +struct ice_tc_flower_lyr_2_4_hdrs { + /* L2 layer fields with their mask */ + struct ice_tc_l2_hdr l2_key; + struct ice_tc_l2_hdr l2_mask; + struct ice_tc_vlan_hdr vlan_hdr; + /* L3 (IPv4[6]) layer fields with their mask */ + struct ice_tc_l3_hdr l3_key; + struct ice_tc_l3_hdr l3_mask; + + /* L4 layer fields with their mask */ + struct ice_tc_l4_hdr l4_key; + struct ice_tc_l4_hdr l4_mask; +}; + +enum ice_eswitch_fltr_direction { + ICE_ESWITCH_FLTR_INGRESS, + ICE_ESWITCH_FLTR_EGRESS, +}; + +struct ice_tc_flower_fltr { + struct hlist_node tc_flower_node; + + /* cookie becomes filter_rule_id if rule is added successfully */ + unsigned long cookie; + + /* add_adv_rule returns information like recipe ID, rule_id. Store + * those values since they are needed to remove advanced rule + */ + u16 rid; + u16 rule_id; + /* this could be queue/vsi_idx (sw handle)/queue_group, depending upon + * destination type + */ + u16 dest_id; + /* if dest_id is vsi_idx, then need to store destination VSI ptr */ + struct ice_vsi *dest_vsi; + /* direction of fltr for eswitch use case */ + enum ice_eswitch_fltr_direction direction; + + /* Parsed TC flower configuration params */ + struct ice_tc_flower_lyr_2_4_hdrs outer_headers; + struct ice_tc_flower_lyr_2_4_hdrs inner_headers; + struct ice_vsi *src_vsi; + __be32 tenant_id; + u32 flags; + struct ice_tc_flower_action action; + + /* cache ptr which is used wherever needed to communicate netlink + * messages + */ + struct netlink_ext_ack *extack; +}; + +/** + * ice_is_chnl_fltr - is this a valid channel filter + * @f: Pointer to tc-flower filter + * + * Criteria to determine of given filter is valid channel filter + * or not is based on its "destination". If destination is hw_tc (aka tc_class) + * and it is non-zero, then it is valid channel (aka ADQ) filter + */ +static inline bool ice_is_chnl_fltr(struct ice_tc_flower_fltr *f) +{ + return !!f->action.tc_class; +} + +/** + * ice_chnl_dmac_fltr_cnt - DMAC based CHNL filter count + * @pf: Pointer to PF + */ +static inline int ice_chnl_dmac_fltr_cnt(struct ice_pf *pf) +{ + return pf->num_dmac_chnl_fltrs; +} + +int +ice_add_cls_flower(struct net_device *netdev, struct ice_vsi *vsi, + struct flow_cls_offload *cls_flower); +int +ice_del_cls_flower(struct ice_vsi *vsi, struct flow_cls_offload *cls_flower); +void ice_replay_tc_fltrs(struct ice_pf *pf); + +#endif /* _ICE_TC_LIB_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_trace.h b/drivers/net/ethernet/intel/ice/ice_trace.h index 9bc0b8fdfc77..cf685247c07a 100644 --- a/drivers/net/ethernet/intel/ice/ice_trace.h +++ b/drivers/net/ethernet/intel/ice/ice_trace.h @@ -64,15 +64,15 @@ DECLARE_EVENT_CLASS(ice_rx_dim_template, TP_ARGS(q_vector, dim), TP_STRUCT__entry(__field(struct ice_q_vector *, q_vector) __field(struct dim *, dim) - __string(devname, q_vector->rx.ring->netdev->name)), + __string(devname, q_vector->rx.rx_ring->netdev->name)), TP_fast_assign(__entry->q_vector = q_vector; __entry->dim = dim; - __assign_str(devname, q_vector->rx.ring->netdev->name);), + __assign_str(devname, q_vector->rx.rx_ring->netdev->name);), TP_printk("netdev: %s Rx-Q: %d dim-state: %d dim-profile: %d dim-tune: %d dim-st-right: %d dim-st-left: %d dim-tired: %d", __get_str(devname), - __entry->q_vector->rx.ring->q_index, + __entry->q_vector->rx.rx_ring->q_index, __entry->dim->state, __entry->dim->profile_ix, __entry->dim->tune_state, @@ -91,15 +91,15 @@ DECLARE_EVENT_CLASS(ice_tx_dim_template, TP_ARGS(q_vector, dim), TP_STRUCT__entry(__field(struct ice_q_vector *, q_vector) __field(struct dim *, dim) - __string(devname, q_vector->tx.ring->netdev->name)), + __string(devname, q_vector->tx.tx_ring->netdev->name)), TP_fast_assign(__entry->q_vector = q_vector; __entry->dim = dim; - __assign_str(devname, q_vector->tx.ring->netdev->name);), + __assign_str(devname, q_vector->tx.tx_ring->netdev->name);), TP_printk("netdev: %s Tx-Q: %d dim-state: %d dim-profile: %d dim-tune: %d dim-st-right: %d dim-st-left: %d dim-tired: %d", __get_str(devname), - __entry->q_vector->tx.ring->q_index, + __entry->q_vector->tx.tx_ring->q_index, __entry->dim->state, __entry->dim->profile_ix, __entry->dim->tune_state, @@ -115,7 +115,7 @@ DEFINE_EVENT(ice_tx_dim_template, ice_tx_dim_work, /* Events related to a vsi & ring */ DECLARE_EVENT_CLASS(ice_tx_template, - TP_PROTO(struct ice_ring *ring, struct ice_tx_desc *desc, + TP_PROTO(struct ice_tx_ring *ring, struct ice_tx_desc *desc, struct ice_tx_buf *buf), TP_ARGS(ring, desc, buf), @@ -135,7 +135,7 @@ DECLARE_EVENT_CLASS(ice_tx_template, #define DEFINE_TX_TEMPLATE_OP_EVENT(name) \ DEFINE_EVENT(ice_tx_template, name, \ - TP_PROTO(struct ice_ring *ring, \ + TP_PROTO(struct ice_tx_ring *ring, \ struct ice_tx_desc *desc, \ struct ice_tx_buf *buf), \ TP_ARGS(ring, desc, buf)) @@ -145,7 +145,7 @@ DEFINE_TX_TEMPLATE_OP_EVENT(ice_clean_tx_irq_unmap); DEFINE_TX_TEMPLATE_OP_EVENT(ice_clean_tx_irq_unmap_eop); DECLARE_EVENT_CLASS(ice_rx_template, - TP_PROTO(struct ice_ring *ring, union ice_32b_rx_flex_desc *desc), + TP_PROTO(struct ice_rx_ring *ring, union ice_32b_rx_flex_desc *desc), TP_ARGS(ring, desc), @@ -161,12 +161,12 @@ DECLARE_EVENT_CLASS(ice_rx_template, __entry->ring, __entry->desc) ); DEFINE_EVENT(ice_rx_template, ice_clean_rx_irq, - TP_PROTO(struct ice_ring *ring, union ice_32b_rx_flex_desc *desc), + TP_PROTO(struct ice_rx_ring *ring, union ice_32b_rx_flex_desc *desc), TP_ARGS(ring, desc) ); DECLARE_EVENT_CLASS(ice_rx_indicate_template, - TP_PROTO(struct ice_ring *ring, union ice_32b_rx_flex_desc *desc, + TP_PROTO(struct ice_rx_ring *ring, union ice_32b_rx_flex_desc *desc, struct sk_buff *skb), TP_ARGS(ring, desc, skb), @@ -186,13 +186,13 @@ DECLARE_EVENT_CLASS(ice_rx_indicate_template, ); DEFINE_EVENT(ice_rx_indicate_template, ice_clean_rx_irq_indicate, - TP_PROTO(struct ice_ring *ring, union ice_32b_rx_flex_desc *desc, + TP_PROTO(struct ice_rx_ring *ring, union ice_32b_rx_flex_desc *desc, struct sk_buff *skb), TP_ARGS(ring, desc, skb) ); DECLARE_EVENT_CLASS(ice_xmit_template, - TP_PROTO(struct ice_ring *ring, struct sk_buff *skb), + TP_PROTO(struct ice_tx_ring *ring, struct sk_buff *skb), TP_ARGS(ring, skb), @@ -210,7 +210,7 @@ DECLARE_EVENT_CLASS(ice_xmit_template, #define DEFINE_XMIT_TEMPLATE_OP_EVENT(name) \ DEFINE_EVENT(ice_xmit_template, name, \ - TP_PROTO(struct ice_ring *ring, struct sk_buff *skb), \ + TP_PROTO(struct ice_tx_ring *ring, struct sk_buff *skb), \ TP_ARGS(ring, skb)) DEFINE_XMIT_TEMPLATE_OP_EVENT(ice_xmit_frame_ring); diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index 4da9420df1b0..bc3ba19dc88f 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -34,7 +34,7 @@ ice_prgm_fdir_fltr(struct ice_vsi *vsi, struct ice_fltr_desc *fdir_desc, struct ice_tx_buf *tx_buf, *first; struct ice_fltr_desc *f_desc; struct ice_tx_desc *tx_desc; - struct ice_ring *tx_ring; + struct ice_tx_ring *tx_ring; struct device *dev; dma_addr_t dma; u32 td_cmd; @@ -108,7 +108,7 @@ ice_prgm_fdir_fltr(struct ice_vsi *vsi, struct ice_fltr_desc *fdir_desc, * @tx_buf: the buffer to free */ static void -ice_unmap_and_free_tx_buf(struct ice_ring *ring, struct ice_tx_buf *tx_buf) +ice_unmap_and_free_tx_buf(struct ice_tx_ring *ring, struct ice_tx_buf *tx_buf) { if (tx_buf->skb) { if (tx_buf->tx_flags & ICE_TX_FLAGS_DUMMY_PKT) @@ -135,7 +135,7 @@ ice_unmap_and_free_tx_buf(struct ice_ring *ring, struct ice_tx_buf *tx_buf) /* tx_buf must be completely set up in the transmit path */ } -static struct netdev_queue *txring_txq(const struct ice_ring *ring) +static struct netdev_queue *txring_txq(const struct ice_tx_ring *ring) { return netdev_get_tx_queue(ring->netdev, ring->q_index); } @@ -144,8 +144,9 @@ static struct netdev_queue *txring_txq(const struct ice_ring *ring) * ice_clean_tx_ring - Free any empty Tx buffers * @tx_ring: ring to be cleaned */ -void ice_clean_tx_ring(struct ice_ring *tx_ring) +void ice_clean_tx_ring(struct ice_tx_ring *tx_ring) { + u32 size; u16 i; if (ice_ring_is_xdp(tx_ring) && tx_ring->xsk_pool) { @@ -164,8 +165,10 @@ void ice_clean_tx_ring(struct ice_ring *tx_ring) tx_skip_free: memset(tx_ring->tx_buf, 0, sizeof(*tx_ring->tx_buf) * tx_ring->count); + size = ALIGN(tx_ring->count * sizeof(struct ice_tx_desc), + PAGE_SIZE); /* Zero out the descriptor ring */ - memset(tx_ring->desc, 0, tx_ring->size); + memset(tx_ring->desc, 0, size); tx_ring->next_to_use = 0; tx_ring->next_to_clean = 0; @@ -183,14 +186,18 @@ tx_skip_free: * * Free all transmit software resources */ -void ice_free_tx_ring(struct ice_ring *tx_ring) +void ice_free_tx_ring(struct ice_tx_ring *tx_ring) { + u32 size; + ice_clean_tx_ring(tx_ring); devm_kfree(tx_ring->dev, tx_ring->tx_buf); tx_ring->tx_buf = NULL; if (tx_ring->desc) { - dmam_free_coherent(tx_ring->dev, tx_ring->size, + size = ALIGN(tx_ring->count * sizeof(struct ice_tx_desc), + PAGE_SIZE); + dmam_free_coherent(tx_ring->dev, size, tx_ring->desc, tx_ring->dma); tx_ring->desc = NULL; } @@ -203,7 +210,7 @@ void ice_free_tx_ring(struct ice_ring *tx_ring) * * Returns true if there's any budget left (e.g. the clean is finished) */ -static bool ice_clean_tx_irq(struct ice_ring *tx_ring, int napi_budget) +static bool ice_clean_tx_irq(struct ice_tx_ring *tx_ring, int napi_budget) { unsigned int total_bytes = 0, total_pkts = 0; unsigned int budget = ICE_DFLT_IRQ_WORK; @@ -240,11 +247,8 @@ static bool ice_clean_tx_irq(struct ice_ring *tx_ring, int napi_budget) total_bytes += tx_buf->bytecount; total_pkts += tx_buf->gso_segs; - if (ice_ring_is_xdp(tx_ring)) - page_frag_free(tx_buf->raw_buf); - else - /* free the skb */ - napi_consume_skb(tx_buf->skb, napi_budget); + /* free the skb */ + napi_consume_skb(tx_buf->skb, napi_budget); /* unmap skb header data */ dma_unmap_single(tx_ring->dev, @@ -300,9 +304,6 @@ static bool ice_clean_tx_irq(struct ice_ring *tx_ring, int napi_budget) ice_update_tx_ring_stats(tx_ring, total_pkts, total_bytes); - if (ice_ring_is_xdp(tx_ring)) - return !!budget; - netdev_tx_completed_queue(txring_txq(tx_ring), total_pkts, total_bytes); @@ -331,9 +332,10 @@ static bool ice_clean_tx_irq(struct ice_ring *tx_ring, int napi_budget) * * Return 0 on success, negative on error */ -int ice_setup_tx_ring(struct ice_ring *tx_ring) +int ice_setup_tx_ring(struct ice_tx_ring *tx_ring) { struct device *dev = tx_ring->dev; + u32 size; if (!dev) return -ENOMEM; @@ -341,19 +343,19 @@ int ice_setup_tx_ring(struct ice_ring *tx_ring) /* warn if we are about to overwrite the pointer */ WARN_ON(tx_ring->tx_buf); tx_ring->tx_buf = - devm_kzalloc(dev, sizeof(*tx_ring->tx_buf) * tx_ring->count, + devm_kcalloc(dev, sizeof(*tx_ring->tx_buf), tx_ring->count, GFP_KERNEL); if (!tx_ring->tx_buf) return -ENOMEM; /* round up to nearest page */ - tx_ring->size = ALIGN(tx_ring->count * sizeof(struct ice_tx_desc), - PAGE_SIZE); - tx_ring->desc = dmam_alloc_coherent(dev, tx_ring->size, &tx_ring->dma, + size = ALIGN(tx_ring->count * sizeof(struct ice_tx_desc), + PAGE_SIZE); + tx_ring->desc = dmam_alloc_coherent(dev, size, &tx_ring->dma, GFP_KERNEL); if (!tx_ring->desc) { dev_err(dev, "Unable to allocate memory for the Tx descriptor ring, size=%d\n", - tx_ring->size); + size); goto err; } @@ -372,9 +374,10 @@ err: * ice_clean_rx_ring - Free Rx buffers * @rx_ring: ring to be cleaned */ -void ice_clean_rx_ring(struct ice_ring *rx_ring) +void ice_clean_rx_ring(struct ice_rx_ring *rx_ring) { struct device *dev = rx_ring->dev; + u32 size; u16 i; /* ring already cleared, nothing to do */ @@ -419,7 +422,9 @@ rx_skip_free: memset(rx_ring->rx_buf, 0, sizeof(*rx_ring->rx_buf) * rx_ring->count); /* Zero out the descriptor ring */ - memset(rx_ring->desc, 0, rx_ring->size); + size = ALIGN(rx_ring->count * sizeof(union ice_32byte_rx_desc), + PAGE_SIZE); + memset(rx_ring->desc, 0, size); rx_ring->next_to_alloc = 0; rx_ring->next_to_clean = 0; @@ -432,8 +437,10 @@ rx_skip_free: * * Free all receive software resources */ -void ice_free_rx_ring(struct ice_ring *rx_ring) +void ice_free_rx_ring(struct ice_rx_ring *rx_ring) { + u32 size; + ice_clean_rx_ring(rx_ring); if (rx_ring->vsi->type == ICE_VSI_PF) if (xdp_rxq_info_is_reg(&rx_ring->xdp_rxq)) @@ -443,7 +450,9 @@ void ice_free_rx_ring(struct ice_ring *rx_ring) rx_ring->rx_buf = NULL; if (rx_ring->desc) { - dmam_free_coherent(rx_ring->dev, rx_ring->size, + size = ALIGN(rx_ring->count * sizeof(union ice_32byte_rx_desc), + PAGE_SIZE); + dmam_free_coherent(rx_ring->dev, size, rx_ring->desc, rx_ring->dma); rx_ring->desc = NULL; } @@ -455,9 +464,10 @@ void ice_free_rx_ring(struct ice_ring *rx_ring) * * Return 0 on success, negative on error */ -int ice_setup_rx_ring(struct ice_ring *rx_ring) +int ice_setup_rx_ring(struct ice_rx_ring *rx_ring) { struct device *dev = rx_ring->dev; + u32 size; if (!dev) return -ENOMEM; @@ -465,19 +475,19 @@ int ice_setup_rx_ring(struct ice_ring *rx_ring) /* warn if we are about to overwrite the pointer */ WARN_ON(rx_ring->rx_buf); rx_ring->rx_buf = - devm_kzalloc(dev, sizeof(*rx_ring->rx_buf) * rx_ring->count, + devm_kcalloc(dev, sizeof(*rx_ring->rx_buf), rx_ring->count, GFP_KERNEL); if (!rx_ring->rx_buf) return -ENOMEM; /* round up to nearest page */ - rx_ring->size = ALIGN(rx_ring->count * sizeof(union ice_32byte_rx_desc), - PAGE_SIZE); - rx_ring->desc = dmam_alloc_coherent(dev, rx_ring->size, &rx_ring->dma, + size = ALIGN(rx_ring->count * sizeof(union ice_32byte_rx_desc), + PAGE_SIZE); + rx_ring->desc = dmam_alloc_coherent(dev, size, &rx_ring->dma, GFP_KERNEL); if (!rx_ring->desc) { dev_err(dev, "Unable to allocate memory for the Rx descriptor ring, size=%d\n", - rx_ring->size); + size); goto err; } @@ -501,7 +511,7 @@ err: } static unsigned int -ice_rx_frame_truesize(struct ice_ring *rx_ring, unsigned int __maybe_unused size) +ice_rx_frame_truesize(struct ice_rx_ring *rx_ring, unsigned int __maybe_unused size) { unsigned int truesize; @@ -521,15 +531,15 @@ ice_rx_frame_truesize(struct ice_ring *rx_ring, unsigned int __maybe_unused size * @rx_ring: Rx ring * @xdp: xdp_buff used as input to the XDP program * @xdp_prog: XDP program to run + * @xdp_ring: ring to be used for XDP_TX action * * Returns any of ICE_XDP_{PASS, CONSUMED, TX, REDIR} */ static int -ice_run_xdp(struct ice_ring *rx_ring, struct xdp_buff *xdp, - struct bpf_prog *xdp_prog) +ice_run_xdp(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp, + struct bpf_prog *xdp_prog, struct ice_tx_ring *xdp_ring) { - struct ice_ring *xdp_ring; - int err, result; + int err; u32 act; act = bpf_prog_run_xdp(xdp_prog, xdp); @@ -537,11 +547,14 @@ ice_run_xdp(struct ice_ring *rx_ring, struct xdp_buff *xdp, case XDP_PASS: return ICE_XDP_PASS; case XDP_TX: - xdp_ring = rx_ring->vsi->xdp_rings[smp_processor_id()]; - result = ice_xmit_xdp_buff(xdp, xdp_ring); - if (result == ICE_XDP_CONSUMED) + if (static_branch_unlikely(&ice_xdp_locking_key)) + spin_lock(&xdp_ring->tx_lock); + err = ice_xmit_xdp_ring(xdp->data, xdp->data_end - xdp->data, xdp_ring); + if (static_branch_unlikely(&ice_xdp_locking_key)) + spin_unlock(&xdp_ring->tx_lock); + if (err == ICE_XDP_CONSUMED) goto out_failure; - return result; + return err; case XDP_REDIRECT: err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog); if (err) @@ -578,7 +591,7 @@ ice_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, struct ice_netdev_priv *np = netdev_priv(dev); unsigned int queue_index = smp_processor_id(); struct ice_vsi *vsi = np->vsi; - struct ice_ring *xdp_ring; + struct ice_tx_ring *xdp_ring; int nxmit = 0, i; if (test_bit(ICE_VSI_DOWN, vsi->state)) @@ -590,7 +603,14 @@ ice_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) return -EINVAL; - xdp_ring = vsi->xdp_rings[queue_index]; + if (static_branch_unlikely(&ice_xdp_locking_key)) { + queue_index %= vsi->num_xdp_txq; + xdp_ring = vsi->xdp_rings[queue_index]; + spin_lock(&xdp_ring->tx_lock); + } else { + xdp_ring = vsi->xdp_rings[queue_index]; + } + for (i = 0; i < n; i++) { struct xdp_frame *xdpf = frames[i]; int err; @@ -604,6 +624,9 @@ ice_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, if (unlikely(flags & XDP_XMIT_FLUSH)) ice_xdp_ring_update_tail(xdp_ring); + if (static_branch_unlikely(&ice_xdp_locking_key)) + spin_unlock(&xdp_ring->tx_lock); + return nxmit; } @@ -616,7 +639,7 @@ ice_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, * reused. */ static bool -ice_alloc_mapped_page(struct ice_ring *rx_ring, struct ice_rx_buf *bi) +ice_alloc_mapped_page(struct ice_rx_ring *rx_ring, struct ice_rx_buf *bi) { struct page *page = bi->page; dma_addr_t dma; @@ -667,7 +690,7 @@ ice_alloc_mapped_page(struct ice_ring *rx_ring, struct ice_rx_buf *bi) * buffers. Then bump tail at most one time. Grouping like this lets us avoid * multiple tail writes per call. */ -bool ice_alloc_rx_bufs(struct ice_ring *rx_ring, u16 cleaned_count) +bool ice_alloc_rx_bufs(struct ice_rx_ring *rx_ring, u16 cleaned_count) { union ice_32b_rx_flex_desc *rx_desc; u16 ntu = rx_ring->next_to_use; @@ -796,7 +819,7 @@ ice_can_reuse_rx_page(struct ice_rx_buf *rx_buf, int rx_buf_pgcnt) * The function will then update the page offset. */ static void -ice_add_rx_frag(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf, +ice_add_rx_frag(struct ice_rx_ring *rx_ring, struct ice_rx_buf *rx_buf, struct sk_buff *skb, unsigned int size) { #if (PAGE_SIZE >= 8192) @@ -822,7 +845,7 @@ ice_add_rx_frag(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf, * Synchronizes page for reuse by the adapter */ static void -ice_reuse_rx_page(struct ice_ring *rx_ring, struct ice_rx_buf *old_buf) +ice_reuse_rx_page(struct ice_rx_ring *rx_ring, struct ice_rx_buf *old_buf) { u16 nta = rx_ring->next_to_alloc; struct ice_rx_buf *new_buf; @@ -853,7 +876,7 @@ ice_reuse_rx_page(struct ice_ring *rx_ring, struct ice_rx_buf *old_buf) * for use by the CPU. */ static struct ice_rx_buf * -ice_get_rx_buf(struct ice_ring *rx_ring, const unsigned int size, +ice_get_rx_buf(struct ice_rx_ring *rx_ring, const unsigned int size, int *rx_buf_pgcnt) { struct ice_rx_buf *rx_buf; @@ -890,7 +913,7 @@ ice_get_rx_buf(struct ice_ring *rx_ring, const unsigned int size, * to set up the skb correctly and avoid any memcpy overhead. */ static struct sk_buff * -ice_build_skb(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf, +ice_build_skb(struct ice_rx_ring *rx_ring, struct ice_rx_buf *rx_buf, struct xdp_buff *xdp) { u8 metasize = xdp->data - xdp->data_meta; @@ -942,7 +965,7 @@ ice_build_skb(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf, * skb correctly. */ static struct sk_buff * -ice_construct_skb(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf, +ice_construct_skb(struct ice_rx_ring *rx_ring, struct ice_rx_buf *rx_buf, struct xdp_buff *xdp) { unsigned int size = xdp->data_end - xdp->data; @@ -1002,7 +1025,7 @@ ice_construct_skb(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf, * the associated resources. */ static void -ice_put_rx_buf(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf, +ice_put_rx_buf(struct ice_rx_ring *rx_ring, struct ice_rx_buf *rx_buf, int rx_buf_pgcnt) { u16 ntc = rx_ring->next_to_clean + 1; @@ -1038,7 +1061,7 @@ ice_put_rx_buf(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf, * otherwise return true indicating that this is in fact a non-EOP buffer. */ static bool -ice_is_non_eop(struct ice_ring *rx_ring, union ice_32b_rx_flex_desc *rx_desc) +ice_is_non_eop(struct ice_rx_ring *rx_ring, union ice_32b_rx_flex_desc *rx_desc) { /* if we are the last buffer then there is nothing else to do */ #define ICE_RXD_EOF BIT(ICE_RX_FLEX_DESC_STATUS0_EOF_S) @@ -1062,11 +1085,12 @@ ice_is_non_eop(struct ice_ring *rx_ring, union ice_32b_rx_flex_desc *rx_desc) * * Returns amount of work completed */ -int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget) +int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget) { unsigned int total_rx_bytes = 0, total_rx_pkts = 0, frame_sz = 0; u16 cleaned_count = ICE_DESC_UNUSED(rx_ring); unsigned int offset = rx_ring->rx_offset; + struct ice_tx_ring *xdp_ring = NULL; unsigned int xdp_res, xdp_xmit = 0; struct sk_buff *skb = rx_ring->skb; struct bpf_prog *xdp_prog = NULL; @@ -1079,6 +1103,10 @@ int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget) #endif xdp_init_buff(&xdp, frame_sz, &rx_ring->xdp_rxq); + xdp_prog = READ_ONCE(rx_ring->xdp_prog); + if (xdp_prog) + xdp_ring = rx_ring->xdp_ring; + /* start the loop to process Rx packets bounded by 'budget' */ while (likely(total_rx_pkts < (unsigned int)budget)) { union ice_32b_rx_flex_desc *rx_desc; @@ -1142,11 +1170,10 @@ int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget) xdp.frame_sz = ice_rx_frame_truesize(rx_ring, size); #endif - xdp_prog = READ_ONCE(rx_ring->xdp_prog); if (!xdp_prog) goto construct_skb; - xdp_res = ice_run_xdp(rx_ring, &xdp, xdp_prog); + xdp_res = ice_run_xdp(rx_ring, &xdp, xdp_prog, xdp_ring); if (!xdp_res) goto construct_skb; if (xdp_res & (ICE_XDP_TX | ICE_XDP_REDIR)) { @@ -1223,7 +1250,7 @@ construct_skb: failure = ice_alloc_rx_bufs(rx_ring, cleaned_count); if (xdp_prog) - ice_finalize_xdp_rx(rx_ring, xdp_xmit); + ice_finalize_xdp_rx(xdp_ring, xdp_xmit); rx_ring->skb = skb; ice_update_rx_ring_stats(rx_ring, total_rx_pkts, total_rx_bytes); @@ -1232,6 +1259,41 @@ construct_skb: return failure ? budget : (int)total_rx_pkts; } +static void __ice_update_sample(struct ice_q_vector *q_vector, + struct ice_ring_container *rc, + struct dim_sample *sample, + bool is_tx) +{ + u64 packets = 0, bytes = 0; + + if (is_tx) { + struct ice_tx_ring *tx_ring; + + ice_for_each_tx_ring(tx_ring, *rc) { + packets += tx_ring->stats.pkts; + bytes += tx_ring->stats.bytes; + } + } else { + struct ice_rx_ring *rx_ring; + + ice_for_each_rx_ring(rx_ring, *rc) { + packets += rx_ring->stats.pkts; + bytes += rx_ring->stats.bytes; + } + } + + dim_update_sample(q_vector->total_events, packets, bytes, sample); + sample->comp_ctr = 0; + + /* if dim settings get stale, like when not updated for 1 + * second or longer, force it to start again. This addresses the + * frequent case of an idle queue being switched to by the + * scheduler. The 1,000 here means 1,000 milliseconds. + */ + if (ktime_ms_delta(sample->time, rc->dim.start_sample.time) >= 1000) + rc->dim.state = DIM_START_MEASURE; +} + /** * ice_net_dim - Update net DIM algorithm * @q_vector: the vector associated with the interrupt @@ -1247,34 +1309,16 @@ static void ice_net_dim(struct ice_q_vector *q_vector) struct ice_ring_container *rx = &q_vector->rx; if (ITR_IS_DYNAMIC(tx)) { - struct dim_sample dim_sample = {}; - u64 packets = 0, bytes = 0; - struct ice_ring *ring; - - ice_for_each_ring(ring, q_vector->tx) { - packets += ring->stats.pkts; - bytes += ring->stats.bytes; - } - - dim_update_sample(q_vector->total_events, packets, bytes, - &dim_sample); + struct dim_sample dim_sample; + __ice_update_sample(q_vector, tx, &dim_sample, true); net_dim(&tx->dim, dim_sample); } if (ITR_IS_DYNAMIC(rx)) { - struct dim_sample dim_sample = {}; - u64 packets = 0, bytes = 0; - struct ice_ring *ring; - - ice_for_each_ring(ring, q_vector->rx) { - packets += ring->stats.pkts; - bytes += ring->stats.bytes; - } - - dim_update_sample(q_vector->total_events, packets, bytes, - &dim_sample); + struct dim_sample dim_sample; + __ice_update_sample(q_vector, rx, &dim_sample, false); net_dim(&rx->dim, dim_sample); } } @@ -1301,15 +1345,14 @@ static u32 ice_buildreg_itr(u16 itr_idx, u16 itr) } /** - * ice_update_ena_itr - Update ITR moderation and re-enable MSI-X interrupt + * ice_enable_interrupt - re-enable MSI-X interrupt * @q_vector: the vector associated with the interrupt to enable * - * Update the net_dim() algorithm and re-enable the interrupt associated with - * this vector. - * - * If the VSI is down, the interrupt will not be re-enabled. + * If the VSI is down, the interrupt will not be re-enabled. Also, + * when enabling the interrupt always reset the wb_on_itr to false + * and trigger a software interrupt to clean out internal state. */ -static void ice_update_ena_itr(struct ice_q_vector *q_vector) +static void ice_enable_interrupt(struct ice_q_vector *q_vector) { struct ice_vsi *vsi = q_vector->vsi; bool wb_en = q_vector->wb_on_itr; @@ -1318,25 +1361,25 @@ static void ice_update_ena_itr(struct ice_q_vector *q_vector) if (test_bit(ICE_DOWN, vsi->state)) return; - /* When exiting WB_ON_ITR, let ITR resume its normal - * interrupts-enabled path. + /* trigger an ITR delayed software interrupt when exiting busy poll, to + * make sure to catch any pending cleanups that might have been missed + * due to interrupt state transition. If busy poll or poll isn't + * enabled, then don't update ITR, and just enable the interrupt. */ - if (wb_en) + if (!wb_en) { + itr_val = ice_buildreg_itr(ICE_ITR_NONE, 0); + } else { q_vector->wb_on_itr = false; - /* This will do nothing if dynamic updates are not enabled. */ - ice_net_dim(q_vector); - - /* net_dim() updates ITR out-of-band using a work item */ - itr_val = ice_buildreg_itr(ICE_ITR_NONE, 0); - /* trigger an immediate software interrupt when exiting - * busy poll, to make sure to catch any pending cleanups - * that might have been missed due to interrupt state - * transition. - */ - if (wb_en) { + /* do two things here with a single write. Set up the third ITR + * index to be used for software interrupt moderation, and then + * trigger a software interrupt with a rate limit of 20K on + * software interrupts, this will help avoid high interrupt + * loads due to frequently polling and exiting polling. + */ + itr_val = ice_buildreg_itr(ICE_IDX_ITR2, ICE_ITR_20K); itr_val |= GLINT_DYN_CTL_SWINT_TRIG_M | - GLINT_DYN_CTL_SW_ITR_INDX_M | + ICE_IDX_ITR2 << GLINT_DYN_CTL_SW_ITR_INDX_S | GLINT_DYN_CTL_SW_ITR_INDX_ENA_M; } wr32(&vsi->back->hw, GLINT_DYN_CTL(q_vector->reg_idx), itr_val); @@ -1389,18 +1432,24 @@ int ice_napi_poll(struct napi_struct *napi, int budget) { struct ice_q_vector *q_vector = container_of(napi, struct ice_q_vector, napi); + struct ice_tx_ring *tx_ring; + struct ice_rx_ring *rx_ring; bool clean_complete = true; - struct ice_ring *ring; int budget_per_ring; int work_done = 0; /* Since the actual Tx work is minimal, we can give the Tx a larger * budget and be more aggressive about cleaning up the Tx descriptors. */ - ice_for_each_ring(ring, q_vector->tx) { - bool wd = ring->xsk_pool ? - ice_clean_tx_irq_zc(ring, budget) : - ice_clean_tx_irq(ring, budget); + ice_for_each_tx_ring(tx_ring, q_vector->tx) { + bool wd; + + if (tx_ring->xsk_pool) + wd = ice_clean_tx_irq_zc(tx_ring, budget); + else if (ice_ring_is_xdp(tx_ring)) + wd = true; + else + wd = ice_clean_tx_irq(tx_ring, budget); if (!wd) clean_complete = false; @@ -1421,16 +1470,16 @@ int ice_napi_poll(struct napi_struct *napi, int budget) /* Max of 1 Rx ring in this q_vector so give it the budget */ budget_per_ring = budget; - ice_for_each_ring(ring, q_vector->rx) { + ice_for_each_rx_ring(rx_ring, q_vector->rx) { int cleaned; /* A dedicated path for zero-copy allows making a single * comparison in the irq context instead of many inside the * ice_clean_rx_irq function and makes the codebase cleaner. */ - cleaned = ring->xsk_pool ? - ice_clean_rx_irq_zc(ring, budget_per_ring) : - ice_clean_rx_irq(ring, budget_per_ring); + cleaned = rx_ring->xsk_pool ? + ice_clean_rx_irq_zc(rx_ring, budget_per_ring) : + ice_clean_rx_irq(rx_ring, budget_per_ring); work_done += cleaned; /* if we clean as many as budgeted, we must not be done */ if (cleaned >= budget_per_ring) @@ -1449,10 +1498,12 @@ int ice_napi_poll(struct napi_struct *napi, int budget) /* Exit the polling mode, but don't re-enable interrupts if stack might * poll us due to busy-polling */ - if (likely(napi_complete_done(napi, work_done))) - ice_update_ena_itr(q_vector); - else + if (likely(napi_complete_done(napi, work_done))) { + ice_net_dim(q_vector); + ice_enable_interrupt(q_vector); + } else { ice_set_wb_on_itr(q_vector); + } return min_t(int, work_done, budget - 1); } @@ -1464,7 +1515,7 @@ int ice_napi_poll(struct napi_struct *napi, int budget) * * Returns -EBUSY if a stop is needed, else 0 */ -static int __ice_maybe_stop_tx(struct ice_ring *tx_ring, unsigned int size) +static int __ice_maybe_stop_tx(struct ice_tx_ring *tx_ring, unsigned int size) { netif_stop_subqueue(tx_ring->netdev, tx_ring->q_index); /* Memory barrier before checking head and tail */ @@ -1487,7 +1538,7 @@ static int __ice_maybe_stop_tx(struct ice_ring *tx_ring, unsigned int size) * * Returns 0 if stop is not needed */ -static int ice_maybe_stop_tx(struct ice_ring *tx_ring, unsigned int size) +static int ice_maybe_stop_tx(struct ice_tx_ring *tx_ring, unsigned int size) { if (likely(ICE_DESC_UNUSED(tx_ring) >= size)) return 0; @@ -1506,7 +1557,7 @@ static int ice_maybe_stop_tx(struct ice_ring *tx_ring, unsigned int size) * it and the length into the transmit descriptor. */ static void -ice_tx_map(struct ice_ring *tx_ring, struct ice_tx_buf *first, +ice_tx_map(struct ice_tx_ring *tx_ring, struct ice_tx_buf *first, struct ice_tx_offload_params *off) { u64 td_offset, td_tag, td_cmd; @@ -1842,7 +1893,7 @@ int ice_tx_csum(struct ice_tx_buf *first, struct ice_tx_offload_params *off) * related to VLAN tagging for the HW, such as VLAN, DCB, etc. */ static void -ice_tx_prepare_vlan_flags(struct ice_ring *tx_ring, struct ice_tx_buf *first) +ice_tx_prepare_vlan_flags(struct ice_tx_ring *tx_ring, struct ice_tx_buf *first) { struct sk_buff *skb = first->skb; @@ -2148,7 +2199,7 @@ static bool ice_chk_linearize(struct sk_buff *skb, unsigned int count) * @off: Tx offload parameters */ static void -ice_tstamp(struct ice_ring *tx_ring, struct sk_buff *skb, +ice_tstamp(struct ice_tx_ring *tx_ring, struct sk_buff *skb, struct ice_tx_buf *first, struct ice_tx_offload_params *off) { s8 idx; @@ -2183,7 +2234,7 @@ ice_tstamp(struct ice_ring *tx_ring, struct sk_buff *skb, * Returns NETDEV_TX_OK if sent, else an error code */ static netdev_tx_t -ice_xmit_frame_ring(struct sk_buff *skb, struct ice_ring *tx_ring) +ice_xmit_frame_ring(struct sk_buff *skb, struct ice_tx_ring *tx_ring) { struct ice_tx_offload_params offload = { 0 }; struct ice_vsi *vsi = tx_ring->vsi; @@ -2286,7 +2337,7 @@ netdev_tx_t ice_start_xmit(struct sk_buff *skb, struct net_device *netdev) { struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_vsi *vsi = np->vsi; - struct ice_ring *tx_ring; + struct ice_tx_ring *tx_ring; tx_ring = vsi->tx_rings[skb->queue_mapping]; @@ -2336,7 +2387,7 @@ ice_select_queue(struct net_device *netdev, struct sk_buff *skb, * ice_clean_ctrl_tx_irq - interrupt handler for flow director Tx queue * @tx_ring: tx_ring to clean */ -void ice_clean_ctrl_tx_irq(struct ice_ring *tx_ring) +void ice_clean_ctrl_tx_irq(struct ice_tx_ring *tx_ring) { struct ice_vsi *vsi = tx_ring->vsi; s16 i = tx_ring->next_to_clean; diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h index cce348c83da8..c56dd1749903 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.h +++ b/drivers/net/ethernet/intel/ice/ice_txrx.h @@ -13,6 +13,7 @@ #define ICE_MAX_CHAINED_RX_BUFS 5 #define ICE_MAX_BUF_TXD 8 #define ICE_MIN_TX_LEN 17 +#define ICE_TX_THRESH 32 /* The size limit for a transmit buffer in a descriptor is (16K - 1). * In order to align with the read requests we will align the value to @@ -154,7 +155,7 @@ struct ice_tx_buf { struct ice_tx_offload_params { u64 cd_qw1; - struct ice_ring *tx_ring; + struct ice_tx_ring *tx_ring; u32 td_cmd; u32 td_offset; u32 td_l2tag1; @@ -251,9 +252,9 @@ enum ice_dynamic_itr { #define ICE_TX_LEGACY 1 /* descriptor ring, associated with a VSI */ -struct ice_ring { +struct ice_rx_ring { /* CL1 - 1st cacheline starts here */ - struct ice_ring *next; /* pointer to next ring in q_vector */ + struct ice_rx_ring *next; /* pointer to next ring in q_vector */ void *desc; /* Descriptor ring memory */ struct device *dev; /* Used for DMA mapping */ struct net_device *netdev; /* netdev ring maps to */ @@ -261,15 +262,13 @@ struct ice_ring { struct ice_q_vector *q_vector; /* Backreference to associated vector */ u8 __iomem *tail; union { - struct ice_tx_buf *tx_buf; struct ice_rx_buf *rx_buf; struct xdp_buff **xdp_buf; }; /* CL2 - 2nd cacheline starts here */ + struct xdp_rxq_info xdp_rxq; + /* CL3 - 3rd cacheline starts here */ u16 q_index; /* Queue number of ring */ - u16 q_handle; /* Queue handle per TC */ - - u8 ring_active:1; /* is ring online or not */ u16 count; /* Number of descriptors */ u16 reg_idx; /* HW register index of the ring */ @@ -278,63 +277,104 @@ struct ice_ring { u16 next_to_use; u16 next_to_clean; u16 next_to_alloc; + u16 rx_offset; + u16 rx_buf_len; + /* stats structs */ + struct ice_rxq_stats rx_stats; + struct ice_q_stats stats; + struct u64_stats_sync syncp; + + struct rcu_head rcu; /* to avoid race on free */ + /* CL4 - 3rd cacheline starts here */ + struct ice_channel *ch; + struct bpf_prog *xdp_prog; + struct ice_tx_ring *xdp_ring; + struct xsk_buff_pool *xsk_pool; + struct sk_buff *skb; + dma_addr_t dma; /* physical address of ring */ +#define ICE_RX_FLAGS_RING_BUILD_SKB BIT(1) + u64 cached_phctime; + u8 dcb_tc; /* Traffic class of ring */ + u8 ptp_rx; + u8 flags; +} ____cacheline_internodealigned_in_smp; + +struct ice_tx_ring { + /* CL1 - 1st cacheline starts here */ + struct ice_tx_ring *next; /* pointer to next ring in q_vector */ + void *desc; /* Descriptor ring memory */ + struct device *dev; /* Used for DMA mapping */ + u8 __iomem *tail; + struct ice_tx_buf *tx_buf; + struct ice_q_vector *q_vector; /* Backreference to associated vector */ + struct net_device *netdev; /* netdev ring maps to */ + struct ice_vsi *vsi; /* Backreference to associated VSI */ + /* CL2 - 2nd cacheline starts here */ + dma_addr_t dma; /* physical address of ring */ + struct xsk_buff_pool *xsk_pool; + u16 next_to_use; + u16 next_to_clean; + u16 next_rs; + u16 next_dd; + u16 q_handle; /* Queue handle per TC */ + u16 reg_idx; /* HW register index of the ring */ + u16 count; /* Number of descriptors */ + u16 q_index; /* Queue number of ring */ /* stats structs */ struct ice_q_stats stats; struct u64_stats_sync syncp; - union { - struct ice_txq_stats tx_stats; - struct ice_rxq_stats rx_stats; - }; + struct ice_txq_stats tx_stats; + /* CL3 - 3rd cacheline starts here */ struct rcu_head rcu; /* to avoid race on free */ DECLARE_BITMAP(xps_state, ICE_TX_NBITS); /* XPS Config State */ - struct bpf_prog *xdp_prog; - struct xsk_buff_pool *xsk_pool; - u16 rx_offset; - /* CL3 - 3rd cacheline starts here */ - struct xdp_rxq_info xdp_rxq; - struct sk_buff *skb; - /* CLX - the below items are only accessed infrequently and should be - * in their own cache line if possible - */ -#define ICE_TX_FLAGS_RING_XDP BIT(0) -#define ICE_RX_FLAGS_RING_BUILD_SKB BIT(1) - u8 flags; - dma_addr_t dma; /* physical address of ring */ - unsigned int size; /* length of descriptor ring in bytes */ - u32 txq_teid; /* Added Tx queue TEID */ - u16 rx_buf_len; - u8 dcb_tc; /* Traffic class of ring */ + struct ice_channel *ch; struct ice_ptp_tx *tx_tstamps; - u64 cached_phctime; - u8 ptp_rx:1; - u8 ptp_tx:1; + spinlock_t tx_lock; + u32 txq_teid; /* Added Tx queue TEID */ +#define ICE_TX_FLAGS_RING_XDP BIT(0) + u8 flags; + u8 dcb_tc; /* Traffic class of ring */ + u8 ptp_tx; } ____cacheline_internodealigned_in_smp; -static inline bool ice_ring_uses_build_skb(struct ice_ring *ring) +static inline bool ice_ring_uses_build_skb(struct ice_rx_ring *ring) { return !!(ring->flags & ICE_RX_FLAGS_RING_BUILD_SKB); } -static inline void ice_set_ring_build_skb_ena(struct ice_ring *ring) +static inline void ice_set_ring_build_skb_ena(struct ice_rx_ring *ring) { ring->flags |= ICE_RX_FLAGS_RING_BUILD_SKB; } -static inline void ice_clear_ring_build_skb_ena(struct ice_ring *ring) +static inline void ice_clear_ring_build_skb_ena(struct ice_rx_ring *ring) { ring->flags &= ~ICE_RX_FLAGS_RING_BUILD_SKB; } -static inline bool ice_ring_is_xdp(struct ice_ring *ring) +static inline bool ice_ring_ch_enabled(struct ice_tx_ring *ring) +{ + return !!ring->ch; +} + +static inline bool ice_ring_is_xdp(struct ice_tx_ring *ring) { return !!(ring->flags & ICE_TX_FLAGS_RING_XDP); } +enum ice_container_type { + ICE_RX_CONTAINER, + ICE_TX_CONTAINER, +}; + struct ice_ring_container { /* head of linked-list of rings */ - struct ice_ring *ring; + union { + struct ice_rx_ring *rx_ring; + struct ice_tx_ring *tx_ring; + }; struct dim dim; /* data for net_dim algorithm */ u16 itr_idx; /* index in the interrupt vector */ /* this matches the maximum number of ITR bits, but in usec @@ -343,6 +383,7 @@ struct ice_ring_container { u16 itr_setting:13; u16 itr_reserved:2; u16 itr_mode:1; + enum ice_container_type type; }; struct ice_coalesce_stored { @@ -354,10 +395,13 @@ struct ice_coalesce_stored { }; /* iterator for handling rings in ring container */ -#define ice_for_each_ring(pos, head) \ - for (pos = (head).ring; pos; pos = pos->next) +#define ice_for_each_rx_ring(pos, head) \ + for (pos = (head).rx_ring; pos; pos = pos->next) -static inline unsigned int ice_rx_pg_order(struct ice_ring *ring) +#define ice_for_each_tx_ring(pos, head) \ + for (pos = (head).tx_ring; pos; pos = pos->next) + +static inline unsigned int ice_rx_pg_order(struct ice_rx_ring *ring) { #if (PAGE_SIZE < 8192) if (ring->rx_buf_len > (PAGE_SIZE / 2)) @@ -370,21 +414,21 @@ static inline unsigned int ice_rx_pg_order(struct ice_ring *ring) union ice_32b_rx_flex_desc; -bool ice_alloc_rx_bufs(struct ice_ring *rxr, u16 cleaned_count); +bool ice_alloc_rx_bufs(struct ice_rx_ring *rxr, u16 cleaned_count); netdev_tx_t ice_start_xmit(struct sk_buff *skb, struct net_device *netdev); u16 ice_select_queue(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev); -void ice_clean_tx_ring(struct ice_ring *tx_ring); -void ice_clean_rx_ring(struct ice_ring *rx_ring); -int ice_setup_tx_ring(struct ice_ring *tx_ring); -int ice_setup_rx_ring(struct ice_ring *rx_ring); -void ice_free_tx_ring(struct ice_ring *tx_ring); -void ice_free_rx_ring(struct ice_ring *rx_ring); +void ice_clean_tx_ring(struct ice_tx_ring *tx_ring); +void ice_clean_rx_ring(struct ice_rx_ring *rx_ring); +int ice_setup_tx_ring(struct ice_tx_ring *tx_ring); +int ice_setup_rx_ring(struct ice_rx_ring *rx_ring); +void ice_free_tx_ring(struct ice_tx_ring *tx_ring); +void ice_free_rx_ring(struct ice_rx_ring *rx_ring); int ice_napi_poll(struct napi_struct *napi, int budget); int ice_prgm_fdir_fltr(struct ice_vsi *vsi, struct ice_fltr_desc *fdir_desc, u8 *raw_packet); -int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget); -void ice_clean_ctrl_tx_irq(struct ice_ring *tx_ring); +int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget); +void ice_clean_ctrl_tx_irq(struct ice_tx_ring *tx_ring); #endif /* _ICE_TXRX_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c index e314a1aee0ff..1dd7e84f41f8 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c @@ -3,13 +3,14 @@ #include "ice_txrx_lib.h" #include "ice_eswitch.h" +#include "ice_lib.h" /** * ice_release_rx_desc - Store the new tail and head values * @rx_ring: ring to bump * @val: new head index */ -void ice_release_rx_desc(struct ice_ring *rx_ring, u16 val) +void ice_release_rx_desc(struct ice_rx_ring *rx_ring, u16 val) { u16 prev_ntu = rx_ring->next_to_use & ~0x7; @@ -67,7 +68,7 @@ static enum pkt_hash_types ice_ptype_to_htype(u16 ptype) * @rx_ptype: the ptype value from the descriptor */ static void -ice_rx_hash(struct ice_ring *rx_ring, union ice_32b_rx_flex_desc *rx_desc, +ice_rx_hash(struct ice_rx_ring *rx_ring, union ice_32b_rx_flex_desc *rx_desc, struct sk_buff *skb, u16 rx_ptype) { struct ice_32b_rx_flex_desc_nic *nic_mdid; @@ -94,7 +95,7 @@ ice_rx_hash(struct ice_ring *rx_ring, union ice_32b_rx_flex_desc *rx_desc, * skb->protocol must be set before this function is called */ static void -ice_rx_csum(struct ice_ring *ring, struct sk_buff *skb, +ice_rx_csum(struct ice_rx_ring *ring, struct sk_buff *skb, union ice_32b_rx_flex_desc *rx_desc, u16 ptype) { struct ice_rx_ptype_decoded decoded; @@ -179,7 +180,7 @@ checksum_fail: * other fields within the skb. */ void -ice_process_skb_fields(struct ice_ring *rx_ring, +ice_process_skb_fields(struct ice_rx_ring *rx_ring, union ice_32b_rx_flex_desc *rx_desc, struct sk_buff *skb, u16 ptype) { @@ -205,7 +206,7 @@ ice_process_skb_fields(struct ice_ring *rx_ring, * gro receive functions (with/without VLAN tag) */ void -ice_receive_skb(struct ice_ring *rx_ring, struct sk_buff *skb, u16 vlan_tag) +ice_receive_skb(struct ice_rx_ring *rx_ring, struct sk_buff *skb, u16 vlan_tag) { if ((rx_ring->netdev->features & NETIF_F_HW_VLAN_CTAG_RX) && (vlan_tag & VLAN_VID_MASK)) @@ -213,19 +214,68 @@ ice_receive_skb(struct ice_ring *rx_ring, struct sk_buff *skb, u16 vlan_tag) napi_gro_receive(&rx_ring->q_vector->napi, skb); } +/** + * ice_clean_xdp_irq - Reclaim resources after transmit completes on XDP ring + * @xdp_ring: XDP ring to clean + */ +static void ice_clean_xdp_irq(struct ice_tx_ring *xdp_ring) +{ + unsigned int total_bytes = 0, total_pkts = 0; + u16 ntc = xdp_ring->next_to_clean; + struct ice_tx_desc *next_dd_desc; + u16 next_dd = xdp_ring->next_dd; + struct ice_tx_buf *tx_buf; + int i; + + next_dd_desc = ICE_TX_DESC(xdp_ring, next_dd); + if (!(next_dd_desc->cmd_type_offset_bsz & + cpu_to_le64(ICE_TX_DESC_DTYPE_DESC_DONE))) + return; + + for (i = 0; i < ICE_TX_THRESH; i++) { + tx_buf = &xdp_ring->tx_buf[ntc]; + + total_bytes += tx_buf->bytecount; + /* normally tx_buf->gso_segs was taken but at this point + * it's always 1 for us + */ + total_pkts++; + + page_frag_free(tx_buf->raw_buf); + dma_unmap_single(xdp_ring->dev, dma_unmap_addr(tx_buf, dma), + dma_unmap_len(tx_buf, len), DMA_TO_DEVICE); + dma_unmap_len_set(tx_buf, len, 0); + tx_buf->raw_buf = NULL; + + ntc++; + if (ntc >= xdp_ring->count) + ntc = 0; + } + + next_dd_desc->cmd_type_offset_bsz = 0; + xdp_ring->next_dd = xdp_ring->next_dd + ICE_TX_THRESH; + if (xdp_ring->next_dd > xdp_ring->count) + xdp_ring->next_dd = ICE_TX_THRESH - 1; + xdp_ring->next_to_clean = ntc; + ice_update_tx_ring_stats(xdp_ring, total_pkts, total_bytes); +} + /** * ice_xmit_xdp_ring - submit single packet to XDP ring for transmission * @data: packet data pointer * @size: packet data size * @xdp_ring: XDP ring for transmission */ -int ice_xmit_xdp_ring(void *data, u16 size, struct ice_ring *xdp_ring) +int ice_xmit_xdp_ring(void *data, u16 size, struct ice_tx_ring *xdp_ring) { u16 i = xdp_ring->next_to_use; struct ice_tx_desc *tx_desc; struct ice_tx_buf *tx_buf; dma_addr_t dma; + if (ICE_DESC_UNUSED(xdp_ring) < ICE_TX_THRESH) + ice_clean_xdp_irq(xdp_ring); + if (!unlikely(ICE_DESC_UNUSED(xdp_ring))) { xdp_ring->tx_stats.tx_busy++; return ICE_XDP_CONSUMED; @@ -246,21 +296,26 @@ int ice_xmit_xdp_ring(void *data, u16 size, struct ice_ring *xdp_ring) tx_desc = ICE_TX_DESC(xdp_ring, i); tx_desc->buf_addr = cpu_to_le64(dma); - tx_desc->cmd_type_offset_bsz = ice_build_ctob(ICE_TXD_LAST_DESC_CMD, 0, + tx_desc->cmd_type_offset_bsz = ice_build_ctob(ICE_TX_DESC_CMD_EOP, 0, size, 0); - /* Make certain all of the status bits have been updated - * before next_to_watch is written. - */ - smp_wmb(); - i++; - if (i == xdp_ring->count) + if (i == xdp_ring->count) { i = 0; - - tx_buf->next_to_watch = tx_desc; + tx_desc = ICE_TX_DESC(xdp_ring, xdp_ring->next_rs); + tx_desc->cmd_type_offset_bsz |= + cpu_to_le64(ICE_TX_DESC_CMD_RS << ICE_TXD_QW1_CMD_S); + xdp_ring->next_rs = ICE_TX_THRESH - 1; + } xdp_ring->next_to_use = i; + if (i > xdp_ring->next_rs) { + tx_desc = ICE_TX_DESC(xdp_ring, xdp_ring->next_rs); + tx_desc->cmd_type_offset_bsz |= + cpu_to_le64(ICE_TX_DESC_CMD_RS << ICE_TXD_QW1_CMD_S); + xdp_ring->next_rs += ICE_TX_THRESH; + } + return ICE_XDP_TX; } @@ -271,7 +326,7 @@ int ice_xmit_xdp_ring(void *data, u16 size, struct ice_ring *xdp_ring) * * Returns negative on failure, 0 on success. */ -int ice_xmit_xdp_buff(struct xdp_buff *xdp, struct ice_ring *xdp_ring) +int ice_xmit_xdp_buff(struct xdp_buff *xdp, struct ice_tx_ring *xdp_ring) { struct xdp_frame *xdpf = xdp_convert_buff_to_frame(xdp); @@ -283,22 +338,23 @@ int ice_xmit_xdp_buff(struct xdp_buff *xdp, struct ice_ring *xdp_ring) /** * ice_finalize_xdp_rx - Bump XDP Tx tail and/or flush redirect map - * @rx_ring: Rx ring + * @xdp_ring: XDP ring * @xdp_res: Result of the receive batch * * This function bumps XDP Tx tail and/or flush redirect map, and * should be called when a batch of packets has been processed in the * napi loop. */ -void ice_finalize_xdp_rx(struct ice_ring *rx_ring, unsigned int xdp_res) +void ice_finalize_xdp_rx(struct ice_tx_ring *xdp_ring, unsigned int xdp_res) { if (xdp_res & ICE_XDP_REDIR) xdp_do_flush_map(); if (xdp_res & ICE_XDP_TX) { - struct ice_ring *xdp_ring = - rx_ring->vsi->xdp_rings[rx_ring->q_index]; - + if (static_branch_unlikely(&ice_xdp_locking_key)) + spin_lock(&xdp_ring->tx_lock); ice_xdp_ring_update_tail(xdp_ring); + if (static_branch_unlikely(&ice_xdp_locking_key)) + spin_unlock(&xdp_ring->tx_lock); } } diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h index 05ac30752902..11b6c1601986 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h @@ -37,7 +37,7 @@ ice_build_ctob(u64 td_cmd, u64 td_offset, unsigned int size, u64 td_tag) * * This function updates the XDP Tx ring tail register. */ -static inline void ice_xdp_ring_update_tail(struct ice_ring *xdp_ring) +static inline void ice_xdp_ring_update_tail(struct ice_tx_ring *xdp_ring) { /* Force memory writes to complete before letting h/w * know there are new descriptors to fetch. @@ -46,14 +46,14 @@ static inline void ice_xdp_ring_update_tail(struct ice_ring *xdp_ring) writel_relaxed(xdp_ring->next_to_use, xdp_ring->tail); } -void ice_finalize_xdp_rx(struct ice_ring *rx_ring, unsigned int xdp_res); -int ice_xmit_xdp_buff(struct xdp_buff *xdp, struct ice_ring *xdp_ring); -int ice_xmit_xdp_ring(void *data, u16 size, struct ice_ring *xdp_ring); -void ice_release_rx_desc(struct ice_ring *rx_ring, u16 val); +void ice_finalize_xdp_rx(struct ice_tx_ring *xdp_ring, unsigned int xdp_res); +int ice_xmit_xdp_buff(struct xdp_buff *xdp, struct ice_tx_ring *xdp_ring); +int ice_xmit_xdp_ring(void *data, u16 size, struct ice_tx_ring *xdp_ring); +void ice_release_rx_desc(struct ice_rx_ring *rx_ring, u16 val); void -ice_process_skb_fields(struct ice_ring *rx_ring, +ice_process_skb_fields(struct ice_rx_ring *rx_ring, union ice_32b_rx_flex_desc *rx_desc, struct sk_buff *skb, u16 ptype); void -ice_receive_skb(struct ice_ring *rx_ring, struct sk_buff *skb, u16 vlan_tag); +ice_receive_skb(struct ice_rx_ring *rx_ring, struct sk_buff *skb, u16 vlan_tag); #endif /* !_ICE_TXRX_LIB_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h index e064439fc1a9..9e0c2923c62e 100644 --- a/drivers/net/ethernet/intel/ice/ice_type.h +++ b/drivers/net/ethernet/intel/ice/ice_type.h @@ -138,6 +138,7 @@ enum ice_vsi_type { ICE_VSI_PF = 0, ICE_VSI_VF = 1, ICE_VSI_CTRL = 3, /* equates to ICE_VSI_PF with 1 queue pair */ + ICE_VSI_CHNL = 4, ICE_VSI_LB = 6, ICE_VSI_SWITCHDEV_CTRL = 7, }; @@ -570,6 +571,8 @@ struct ice_sched_vsi_info { struct list_head list_entry; u16 max_lanq[ICE_MAX_TRAFFIC_CLASS]; u16 max_rdmaq[ICE_MAX_TRAFFIC_CLASS]; + /* bw_t_info saves VSI BW information */ + struct ice_bw_type_info bw_t_info[ICE_MAX_TRAFFIC_CLASS]; }; /* driver defines the policy */ @@ -677,6 +680,10 @@ struct ice_port_info { struct ice_switch_info { struct list_head vsi_list_map_head; struct ice_sw_recipe *recp_list; + u16 prof_res_bm_init; + u16 max_used_prof_index; + + DECLARE_BITMAP(prof_res_bm[ICE_MAX_NUM_PROFILES], ICE_MAX_FV_WORDS); }; /* FW logging configuration */ @@ -912,6 +919,7 @@ struct ice_hw { struct mutex rss_locks; /* protect RSS configuration */ struct list_head rss_list_head; struct ice_mbx_snapshot mbx_snapshot; + u16 io_expander_handle; }; /* Statistics collected by each port, VSI, VEB, and S-channel */ diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c index 4d0b643906ff..a42eaf6f942e 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c @@ -5,6 +5,7 @@ #include "ice_base.h" #include "ice_lib.h" #include "ice_fltr.h" +#include "ice_dcb_lib.h" #include "ice_flow.h" #include "ice_eswitch.h" #include "ice_virtchnl_allowlist.h" @@ -831,7 +832,7 @@ static struct ice_vsi *ice_vf_vsi_setup(struct ice_vf *vf) struct ice_pf *pf = vf->pf; struct ice_vsi *vsi; - vsi = ice_vsi_setup(pf, pi, ICE_VSI_VF, vf->vf_id); + vsi = ice_vsi_setup(pf, pi, ICE_VSI_VF, vf->vf_id, NULL); if (!vsi) { dev_err(ice_pf_to_dev(pf), "Failed to create VF VSI\n"); @@ -858,7 +859,7 @@ struct ice_vsi *ice_vf_ctrl_vsi_setup(struct ice_vf *vf) struct ice_pf *pf = vf->pf; struct ice_vsi *vsi; - vsi = ice_vsi_setup(pf, pi, ICE_VSI_CTRL, vf->vf_id); + vsi = ice_vsi_setup(pf, pi, ICE_VSI_CTRL, vf->vf_id, NULL); if (!vsi) { dev_err(ice_pf_to_dev(pf), "Failed to create VF control VSI\n"); ice_vf_ctrl_invalidate_vsi(vf); @@ -884,6 +885,40 @@ static int ice_calc_vf_first_vector_idx(struct ice_pf *pf, struct ice_vf *vf) return pf->sriov_base_vector + vf->vf_id * pf->num_msix_per_vf; } +/** + * ice_vf_rebuild_host_tx_rate_cfg - re-apply the Tx rate limiting configuration + * @vf: VF to re-apply the configuration for + * + * Called after a VF VSI has been re-added/rebuild during reset. The PF driver + * needs to re-apply the host configured Tx rate limiting configuration. + */ +static int ice_vf_rebuild_host_tx_rate_cfg(struct ice_vf *vf) +{ + struct device *dev = ice_pf_to_dev(vf->pf); + struct ice_vsi *vsi = ice_get_vf_vsi(vf); + int err; + + if (vf->min_tx_rate) { + err = ice_set_min_bw_limit(vsi, (u64)vf->min_tx_rate * 1000); + if (err) { + dev_err(dev, "failed to set min Tx rate to %d Mbps for VF %u, error %d\n", + vf->min_tx_rate, vf->vf_id, err); + return err; + } + } + + if (vf->max_tx_rate) { + err = ice_set_max_bw_limit(vsi, (u64)vf->max_tx_rate * 1000); + if (err) { + dev_err(dev, "failed to set max Tx rate to %d Mbps for VF %u, error %d\n", + vf->max_tx_rate, vf->vf_id, err); + return err; + } + } + + return 0; +} + /** * ice_vf_rebuild_host_vlan_cfg - add VLAN 0 filter or rebuild the Port VLAN * @vf: VF to add MAC filters for @@ -1420,6 +1455,11 @@ static void ice_vf_rebuild_host_cfg(struct ice_vf *vf) if (ice_vf_rebuild_host_vlan_cfg(vf)) dev_err(dev, "failed to rebuild VLAN configuration for VF %u\n", vf->vf_id); + + if (ice_vf_rebuild_host_tx_rate_cfg(vf)) + dev_err(dev, "failed to rebuild Tx rate limiting configuration for VF %u\n", + vf->vf_id); + /* rebuild aggregator node config for main VF VSI */ ice_vf_rebuild_aggregator_node_cfg(vsi); } @@ -1975,7 +2015,8 @@ static int ice_ena_vfs(struct ice_pf *pf, u16 num_vfs) clear_bit(ICE_VF_DIS, pf->state); - if (ice_eswitch_configure(pf)) + ret = ice_eswitch_configure(pf); + if (ret) goto err_unroll_sriov; return 0; @@ -3347,7 +3388,7 @@ static int ice_vc_dis_qs_msg(struct ice_vf *vf, u8 *msg) q_map = vqs->tx_queues; for_each_set_bit(vf_q_id, &q_map, ICE_MAX_RSS_QS_PER_VF) { - struct ice_ring *ring = vsi->tx_rings[vf_q_id]; + struct ice_tx_ring *ring = vsi->tx_rings[vf_q_id]; struct ice_txq_meta txq_meta = { 0 }; if (!ice_vc_isvalid_q_id(vf, vqs->vsi_id, vf_q_id)) { @@ -4747,8 +4788,8 @@ ice_get_vf_cfg(struct net_device *netdev, int vf_id, struct ifla_vf_info *ivi) ivi->linkstate = IFLA_VF_LINK_STATE_ENABLE; else ivi->linkstate = IFLA_VF_LINK_STATE_DISABLE; - ivi->max_tx_rate = vf->tx_rate; - ivi->min_tx_rate = 0; + ivi->max_tx_rate = vf->max_tx_rate; + ivi->min_tx_rate = vf->min_tx_rate; return 0; } @@ -4799,11 +4840,6 @@ int ice_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) struct ice_vf *vf; int ret; - if (ice_is_eswitch_mode_switchdev(pf)) { - dev_info(ice_pf_to_dev(pf), "Trusted VF is forbidden in switchdev mode\n"); - return -EOPNOTSUPP; - } - if (ice_validate_vf_id(pf, vf_id)) return -EINVAL; @@ -4863,6 +4899,11 @@ int ice_set_vf_trust(struct net_device *netdev, int vf_id, bool trusted) struct ice_vf *vf; int ret; + if (ice_is_eswitch_mode_switchdev(pf)) { + dev_info(ice_pf_to_dev(pf), "Trusted VF is forbidden in switchdev mode\n"); + return -EOPNOTSUPP; + } + if (ice_validate_vf_id(pf, vf_id)) return -EINVAL; @@ -4926,6 +4967,122 @@ int ice_set_vf_link_state(struct net_device *netdev, int vf_id, int link_state) return 0; } +/** + * ice_calc_all_vfs_min_tx_rate - calculate cumulative min Tx rate on all VFs + * @pf: PF associated with VFs + */ +static int ice_calc_all_vfs_min_tx_rate(struct ice_pf *pf) +{ + int rate = 0, i; + + ice_for_each_vf(pf, i) + rate += pf->vf[i].min_tx_rate; + + return rate; +} + +/** + * ice_min_tx_rate_oversubscribed - check if min Tx rate causes oversubscription + * @vf: VF trying to configure min_tx_rate + * @min_tx_rate: min Tx rate in Mbps + * + * Check if the min_tx_rate being passed in will cause oversubscription of total + * min_tx_rate based on the current link speed and all other VFs configured + * min_tx_rate + * + * Return true if the passed min_tx_rate would cause oversubscription, else + * return false + */ +static bool +ice_min_tx_rate_oversubscribed(struct ice_vf *vf, int min_tx_rate) +{ + int link_speed_mbps = ice_get_link_speed_mbps(ice_get_vf_vsi(vf)); + int all_vfs_min_tx_rate = ice_calc_all_vfs_min_tx_rate(vf->pf); + + /* this VF's previous rate is being overwritten */ + all_vfs_min_tx_rate -= vf->min_tx_rate; + + if (all_vfs_min_tx_rate + min_tx_rate > link_speed_mbps) { + dev_err(ice_pf_to_dev(vf->pf), "min_tx_rate of %d Mbps on VF %u would cause oversubscription of %d Mbps based on the current link speed %d Mbps\n", + min_tx_rate, vf->vf_id, + all_vfs_min_tx_rate + min_tx_rate - link_speed_mbps, + link_speed_mbps); + return true; + } + + return false; +} + +/** + * ice_set_vf_bw - set min/max VF bandwidth + * @netdev: network interface device structure + * @vf_id: VF identifier + * @min_tx_rate: Minimum Tx rate in Mbps + * @max_tx_rate: Maximum Tx rate in Mbps + */ +int +ice_set_vf_bw(struct net_device *netdev, int vf_id, int min_tx_rate, + int max_tx_rate) +{ + struct ice_pf *pf = ice_netdev_to_pf(netdev); + struct ice_vsi *vsi; + struct device *dev; + struct ice_vf *vf; + int ret; + + dev = ice_pf_to_dev(pf); + if (ice_validate_vf_id(pf, vf_id)) + return -EINVAL; + + vf = &pf->vf[vf_id]; + ret = ice_check_vf_ready_for_cfg(vf); + if (ret) + return ret; + + vsi = ice_get_vf_vsi(vf); + + /* when max_tx_rate is zero that means no max Tx rate limiting, so only + * check if max_tx_rate is non-zero + */ + if (max_tx_rate && min_tx_rate > max_tx_rate) { + dev_err(dev, "Cannot set min Tx rate %d Mbps greater than max Tx rate %d Mbps\n", + min_tx_rate, max_tx_rate); + return -EINVAL; + } + + if (min_tx_rate && ice_is_dcb_active(pf)) { + dev_err(dev, "DCB on PF is currently enabled. VF min Tx rate limiting not allowed on this PF.\n"); + return -EOPNOTSUPP; + } + + if (ice_min_tx_rate_oversubscribed(vf, min_tx_rate)) + return -EINVAL; + + if (vf->min_tx_rate != (unsigned int)min_tx_rate) { + ret = ice_set_min_bw_limit(vsi, (u64)min_tx_rate * 1000); + if (ret) { + dev_err(dev, "Unable to set min-tx-rate for VF %d\n", + vf->vf_id); + return ret; + } + + vf->min_tx_rate = min_tx_rate; + } + + if (vf->max_tx_rate != (unsigned int)max_tx_rate) { + ret = ice_set_max_bw_limit(vsi, (u64)max_tx_rate * 1000); + if (ret) { + dev_err(dev, "Unable to set max-tx-rate for VF %d\n", + vf->vf_id); + return ret; + } + + vf->max_tx_rate = max_tx_rate; + } + + return 0; +} + /** * ice_get_vf_stats - populate some stats for the VF * @netdev: the netdev of the PF diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h index 3115284e5411..5ff93a08f54c 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h @@ -125,7 +125,8 @@ struct ice_vf { * the main LAN VSI for the PF. */ u16 lan_vsi_num; /* ID as used by firmware */ - unsigned int tx_rate; /* Tx bandwidth limit in Mbps */ + unsigned int min_tx_rate; /* Minimum Tx bandwidth limit in Mbps */ + unsigned int max_tx_rate; /* Maximum Tx bandwidth limit in Mbps */ DECLARE_BITMAP(vf_states, ICE_VF_STATES_NBITS); /* VF runtime states */ u64 num_inval_msgs; /* number of continuous invalid msgs */ @@ -172,6 +173,10 @@ int ice_set_vf_port_vlan(struct net_device *netdev, int vf_id, u16 vlan_id, u8 qos, __be16 vlan_proto); +int +ice_set_vf_bw(struct net_device *netdev, int vf_id, int min_tx_rate, + int max_tx_rate); + int ice_set_vf_trust(struct net_device *netdev, int vf_id, bool trusted); int ice_set_vf_link_state(struct net_device *netdev, int vf_id, int link_state); @@ -303,6 +308,14 @@ ice_set_vf_link_state(struct net_device __always_unused *netdev, return -EOPNOTSUPP; } +static inline int +ice_set_vf_bw(struct net_device __always_unused *netdev, + int __always_unused vf_id, int __always_unused min_tx_rate, + int __always_unused max_tx_rate) +{ + return -EOPNOTSUPP; +} + static inline int ice_calc_vf_reg_idx(struct ice_vf __always_unused *vf, struct ice_q_vector __always_unused *q_vector) diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index 7682eaa9a9ec..d9dfcfc2c6f9 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -67,7 +67,7 @@ ice_qvec_toggle_napi(struct ice_vsi *vsi, struct ice_q_vector *q_vector, * @q_vector: queue vector */ static void -ice_qvec_dis_irq(struct ice_vsi *vsi, struct ice_ring *rx_ring, +ice_qvec_dis_irq(struct ice_vsi *vsi, struct ice_rx_ring *rx_ring, struct ice_q_vector *q_vector) { struct ice_pf *pf = vsi->back; @@ -104,16 +104,17 @@ ice_qvec_cfg_msix(struct ice_vsi *vsi, struct ice_q_vector *q_vector) u16 reg_idx = q_vector->reg_idx; struct ice_pf *pf = vsi->back; struct ice_hw *hw = &pf->hw; - struct ice_ring *ring; + struct ice_tx_ring *tx_ring; + struct ice_rx_ring *rx_ring; ice_cfg_itr(hw, q_vector); - ice_for_each_ring(ring, q_vector->tx) - ice_cfg_txq_interrupt(vsi, ring->reg_idx, reg_idx, + ice_for_each_tx_ring(tx_ring, q_vector->tx) + ice_cfg_txq_interrupt(vsi, tx_ring->reg_idx, reg_idx, q_vector->tx.itr_idx); - ice_for_each_ring(ring, q_vector->rx) - ice_cfg_rxq_interrupt(vsi, ring->reg_idx, reg_idx, + ice_for_each_rx_ring(rx_ring, q_vector->rx) + ice_cfg_rxq_interrupt(vsi, rx_ring->reg_idx, reg_idx, q_vector->rx.itr_idx); ice_flush(hw); @@ -144,8 +145,9 @@ static void ice_qvec_ena_irq(struct ice_vsi *vsi, struct ice_q_vector *q_vector) static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx) { struct ice_txq_meta txq_meta = { }; - struct ice_ring *tx_ring, *rx_ring; struct ice_q_vector *q_vector; + struct ice_tx_ring *tx_ring; + struct ice_rx_ring *rx_ring; int timeout = 50; int err; @@ -171,7 +173,7 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx) if (err) return err; if (ice_is_xdp_ena_vsi(vsi)) { - struct ice_ring *xdp_ring = vsi->xdp_rings[q_idx]; + struct ice_tx_ring *xdp_ring = vsi->xdp_rings[q_idx]; memset(&txq_meta, 0, sizeof(txq_meta)); ice_fill_txq_meta(vsi, xdp_ring, &txq_meta); @@ -201,8 +203,9 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx) static int ice_qp_ena(struct ice_vsi *vsi, u16 q_idx) { struct ice_aqc_add_tx_qgrp *qg_buf; - struct ice_ring *tx_ring, *rx_ring; struct ice_q_vector *q_vector; + struct ice_tx_ring *tx_ring; + struct ice_rx_ring *rx_ring; u16 size; int err; @@ -225,7 +228,7 @@ static int ice_qp_ena(struct ice_vsi *vsi, u16 q_idx) goto free_buf; if (ice_is_xdp_ena_vsi(vsi)) { - struct ice_ring *xdp_ring = vsi->xdp_rings[q_idx]; + struct ice_tx_ring *xdp_ring = vsi->xdp_rings[q_idx]; memset(qg_buf, 0, size); qg_buf->num_txqs = 1; @@ -233,7 +236,7 @@ static int ice_qp_ena(struct ice_vsi *vsi, u16 q_idx) if (err) goto free_buf; ice_set_ring_xdp(xdp_ring); - xdp_ring->xsk_pool = ice_xsk_pool(xdp_ring); + xdp_ring->xsk_pool = ice_tx_xsk_pool(xdp_ring); } err = ice_vsi_cfg_rxq(rx_ring); @@ -360,7 +363,7 @@ xsk_pool_if_up: * * Returns true if all allocations were successful, false if any fail. */ -bool ice_alloc_rx_bufs_zc(struct ice_ring *rx_ring, u16 count) +bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count) { union ice_32b_rx_flex_desc *rx_desc; u16 ntu = rx_ring->next_to_use; @@ -403,7 +406,7 @@ bool ice_alloc_rx_bufs_zc(struct ice_ring *rx_ring, u16 count) * ice_bump_ntc - Bump the next_to_clean counter of an Rx ring * @rx_ring: Rx ring */ -static void ice_bump_ntc(struct ice_ring *rx_ring) +static void ice_bump_ntc(struct ice_rx_ring *rx_ring) { int ntc = rx_ring->next_to_clean + 1; @@ -422,7 +425,7 @@ static void ice_bump_ntc(struct ice_ring *rx_ring) * Returns the skb on success, NULL on failure. */ static struct sk_buff * -ice_construct_skb_zc(struct ice_ring *rx_ring, struct xdp_buff **xdp_arr) +ice_construct_skb_zc(struct ice_rx_ring *rx_ring, struct xdp_buff **xdp_arr) { struct xdp_buff *xdp = *xdp_arr; unsigned int metasize = xdp->data - xdp->data_meta; @@ -449,22 +452,18 @@ ice_construct_skb_zc(struct ice_ring *rx_ring, struct xdp_buff **xdp_arr) * ice_run_xdp_zc - Executes an XDP program in zero-copy path * @rx_ring: Rx ring * @xdp: xdp_buff used as input to the XDP program + * @xdp_prog: XDP program to run + * @xdp_ring: ring to be used for XDP_TX action * * Returns any of ICE_XDP_{PASS, CONSUMED, TX, REDIR} */ static int -ice_run_xdp_zc(struct ice_ring *rx_ring, struct xdp_buff *xdp) +ice_run_xdp_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp, + struct bpf_prog *xdp_prog, struct ice_tx_ring *xdp_ring) { int err, result = ICE_XDP_PASS; - struct bpf_prog *xdp_prog; - struct ice_ring *xdp_ring; u32 act; - /* ZC patch is enabled only when XDP program is set, - * so here it can not be NULL - */ - xdp_prog = READ_ONCE(rx_ring->xdp_prog); - act = bpf_prog_run_xdp(xdp_prog, xdp); if (likely(act == XDP_REDIRECT)) { @@ -478,7 +477,6 @@ ice_run_xdp_zc(struct ice_ring *rx_ring, struct xdp_buff *xdp) case XDP_PASS: break; case XDP_TX: - xdp_ring = rx_ring->vsi->xdp_rings[rx_ring->q_index]; result = ice_xmit_xdp_buff(xdp, xdp_ring); if (result == ICE_XDP_CONSUMED) goto out_failure; @@ -505,13 +503,21 @@ out_failure: * * Returns number of processed packets on success, remaining budget on failure. */ -int ice_clean_rx_irq_zc(struct ice_ring *rx_ring, int budget) +int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget) { unsigned int total_rx_bytes = 0, total_rx_packets = 0; u16 cleaned_count = ICE_DESC_UNUSED(rx_ring); + struct ice_tx_ring *xdp_ring; unsigned int xdp_xmit = 0; + struct bpf_prog *xdp_prog; bool failure = false; + /* ZC patch is enabled only when XDP program is set, + * so here it can not be NULL + */ + xdp_prog = READ_ONCE(rx_ring->xdp_prog); + xdp_ring = rx_ring->xdp_ring; + while (likely(total_rx_packets < (unsigned int)budget)) { union ice_32b_rx_flex_desc *rx_desc; unsigned int size, xdp_res = 0; @@ -542,7 +548,7 @@ int ice_clean_rx_irq_zc(struct ice_ring *rx_ring, int budget) xsk_buff_set_size(*xdp, size); xsk_buff_dma_sync_for_cpu(*xdp, rx_ring->xsk_pool); - xdp_res = ice_run_xdp_zc(rx_ring, *xdp); + xdp_res = ice_run_xdp_zc(rx_ring, *xdp, xdp_prog, xdp_ring); if (xdp_res) { if (xdp_res & (ICE_XDP_TX | ICE_XDP_REDIR)) xdp_xmit |= xdp_res; @@ -590,7 +596,7 @@ int ice_clean_rx_irq_zc(struct ice_ring *rx_ring, int budget) if (cleaned_count >= ICE_RX_BUF_WRITE) failure = !ice_alloc_rx_bufs_zc(rx_ring, cleaned_count); - ice_finalize_xdp_rx(rx_ring, xdp_xmit); + ice_finalize_xdp_rx(xdp_ring, xdp_xmit); ice_update_rx_ring_stats(rx_ring, total_rx_packets, total_rx_bytes); if (xsk_uses_need_wakeup(rx_ring->xsk_pool)) { @@ -612,7 +618,7 @@ int ice_clean_rx_irq_zc(struct ice_ring *rx_ring, int budget) * * Returns true if cleanup/transmission is done. */ -static bool ice_xmit_zc(struct ice_ring *xdp_ring, int budget) +static bool ice_xmit_zc(struct ice_tx_ring *xdp_ring, int budget) { struct ice_tx_desc *tx_desc = NULL; bool work_done = true; @@ -663,7 +669,7 @@ static bool ice_xmit_zc(struct ice_ring *xdp_ring, int budget) * @tx_buf: Tx buffer to clean */ static void -ice_clean_xdp_tx_buf(struct ice_ring *xdp_ring, struct ice_tx_buf *tx_buf) +ice_clean_xdp_tx_buf(struct ice_tx_ring *xdp_ring, struct ice_tx_buf *tx_buf) { xdp_return_frame((struct xdp_frame *)tx_buf->raw_buf); dma_unmap_single(xdp_ring->dev, dma_unmap_addr(tx_buf, dma), @@ -678,7 +684,7 @@ ice_clean_xdp_tx_buf(struct ice_ring *xdp_ring, struct ice_tx_buf *tx_buf) * * Returns true if cleanup/tranmission is done. */ -bool ice_clean_tx_irq_zc(struct ice_ring *xdp_ring, int budget) +bool ice_clean_tx_irq_zc(struct ice_tx_ring *xdp_ring, int budget) { int total_packets = 0, total_bytes = 0; s16 ntc = xdp_ring->next_to_clean; @@ -751,7 +757,7 @@ ice_xsk_wakeup(struct net_device *netdev, u32 queue_id, struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_q_vector *q_vector; struct ice_vsi *vsi = np->vsi; - struct ice_ring *ring; + struct ice_tx_ring *ring; if (test_bit(ICE_DOWN, vsi->state)) return -ENETDOWN; @@ -802,7 +808,7 @@ bool ice_xsk_any_rx_ring_ena(struct ice_vsi *vsi) * ice_xsk_clean_rx_ring - clean buffer pool queues connected to a given Rx ring * @rx_ring: ring to be cleaned */ -void ice_xsk_clean_rx_ring(struct ice_ring *rx_ring) +void ice_xsk_clean_rx_ring(struct ice_rx_ring *rx_ring) { u16 i; @@ -820,7 +826,7 @@ void ice_xsk_clean_rx_ring(struct ice_ring *rx_ring) * ice_xsk_clean_xdp_ring - Clean the XDP Tx ring and its buffer pool queues * @xdp_ring: XDP_Tx ring */ -void ice_xsk_clean_xdp_ring(struct ice_ring *xdp_ring) +void ice_xsk_clean_xdp_ring(struct ice_tx_ring *xdp_ring) { u16 ntc = xdp_ring->next_to_clean, ntu = xdp_ring->next_to_use; u32 xsk_frames = 0; diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.h b/drivers/net/ethernet/intel/ice/ice_xsk.h index ea208808623a..4c7bd8e9dfc4 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.h +++ b/drivers/net/ethernet/intel/ice/ice_xsk.h @@ -11,13 +11,13 @@ struct ice_vsi; #ifdef CONFIG_XDP_SOCKETS int ice_xsk_pool_setup(struct ice_vsi *vsi, struct xsk_buff_pool *pool, u16 qid); -int ice_clean_rx_irq_zc(struct ice_ring *rx_ring, int budget); -bool ice_clean_tx_irq_zc(struct ice_ring *xdp_ring, int budget); +int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget); +bool ice_clean_tx_irq_zc(struct ice_tx_ring *xdp_ring, int budget); int ice_xsk_wakeup(struct net_device *netdev, u32 queue_id, u32 flags); -bool ice_alloc_rx_bufs_zc(struct ice_ring *rx_ring, u16 count); +bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count); bool ice_xsk_any_rx_ring_ena(struct ice_vsi *vsi); -void ice_xsk_clean_rx_ring(struct ice_ring *rx_ring); -void ice_xsk_clean_xdp_ring(struct ice_ring *xdp_ring); +void ice_xsk_clean_rx_ring(struct ice_rx_ring *rx_ring); +void ice_xsk_clean_xdp_ring(struct ice_tx_ring *xdp_ring); #else static inline int ice_xsk_pool_setup(struct ice_vsi __always_unused *vsi, @@ -28,21 +28,21 @@ ice_xsk_pool_setup(struct ice_vsi __always_unused *vsi, } static inline int -ice_clean_rx_irq_zc(struct ice_ring __always_unused *rx_ring, +ice_clean_rx_irq_zc(struct ice_rx_ring __always_unused *rx_ring, int __always_unused budget) { return 0; } static inline bool -ice_clean_tx_irq_zc(struct ice_ring __always_unused *xdp_ring, +ice_clean_tx_irq_zc(struct ice_tx_ring __always_unused *xdp_ring, int __always_unused budget) { return false; } static inline bool -ice_alloc_rx_bufs_zc(struct ice_ring __always_unused *rx_ring, +ice_alloc_rx_bufs_zc(struct ice_rx_ring __always_unused *rx_ring, u16 __always_unused count) { return false; @@ -60,7 +60,7 @@ ice_xsk_wakeup(struct net_device __always_unused *netdev, return -EOPNOTSUPP; } -static inline void ice_xsk_clean_rx_ring(struct ice_ring *rx_ring) { } -static inline void ice_xsk_clean_xdp_ring(struct ice_ring *xdp_ring) { } +static inline void ice_xsk_clean_rx_ring(struct ice_rx_ring *rx_ring) { } +static inline void ice_xsk_clean_xdp_ring(struct ice_tx_ring *xdp_ring) { } #endif /* CONFIG_XDP_SOCKETS */ #endif /* !_ICE_XSK_H_ */ diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c index 0f021909b430..30568e3544cd 100644 --- a/drivers/net/ethernet/intel/igc/igc_ptp.c +++ b/drivers/net/ethernet/intel/igc/igc_ptp.c @@ -773,7 +773,7 @@ static bool igc_is_crosststamp_supported(struct igc_adapter *adapter) static struct system_counterval_t igc_device_tstamp_to_system(u64 tstamp) { -#if IS_ENABLED(CONFIG_X86_TSC) +#if IS_ENABLED(CONFIG_X86_TSC) && !defined(CONFIG_UML) return convert_art_ns_to_tsc(tstamp); #else return (struct system_counterval_t) { }; diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_hw.c b/drivers/net/ethernet/intel/ixgb/ixgb_hw.c index a430871d1c27..c8d1e815ec6b 100644 --- a/drivers/net/ethernet/intel/ixgb/ixgb_hw.c +++ b/drivers/net/ethernet/intel/ixgb/ixgb_hw.c @@ -549,7 +549,7 @@ ixgb_mta_set(struct ixgb_hw *hw, *****************************************************************************/ void ixgb_rar_set(struct ixgb_hw *hw, - u8 *addr, + const u8 *addr, u32 index) { u32 rar_low, rar_high; diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_hw.h b/drivers/net/ethernet/intel/ixgb/ixgb_hw.h index 6064583095da..70bcff5fb3db 100644 --- a/drivers/net/ethernet/intel/ixgb/ixgb_hw.h +++ b/drivers/net/ethernet/intel/ixgb/ixgb_hw.h @@ -740,7 +740,7 @@ bool ixgb_adapter_start(struct ixgb_hw *hw); void ixgb_check_for_link(struct ixgb_hw *hw); bool ixgb_check_for_bad_link(struct ixgb_hw *hw); -void ixgb_rar_set(struct ixgb_hw *hw, u8 *addr, u32 index); +void ixgb_rar_set(struct ixgb_hw *hw, const u8 *addr, u32 index); /* Filters (multicast, vlan, receive) */ void ixgb_mc_addr_list_update(struct ixgb_hw *hw, u8 *mc_addr_list, diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_main.c b/drivers/net/ethernet/intel/ixgb/ixgb_main.c index 5e1e2f0db82a..99d481904ce6 100644 --- a/drivers/net/ethernet/intel/ixgb/ixgb_main.c +++ b/drivers/net/ethernet/intel/ixgb/ixgb_main.c @@ -362,6 +362,7 @@ ixgb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) struct ixgb_adapter *adapter; static int cards_found = 0; int pci_using_dac; + u8 addr[ETH_ALEN]; int i; int err; @@ -461,7 +462,8 @@ ixgb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_eeprom; } - ixgb_get_ee_mac_addr(&adapter->hw, netdev->dev_addr); + ixgb_get_ee_mac_addr(&adapter->hw, addr); + eth_hw_addr_set(netdev, addr); if (!is_valid_ether_addr(netdev->dev_addr)) { netif_err(adapter, probe, adapter->netdev, "Invalid MAC Address\n"); @@ -2227,6 +2229,7 @@ static pci_ers_result_t ixgb_io_slot_reset(struct pci_dev *pdev) { struct net_device *netdev = pci_get_drvdata(pdev); struct ixgb_adapter *adapter = netdev_priv(netdev); + u8 addr[ETH_ALEN]; if (pci_enable_device(pdev)) { netif_err(adapter, probe, adapter->netdev, @@ -2250,7 +2253,8 @@ static pci_ers_result_t ixgb_io_slot_reset(struct pci_dev *pdev) "After reset, the EEPROM checksum is not valid\n"); return PCI_ERS_RESULT_DISCONNECT; } - ixgb_get_ee_mac_addr(&adapter->hw, netdev->dev_addr); + ixgb_get_ee_mac_addr(&adapter->hw, addr); + eth_hw_addr_set(netdev, addr); memcpy(netdev->perm_addr, netdev->dev_addr, netdev->addr_len); if (!is_valid_ether_addr(netdev->perm_addr)) { diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c index 654ec25e6705..bb14fa2241a3 100644 --- a/drivers/net/ethernet/marvell/mv643xx_eth.c +++ b/drivers/net/ethernet/marvell/mv643xx_eth.c @@ -1770,7 +1770,7 @@ static void uc_addr_get(struct mv643xx_eth_private *mp, unsigned char *addr) addr[5] = mac_l & 0xff; } -static void uc_addr_set(struct mv643xx_eth_private *mp, unsigned char *addr) +static void uc_addr_set(struct mv643xx_eth_private *mp, const u8 *addr) { wrlp(mp, MAC_ADDR_HIGH, (addr[0] << 24) | (addr[1] << 16) | (addr[2] << 8) | addr[3]); @@ -2925,10 +2925,14 @@ static void set_params(struct mv643xx_eth_private *mp, struct net_device *dev = mp->dev; unsigned int tx_ring_size; - if (is_valid_ether_addr(pd->mac_addr)) + if (is_valid_ether_addr(pd->mac_addr)) { eth_hw_addr_set(dev, pd->mac_addr); - else - uc_addr_get(mp, dev->dev_addr); + } else { + u8 addr[ETH_ALEN]; + + uc_addr_get(mp, addr); + eth_hw_addr_set(dev, addr); + } mp->rx_ring_size = DEFAULT_RX_QUEUE_SIZE; if (pd->rx_queue_size) diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 761155af25d8..98f276c617fb 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -1623,8 +1623,8 @@ static void mvneta_set_ucast_addr(struct mvneta_port *pp, u8 last_nibble, } /* Set mac address */ -static void mvneta_mac_addr_set(struct mvneta_port *pp, unsigned char *addr, - int queue) +static void mvneta_mac_addr_set(struct mvneta_port *pp, + const unsigned char *addr, int queue) { unsigned int mac_h; unsigned int mac_l; @@ -1914,7 +1914,7 @@ static int mvneta_rx_refill(struct mvneta_port *pp, } /* Handle tx checksum */ -static u32 mvneta_skb_tx_csum(struct mvneta_port *pp, struct sk_buff *skb) +static u32 mvneta_skb_tx_csum(struct sk_buff *skb) { if (skb->ip_summed == CHECKSUM_PARTIAL) { int ip_hdr_len = 0; @@ -2595,8 +2595,7 @@ err_drop_frame: } static inline void -mvneta_tso_put_hdr(struct sk_buff *skb, - struct mvneta_port *pp, struct mvneta_tx_queue *txq) +mvneta_tso_put_hdr(struct sk_buff *skb, struct mvneta_tx_queue *txq) { int hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb); struct mvneta_tx_buf *buf = &txq->buf[txq->txq_put_index]; @@ -2604,7 +2603,7 @@ mvneta_tso_put_hdr(struct sk_buff *skb, tx_desc = mvneta_txq_next_desc_get(txq); tx_desc->data_size = hdr_len; - tx_desc->command = mvneta_skb_tx_csum(pp, skb); + tx_desc->command = mvneta_skb_tx_csum(skb); tx_desc->command |= MVNETA_TXD_F_DESC; tx_desc->buf_phys_addr = txq->tso_hdrs_phys + txq->txq_put_index * TSO_HEADER_SIZE; @@ -2681,7 +2680,7 @@ static int mvneta_tx_tso(struct sk_buff *skb, struct net_device *dev, hdr = txq->tso_hdrs + txq->txq_put_index * TSO_HEADER_SIZE; tso_build_hdr(skb, hdr, &tso, data_left, total_len == 0); - mvneta_tso_put_hdr(skb, pp, txq); + mvneta_tso_put_hdr(skb, txq); while (data_left > 0) { int size; @@ -2799,7 +2798,7 @@ static netdev_tx_t mvneta_tx(struct sk_buff *skb, struct net_device *dev) /* Get a descriptor for the first part of the packet */ tx_desc = mvneta_txq_next_desc_get(txq); - tx_cmd = mvneta_skb_tx_csum(pp, skb); + tx_cmd = mvneta_skb_tx_csum(skb); tx_desc->data_size = skb_headlen(skb); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c index d379a35c4618..186d00a9ab35 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c @@ -1519,7 +1519,6 @@ static int cgx_lmac_exit(struct cgx *cgx) int i; if (cgx->cgx_cmd_workq) { - flush_workqueue(cgx->cgx_cmd_workq); destroy_workqueue(cgx->cgx_cmd_workq); cgx->cgx_cmd_workq = NULL; } diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h index dfe487235007..4e79e918a161 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h @@ -191,6 +191,7 @@ M(CPT_INLINE_IPSEC_CFG, 0xA04, cpt_inline_ipsec_cfg, \ M(CPT_STATS, 0xA05, cpt_sts, cpt_sts_req, cpt_sts_rsp) \ M(CPT_RXC_TIME_CFG, 0xA06, cpt_rxc_time_cfg, cpt_rxc_time_cfg_req, \ msg_rsp) \ +M(CPT_CTX_CACHE_SYNC, 0xA07, cpt_ctx_cache_sync, msg_req, msg_rsp) \ /* SDP mbox IDs (range 0x1000 - 0x11FF) */ \ M(SET_SDP_CHAN_INFO, 0x1000, set_sdp_chan_info, sdp_chan_info_msg, msg_rsp) \ M(GET_SDP_CHAN_INFO, 0x1001, get_sdp_chan_info, msg_req, sdp_get_chan_info_msg) \ @@ -292,10 +293,14 @@ M(NIX_BANDPROF_GET_HWINFO, 0x801f, nix_bandprof_get_hwinfo, msg_req, \ #define MBOX_UP_CGX_MESSAGES \ M(CGX_LINK_EVENT, 0xC00, cgx_link_event, cgx_link_info_msg, msg_rsp) +#define MBOX_UP_CPT_MESSAGES \ +M(CPT_INST_LMTST, 0xD00, cpt_inst_lmtst, cpt_inst_lmtst_req, msg_rsp) + enum { #define M(_name, _id, _1, _2, _3) MBOX_MSG_ ## _name = _id, MBOX_MESSAGES MBOX_UP_CGX_MESSAGES +MBOX_UP_CPT_MESSAGES #undef M }; @@ -1562,6 +1567,13 @@ struct cpt_rxc_time_cfg_req { u16 active_limit; }; +/* Mailbox message request format to request for CPT_INST_S lmtst. */ +struct cpt_inst_lmtst_req { + struct mbox_msghdr hdr; + u64 inst[8]; + u64 rsvd; +}; + struct sdp_node_info { /* Node to which this PF belons to */ u8 node_id; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c index 4cb24e91e648..cb56e171ddd4 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c @@ -854,6 +854,7 @@ static int rvu_setup_nix_hw_resource(struct rvu *rvu, int blkaddr) block->lfcfg_reg = NIX_PRIV_LFX_CFG; block->msixcfg_reg = NIX_PRIV_LFX_INT_CFG; block->lfreset_reg = NIX_AF_LF_RST; + block->rvu = rvu; sprintf(block->name, "NIX%d", blkid); rvu->nix_blkaddr[blkid] = blkaddr; return rvu_alloc_bitmap(&block->lf); @@ -883,6 +884,7 @@ static int rvu_setup_cpt_hw_resource(struct rvu *rvu, int blkaddr) block->lfcfg_reg = CPT_PRIV_LFX_CFG; block->msixcfg_reg = CPT_PRIV_LFX_INT_CFG; block->lfreset_reg = CPT_AF_LF_RST; + block->rvu = rvu; sprintf(block->name, "CPT%d", blkid); return rvu_alloc_bitmap(&block->lf); } @@ -940,6 +942,7 @@ static int rvu_setup_hw_resources(struct rvu *rvu) block->lfcfg_reg = NPA_PRIV_LFX_CFG; block->msixcfg_reg = NPA_PRIV_LFX_INT_CFG; block->lfreset_reg = NPA_AF_LF_RST; + block->rvu = rvu; sprintf(block->name, "NPA"); err = rvu_alloc_bitmap(&block->lf); if (err) { @@ -979,6 +982,7 @@ nix: block->lfcfg_reg = SSO_PRIV_LFX_HWGRP_CFG; block->msixcfg_reg = SSO_PRIV_LFX_HWGRP_INT_CFG; block->lfreset_reg = SSO_AF_LF_HWGRP_RST; + block->rvu = rvu; sprintf(block->name, "SSO GROUP"); err = rvu_alloc_bitmap(&block->lf); if (err) { @@ -1003,6 +1007,7 @@ ssow: block->lfcfg_reg = SSOW_PRIV_LFX_HWS_CFG; block->msixcfg_reg = SSOW_PRIV_LFX_HWS_INT_CFG; block->lfreset_reg = SSOW_AF_LF_HWS_RST; + block->rvu = rvu; sprintf(block->name, "SSOWS"); err = rvu_alloc_bitmap(&block->lf); if (err) { @@ -1028,6 +1033,7 @@ tim: block->lfcfg_reg = TIM_PRIV_LFX_CFG; block->msixcfg_reg = TIM_PRIV_LFX_INT_CFG; block->lfreset_reg = TIM_AF_LF_RST; + block->rvu = rvu; sprintf(block->name, "TIM"); err = rvu_alloc_bitmap(&block->lf); if (err) { @@ -2399,7 +2405,6 @@ static void rvu_mbox_destroy(struct mbox_wq_info *mw) int devid; if (mw->mbox_wq) { - flush_workqueue(mw->mbox_wq); destroy_workqueue(mw->mbox_wq); mw->mbox_wq = NULL; } @@ -2527,7 +2532,8 @@ static void rvu_blklf_teardown(struct rvu *rvu, u16 pcifunc, u8 blkaddr) rvu_npa_lf_teardown(rvu, pcifunc, lf); else if ((block->addr == BLKADDR_CPT0) || (block->addr == BLKADDR_CPT1)) - rvu_cpt_lf_teardown(rvu, pcifunc, lf, slot); + rvu_cpt_lf_teardown(rvu, pcifunc, block->addr, lf, + slot); err = rvu_lf_reset(rvu, block, lf); if (err) { @@ -2725,6 +2731,8 @@ static void rvu_unregister_interrupts(struct rvu *rvu) { int irq; + rvu_cpt_unregister_interrupts(rvu); + /* Disable the Mbox interrupt */ rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_PFAF_MBOX_INT_ENA_W1C, INTR_MASK(rvu->hw->total_pfs) & ~1ULL); @@ -2934,6 +2942,11 @@ static int rvu_register_interrupts(struct rvu *rvu) goto fail; } rvu->irq_allocated[offset] = true; + + ret = rvu_cpt_register_interrupts(rvu); + if (ret) + goto fail; + return 0; fail: @@ -2944,7 +2957,6 @@ fail: static void rvu_flr_wq_destroy(struct rvu *rvu) { if (rvu->flr_wq) { - flush_workqueue(rvu->flr_wq); destroy_workqueue(rvu->flr_wq); rvu->flr_wq = NULL; } diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h index 58b166698fa5..66e45d733824 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h @@ -101,6 +101,7 @@ struct rvu_block { u64 msixcfg_reg; u64 lfreset_reg; unsigned char name[NAME_SIZE]; + struct rvu *rvu; }; struct nix_mcast { @@ -812,7 +813,11 @@ bool is_mcam_entry_enabled(struct rvu *rvu, struct npc_mcam *mcam, int blkaddr, int index); /* CPT APIs */ -int rvu_cpt_lf_teardown(struct rvu *rvu, u16 pcifunc, int lf, int slot); +int rvu_cpt_register_interrupts(struct rvu *rvu); +void rvu_cpt_unregister_interrupts(struct rvu *rvu); +int rvu_cpt_lf_teardown(struct rvu *rvu, u16 pcifunc, int blkaddr, int lf, + int slot); +int rvu_cpt_ctx_flush(struct rvu *rvu, u16 pcifunc); /* CN10K RVU */ int rvu_set_channels_base(struct rvu *rvu); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c index c3842e454657..2ca182a4ce82 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c @@ -324,7 +324,6 @@ static int cgx_lmac_event_handler_init(struct rvu *rvu) static void rvu_cgx_wq_destroy(struct rvu *rvu) { if (rvu->cgx_evh_wq) { - flush_workqueue(rvu->cgx_evh_wq); destroy_workqueue(rvu->cgx_evh_wq); rvu->cgx_evh_wq = NULL; } diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c index 267d092b8e97..45357deecabb 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c @@ -37,6 +37,236 @@ (_rsp)->free_sts_##etype = free_sts; \ }) +static irqreturn_t rvu_cpt_af_flt_intr_handler(int irq, void *ptr) +{ + struct rvu_block *block = ptr; + struct rvu *rvu = block->rvu; + int blkaddr = block->addr; + u64 reg0, reg1, reg2; + + reg0 = rvu_read64(rvu, blkaddr, CPT_AF_FLTX_INT(0)); + reg1 = rvu_read64(rvu, blkaddr, CPT_AF_FLTX_INT(1)); + if (!is_rvu_otx2(rvu)) { + reg2 = rvu_read64(rvu, blkaddr, CPT_AF_FLTX_INT(2)); + dev_err_ratelimited(rvu->dev, + "Received CPTAF FLT irq : 0x%llx, 0x%llx, 0x%llx", + reg0, reg1, reg2); + } else { + dev_err_ratelimited(rvu->dev, + "Received CPTAF FLT irq : 0x%llx, 0x%llx", + reg0, reg1); + } + + rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT(0), reg0); + rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT(1), reg1); + if (!is_rvu_otx2(rvu)) + rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT(2), reg2); + + return IRQ_HANDLED; +} + +static irqreturn_t rvu_cpt_af_rvu_intr_handler(int irq, void *ptr) +{ + struct rvu_block *block = ptr; + struct rvu *rvu = block->rvu; + int blkaddr = block->addr; + u64 reg; + + reg = rvu_read64(rvu, blkaddr, CPT_AF_RVU_INT); + dev_err_ratelimited(rvu->dev, "Received CPTAF RVU irq : 0x%llx", reg); + + rvu_write64(rvu, blkaddr, CPT_AF_RVU_INT, reg); + return IRQ_HANDLED; +} + +static irqreturn_t rvu_cpt_af_ras_intr_handler(int irq, void *ptr) +{ + struct rvu_block *block = ptr; + struct rvu *rvu = block->rvu; + int blkaddr = block->addr; + u64 reg; + + reg = rvu_read64(rvu, blkaddr, CPT_AF_RAS_INT); + dev_err_ratelimited(rvu->dev, "Received CPTAF RAS irq : 0x%llx", reg); + + rvu_write64(rvu, blkaddr, CPT_AF_RAS_INT, reg); + return IRQ_HANDLED; +} + +static int rvu_cpt_do_register_interrupt(struct rvu_block *block, int irq_offs, + irq_handler_t handler, + const char *name) +{ + struct rvu *rvu = block->rvu; + int ret; + + ret = request_irq(pci_irq_vector(rvu->pdev, irq_offs), handler, 0, + name, block); + if (ret) { + dev_err(rvu->dev, "RVUAF: %s irq registration failed", name); + return ret; + } + + WARN_ON(rvu->irq_allocated[irq_offs]); + rvu->irq_allocated[irq_offs] = true; + return 0; +} + +static void cpt_10k_unregister_interrupts(struct rvu_block *block, int off) +{ + struct rvu *rvu = block->rvu; + int blkaddr = block->addr; + int i; + + /* Disable all CPT AF interrupts */ + for (i = 0; i < CPT_10K_AF_INT_VEC_RVU; i++) + rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT_ENA_W1C(i), 0x1); + rvu_write64(rvu, blkaddr, CPT_AF_RVU_INT_ENA_W1C, 0x1); + rvu_write64(rvu, blkaddr, CPT_AF_RAS_INT_ENA_W1C, 0x1); + + for (i = 0; i < CPT_10K_AF_INT_VEC_CNT; i++) + if (rvu->irq_allocated[off + i]) { + free_irq(pci_irq_vector(rvu->pdev, off + i), block); + rvu->irq_allocated[off + i] = false; + } +} + +static void cpt_unregister_interrupts(struct rvu *rvu, int blkaddr) +{ + struct rvu_hwinfo *hw = rvu->hw; + struct rvu_block *block; + int i, offs; + + if (!is_block_implemented(rvu->hw, blkaddr)) + return; + offs = rvu_read64(rvu, blkaddr, CPT_PRIV_AF_INT_CFG) & 0x7FF; + if (!offs) { + dev_warn(rvu->dev, + "Failed to get CPT_AF_INT vector offsets\n"); + return; + } + block = &hw->block[blkaddr]; + if (!is_rvu_otx2(rvu)) + return cpt_10k_unregister_interrupts(block, offs); + + /* Disable all CPT AF interrupts */ + for (i = 0; i < CPT_AF_INT_VEC_RVU; i++) + rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT_ENA_W1C(i), 0x1); + rvu_write64(rvu, blkaddr, CPT_AF_RVU_INT_ENA_W1C, 0x1); + rvu_write64(rvu, blkaddr, CPT_AF_RAS_INT_ENA_W1C, 0x1); + + for (i = 0; i < CPT_AF_INT_VEC_CNT; i++) + if (rvu->irq_allocated[offs + i]) { + free_irq(pci_irq_vector(rvu->pdev, offs + i), block); + rvu->irq_allocated[offs + i] = false; + } +} + +void rvu_cpt_unregister_interrupts(struct rvu *rvu) +{ + cpt_unregister_interrupts(rvu, BLKADDR_CPT0); + cpt_unregister_interrupts(rvu, BLKADDR_CPT1); +} + +static int cpt_10k_register_interrupts(struct rvu_block *block, int off) +{ + struct rvu *rvu = block->rvu; + int blkaddr = block->addr; + char irq_name[16]; + int i, ret; + + for (i = CPT_10K_AF_INT_VEC_FLT0; i < CPT_10K_AF_INT_VEC_RVU; i++) { + snprintf(irq_name, sizeof(irq_name), "CPTAF FLT%d", i); + ret = rvu_cpt_do_register_interrupt(block, off + i, + rvu_cpt_af_flt_intr_handler, + irq_name); + if (ret) + goto err; + rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT_ENA_W1S(i), 0x1); + } + + ret = rvu_cpt_do_register_interrupt(block, off + CPT_10K_AF_INT_VEC_RVU, + rvu_cpt_af_rvu_intr_handler, + "CPTAF RVU"); + if (ret) + goto err; + rvu_write64(rvu, blkaddr, CPT_AF_RVU_INT_ENA_W1S, 0x1); + + ret = rvu_cpt_do_register_interrupt(block, off + CPT_10K_AF_INT_VEC_RAS, + rvu_cpt_af_ras_intr_handler, + "CPTAF RAS"); + if (ret) + goto err; + rvu_write64(rvu, blkaddr, CPT_AF_RAS_INT_ENA_W1S, 0x1); + + return 0; +err: + rvu_cpt_unregister_interrupts(rvu); + return ret; +} + +static int cpt_register_interrupts(struct rvu *rvu, int blkaddr) +{ + struct rvu_hwinfo *hw = rvu->hw; + struct rvu_block *block; + int i, offs, ret = 0; + char irq_name[16]; + + if (!is_block_implemented(rvu->hw, blkaddr)) + return 0; + + block = &hw->block[blkaddr]; + offs = rvu_read64(rvu, blkaddr, CPT_PRIV_AF_INT_CFG) & 0x7FF; + if (!offs) { + dev_warn(rvu->dev, + "Failed to get CPT_AF_INT vector offsets\n"); + return 0; + } + + if (!is_rvu_otx2(rvu)) + return cpt_10k_register_interrupts(block, offs); + + for (i = CPT_AF_INT_VEC_FLT0; i < CPT_AF_INT_VEC_RVU; i++) { + snprintf(irq_name, sizeof(irq_name), "CPTAF FLT%d", i); + ret = rvu_cpt_do_register_interrupt(block, offs + i, + rvu_cpt_af_flt_intr_handler, + irq_name); + if (ret) + goto err; + rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT_ENA_W1S(i), 0x1); + } + + ret = rvu_cpt_do_register_interrupt(block, offs + CPT_AF_INT_VEC_RVU, + rvu_cpt_af_rvu_intr_handler, + "CPTAF RVU"); + if (ret) + goto err; + rvu_write64(rvu, blkaddr, CPT_AF_RVU_INT_ENA_W1S, 0x1); + + ret = rvu_cpt_do_register_interrupt(block, offs + CPT_AF_INT_VEC_RAS, + rvu_cpt_af_ras_intr_handler, + "CPTAF RAS"); + if (ret) + goto err; + rvu_write64(rvu, blkaddr, CPT_AF_RAS_INT_ENA_W1S, 0x1); + + return 0; +err: + rvu_cpt_unregister_interrupts(rvu); + return ret; +} + +int rvu_cpt_register_interrupts(struct rvu *rvu) +{ + int ret; + + ret = cpt_register_interrupts(rvu, BLKADDR_CPT0); + if (ret) + return ret; + + return cpt_register_interrupts(rvu, BLKADDR_CPT1); +} + static int get_cpt_pf_num(struct rvu *rvu) { int i, domain_nr, cpt_pf_num = -1; @@ -147,9 +377,13 @@ int rvu_mbox_handler_cpt_lf_alloc(struct rvu *rvu, rvu_write64(rvu, blkaddr, CPT_AF_LFX_CTL(cptlf), val); - /* Set CPT LF NIX_PF_FUNC and SSO_PF_FUNC */ - val = (u64)req->nix_pf_func << 48 | - (u64)req->sso_pf_func << 32; + /* Set CPT LF NIX_PF_FUNC and SSO_PF_FUNC. EXE_LDWB is set + * on reset. + */ + val = rvu_read64(rvu, blkaddr, CPT_AF_LFX_CTL2(cptlf)); + val &= ~(GENMASK_ULL(63, 48) | GENMASK_ULL(47, 32)); + val |= ((u64)req->nix_pf_func << 48 | + (u64)req->sso_pf_func << 32); rvu_write64(rvu, blkaddr, CPT_AF_LFX_CTL2(cptlf), val); } @@ -159,7 +393,7 @@ int rvu_mbox_handler_cpt_lf_alloc(struct rvu *rvu, static int cpt_lf_free(struct rvu *rvu, struct msg_req *req, int blkaddr) { u16 pcifunc = req->hdr.pcifunc; - int num_lfs, cptlf, slot; + int num_lfs, cptlf, slot, err; struct rvu_block *block; block = &rvu->hw->block[blkaddr]; @@ -173,10 +407,15 @@ static int cpt_lf_free(struct rvu *rvu, struct msg_req *req, int blkaddr) if (cptlf < 0) return CPT_AF_ERR_LF_INVALID; - /* Reset CPT LF group and priority */ - rvu_write64(rvu, blkaddr, CPT_AF_LFX_CTL(cptlf), 0x0); - /* Reset CPT LF NIX_PF_FUNC and SSO_PF_FUNC */ - rvu_write64(rvu, blkaddr, CPT_AF_LFX_CTL2(cptlf), 0x0); + /* Perform teardown */ + rvu_cpt_lf_teardown(rvu, pcifunc, blkaddr, cptlf, slot); + + /* Reset LF */ + err = rvu_lf_reset(rvu, block, cptlf); + if (err) { + dev_err(rvu->dev, "Failed to reset blkaddr %d LF%d\n", + block->addr, cptlf); + } } return 0; @@ -556,6 +795,58 @@ int rvu_mbox_handler_cpt_rxc_time_cfg(struct rvu *rvu, return 0; } +int rvu_mbox_handler_cpt_ctx_cache_sync(struct rvu *rvu, struct msg_req *req, + struct msg_rsp *rsp) +{ + return rvu_cpt_ctx_flush(rvu, req->hdr.pcifunc); +} + +static void cpt_rxc_teardown(struct rvu *rvu, int blkaddr) +{ + struct cpt_rxc_time_cfg_req req; + int timeout = 2000; + u64 reg; + + if (is_rvu_otx2(rvu)) + return; + + /* Set time limit to minimum values, so that rxc entries will be + * flushed out quickly. + */ + req.step = 1; + req.zombie_thres = 1; + req.zombie_limit = 1; + req.active_thres = 1; + req.active_limit = 1; + + cpt_rxc_time_cfg(rvu, &req, blkaddr); + + do { + reg = rvu_read64(rvu, blkaddr, CPT_AF_RXC_ACTIVE_STS); + udelay(1); + if (FIELD_GET(RXC_ACTIVE_COUNT, reg)) + timeout--; + else + break; + } while (timeout); + + if (timeout == 0) + dev_warn(rvu->dev, "Poll for RXC active count hits hard loop counter\n"); + + timeout = 2000; + do { + reg = rvu_read64(rvu, blkaddr, CPT_AF_RXC_ZOMBIE_STS); + udelay(1); + if (FIELD_GET(RXC_ZOMBIE_COUNT, reg)) + timeout--; + else + break; + } while (timeout); + + if (timeout == 0) + dev_warn(rvu->dev, "Poll for RXC zombie count hits hard loop counter\n"); +} + #define INPROG_INFLIGHT(reg) ((reg) & 0x1FF) #define INPROG_GRB_PARTIAL(reg) ((reg) & BIT_ULL(31)) #define INPROG_GRB(reg) (((reg) >> 32) & 0xFF) @@ -620,14 +911,12 @@ static void cpt_lf_disable_iqueue(struct rvu *rvu, int blkaddr, int slot) dev_warn(rvu->dev, "CPT FLR hits hard loop counter\n"); } -int rvu_cpt_lf_teardown(struct rvu *rvu, u16 pcifunc, int lf, int slot) +int rvu_cpt_lf_teardown(struct rvu *rvu, u16 pcifunc, int blkaddr, int lf, int slot) { - int blkaddr; u64 reg; - blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_CPT, pcifunc); - if (blkaddr != BLKADDR_CPT0 && blkaddr != BLKADDR_CPT1) - return -EINVAL; + if (is_cpt_pf(rvu, pcifunc) || is_cpt_vf(rvu, pcifunc)) + cpt_rxc_teardown(rvu, blkaddr); /* Enable BAR2 ALIAS for this pcifunc. */ reg = BIT_ULL(16) | pcifunc; @@ -644,3 +933,154 @@ int rvu_cpt_lf_teardown(struct rvu *rvu, u16 pcifunc, int lf, int slot) return 0; } + +#define CPT_RES_LEN 16 +#define CPT_SE_IE_EGRP 1ULL + +static int cpt_inline_inb_lf_cmd_send(struct rvu *rvu, int blkaddr, + int nix_blkaddr) +{ + int cpt_pf_num = get_cpt_pf_num(rvu); + struct cpt_inst_lmtst_req *req; + dma_addr_t res_daddr; + int timeout = 3000; + u8 cpt_idx; + u64 *inst; + u16 *res; + int rc; + + res = kzalloc(CPT_RES_LEN, GFP_KERNEL); + if (!res) + return -ENOMEM; + + res_daddr = dma_map_single(rvu->dev, res, CPT_RES_LEN, + DMA_BIDIRECTIONAL); + if (dma_mapping_error(rvu->dev, res_daddr)) { + dev_err(rvu->dev, "DMA mapping failed for CPT result\n"); + rc = -EFAULT; + goto res_free; + } + *res = 0xFFFF; + + /* Send mbox message to CPT PF */ + req = (struct cpt_inst_lmtst_req *) + otx2_mbox_alloc_msg_rsp(&rvu->afpf_wq_info.mbox_up, + cpt_pf_num, sizeof(*req), + sizeof(struct msg_rsp)); + if (!req) { + rc = -ENOMEM; + goto res_daddr_unmap; + } + req->hdr.sig = OTX2_MBOX_REQ_SIG; + req->hdr.id = MBOX_MSG_CPT_INST_LMTST; + + inst = req->inst; + /* Prepare CPT_INST_S */ + inst[0] = 0; + inst[1] = res_daddr; + /* AF PF FUNC */ + inst[2] = 0; + /* Set QORD */ + inst[3] = 1; + inst[4] = 0; + inst[5] = 0; + inst[6] = 0; + /* Set EGRP */ + inst[7] = CPT_SE_IE_EGRP << 61; + + /* Subtract 1 from the NIX-CPT credit count to preserve + * credit counts. + */ + cpt_idx = (blkaddr == BLKADDR_CPT0) ? 0 : 1; + rvu_write64(rvu, nix_blkaddr, NIX_AF_RX_CPTX_CREDIT(cpt_idx), + BIT_ULL(22) - 1); + + otx2_mbox_msg_send(&rvu->afpf_wq_info.mbox_up, cpt_pf_num); + rc = otx2_mbox_wait_for_rsp(&rvu->afpf_wq_info.mbox_up, cpt_pf_num); + if (rc) + dev_warn(rvu->dev, "notification to pf %d failed\n", + cpt_pf_num); + /* Wait for CPT instruction to be completed */ + do { + mdelay(1); + if (*res == 0xFFFF) + timeout--; + else + break; + } while (timeout); + + if (timeout == 0) + dev_warn(rvu->dev, "Poll for result hits hard loop counter\n"); + +res_daddr_unmap: + dma_unmap_single(rvu->dev, res_daddr, CPT_RES_LEN, DMA_BIDIRECTIONAL); +res_free: + kfree(res); + + return 0; +} + +#define CTX_CAM_PF_FUNC GENMASK_ULL(61, 46) +#define CTX_CAM_CPTR GENMASK_ULL(45, 0) + +int rvu_cpt_ctx_flush(struct rvu *rvu, u16 pcifunc) +{ + int nix_blkaddr, blkaddr; + u16 max_ctx_entries, i; + int slot = 0, num_lfs; + u64 reg, cam_data; + int rc; + + nix_blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc); + if (nix_blkaddr < 0) + return -EINVAL; + + if (is_rvu_otx2(rvu)) + return 0; + + blkaddr = (nix_blkaddr == BLKADDR_NIX1) ? BLKADDR_CPT1 : BLKADDR_CPT0; + + /* Submit CPT_INST_S to track when all packets have been + * flushed through for the NIX PF FUNC in inline inbound case. + */ + rc = cpt_inline_inb_lf_cmd_send(rvu, blkaddr, nix_blkaddr); + if (rc) + return rc; + + /* Wait for rxc entries to be flushed out */ + cpt_rxc_teardown(rvu, blkaddr); + + reg = rvu_read64(rvu, blkaddr, CPT_AF_CONSTANTS0); + max_ctx_entries = (reg >> 48) & 0xFFF; + + mutex_lock(&rvu->rsrc_lock); + + num_lfs = rvu_get_rsrc_mapcount(rvu_get_pfvf(rvu, pcifunc), + blkaddr); + if (num_lfs == 0) { + dev_warn(rvu->dev, "CPT LF is not configured\n"); + goto unlock; + } + + /* Enable BAR2 ALIAS for this pcifunc. */ + reg = BIT_ULL(16) | pcifunc; + rvu_write64(rvu, blkaddr, CPT_AF_BAR2_SEL, reg); + + for (i = 0; i < max_ctx_entries; i++) { + cam_data = rvu_read64(rvu, blkaddr, CPT_AF_CTX_CAM_DATA(i)); + + if ((FIELD_GET(CTX_CAM_PF_FUNC, cam_data) == pcifunc) && + FIELD_GET(CTX_CAM_CPTR, cam_data)) { + reg = BIT_ULL(46) | FIELD_GET(CTX_CAM_CPTR, cam_data); + rvu_write64(rvu, blkaddr, + CPT_AF_BAR2_ALIASX(slot, CPT_LF_CTX_FLUSH), + reg); + } + } + rvu_write64(rvu, blkaddr, CPT_AF_BAR2_SEL, 0); + +unlock: + mutex_unlock(&rvu->rsrc_lock); + + return 0; +} diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c index dcff8a9cc629..d8b1948aaa0a 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c @@ -4515,6 +4515,8 @@ int rvu_mbox_handler_nix_lf_stop_rx(struct rvu *rvu, struct msg_req *req, return rvu_cgx_start_stop_io(rvu, pcifunc, false); } +#define RX_SA_BASE GENMASK_ULL(52, 7) + void rvu_nix_lf_teardown(struct rvu *rvu, u16 pcifunc, int blkaddr, int nixlf) { struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc); @@ -4522,6 +4524,7 @@ void rvu_nix_lf_teardown(struct rvu *rvu, u16 pcifunc, int blkaddr, int nixlf) int pf = rvu_get_pf(pcifunc); struct mac_ops *mac_ops; u8 cgx_id, lmac_id; + u64 sa_base; void *cgxd; int err; @@ -4578,6 +4581,14 @@ void rvu_nix_lf_teardown(struct rvu *rvu, u16 pcifunc, int blkaddr, int nixlf) nix_ctx_free(rvu, pfvf); nix_free_all_bandprof(rvu, pcifunc); + + sa_base = rvu_read64(rvu, blkaddr, NIX_AF_LFX_RX_IPSEC_SA_BASE(nixlf)); + if (FIELD_GET(RX_SA_BASE, sa_base)) { + err = rvu_cpt_ctx_flush(rvu, pcifunc); + if (err) + dev_err(rvu->dev, + "CPT ctx flush failed with error: %d\n", err); + } } #define NIX_AF_LFX_TX_CFG_PTP_EN BIT_ULL(32) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h index dbaeb10de7c2..22cd751613cd 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h @@ -527,6 +527,7 @@ #define CPT_AF_CTX_WBACK_LATENCY_PC (0x49448ull) #define CPT_AF_CTX_PSH_PC (0x49450ull) #define CPT_AF_CTX_PSH_LATENCY_PC (0x49458ull) +#define CPT_AF_CTX_CAM_DATA(a) (0x49800ull | (u64)(a) << 3) #define CPT_AF_RXC_TIME (0x50010ull) #define CPT_AF_RXC_TIME_CFG (0x50018ull) #define CPT_AF_RXC_DFRG (0x50020ull) @@ -544,6 +545,7 @@ #define CPT_LF_CTL 0x10 #define CPT_LF_INPROG 0x40 #define CPT_LF_Q_GRP_PTR 0x120 +#define CPT_LF_CTX_FLUSH 0x510 #define NPC_AF_BLK_RST (0x00040) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h index 77ac96693f04..edc9367b1b95 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h @@ -62,6 +62,24 @@ enum rvu_af_int_vec_e { RVU_AF_INT_VEC_CNT = 0x5, }; +/* CPT Admin function Interrupt Vector Enumeration */ +enum cpt_af_int_vec_e { + CPT_AF_INT_VEC_FLT0 = 0x0, + CPT_AF_INT_VEC_FLT1 = 0x1, + CPT_AF_INT_VEC_RVU = 0x2, + CPT_AF_INT_VEC_RAS = 0x3, + CPT_AF_INT_VEC_CNT = 0x4, +}; + +enum cpt_10k_af_int_vec_e { + CPT_10K_AF_INT_VEC_FLT0 = 0x0, + CPT_10K_AF_INT_VEC_FLT1 = 0x1, + CPT_10K_AF_INT_VEC_FLT2 = 0x2, + CPT_10K_AF_INT_VEC_RVU = 0x3, + CPT_10K_AF_INT_VEC_RAS = 0x4, + CPT_10K_AF_INT_VEC_CNT = 0x5, +}; + /* NPA Admin function Interrupt Vector Enumeration */ enum npa_af_int_vec_e { NPA_AF_INT_VEC_RVU = 0x0, diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/Makefile b/drivers/net/ethernet/marvell/octeontx2/nic/Makefile index aaf9accc40ed..0048b5946712 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/Makefile +++ b/drivers/net/ethernet/marvell/octeontx2/nic/Makefile @@ -3,12 +3,12 @@ # Makefile for Marvell's RVU Ethernet device drivers # -obj-$(CONFIG_OCTEONTX2_PF) += rvu_nicpf.o -obj-$(CONFIG_OCTEONTX2_VF) += rvu_nicvf.o +obj-$(CONFIG_OCTEONTX2_PF) += rvu_nicpf.o otx2_ptp.o +obj-$(CONFIG_OCTEONTX2_VF) += rvu_nicvf.o otx2_ptp.o rvu_nicpf-y := otx2_pf.o otx2_common.o otx2_txrx.o otx2_ethtool.o \ - otx2_ptp.o otx2_flows.o otx2_tc.o cn10k.o otx2_dmac_flt.o \ + otx2_flows.o otx2_tc.o cn10k.o otx2_dmac_flt.o \ otx2_devlink.o -rvu_nicvf-y := otx2_vf.o otx2_devlink.o otx2_ptp.o +rvu_nicvf-y := otx2_vf.o otx2_devlink.o ccflags-y += -I$(srctree)/drivers/net/ethernet/marvell/octeontx2/af diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c index 95f21dfdba48..fd4f083c699e 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c @@ -88,7 +88,7 @@ int cn10k_sq_aq_init(void *dev, u16 qidx, u16 sqb_aura) aq->sq.ena = 1; /* Only one SMQ is allocated, map all SQ's to that SMQ */ aq->sq.smq = pfvf->hw.txschq_list[NIX_TXSCH_LVL_SMQ][0]; - aq->sq.smq_rr_weight = mtu_to_dwrr_weight(pfvf, pfvf->max_frs); + aq->sq.smq_rr_weight = mtu_to_dwrr_weight(pfvf, pfvf->tx_max_pktlen); aq->sq.default_chan = pfvf->hw.tx_chan_base; aq->sq.sqe_stype = NIX_STYPE_STF; /* Cache SQB */ aq->sq.sqb_aura = sqb_aura; diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c index 0c89eb8a670b..66da31f30d3e 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c @@ -231,7 +231,7 @@ int otx2_hw_set_mtu(struct otx2_nic *pfvf, int mtu) return -ENOMEM; } - req->maxlen = pfvf->max_frs; + req->maxlen = pfvf->netdev->mtu + OTX2_ETH_HLEN + OTX2_HW_TIMESTAMP_LEN; err = otx2_sync_mbox_msg(&pfvf->mbox); mutex_unlock(&pfvf->mbox.lock); @@ -590,7 +590,7 @@ int otx2_txschq_config(struct otx2_nic *pfvf, int lvl) u64 schq, parent; u64 dwrr_val; - dwrr_val = mtu_to_dwrr_weight(pfvf, pfvf->max_frs); + dwrr_val = mtu_to_dwrr_weight(pfvf, pfvf->tx_max_pktlen); req = otx2_mbox_alloc_msg_nix_txschq_cfg(&pfvf->mbox); if (!req) @@ -603,9 +603,7 @@ int otx2_txschq_config(struct otx2_nic *pfvf, int lvl) /* Set topology e.t.c configuration */ if (lvl == NIX_TXSCH_LVL_SMQ) { req->reg[0] = NIX_AF_SMQX_CFG(schq); - req->regval[0] = ((pfvf->netdev->max_mtu + OTX2_ETH_HLEN) << 8) - | OTX2_MIN_MTU; - + req->regval[0] = ((u64)pfvf->tx_max_pktlen << 8) | OTX2_MIN_MTU; req->regval[0] |= (0x20ULL << 51) | (0x80ULL << 39) | (0x2ULL << 36); req->num_regs++; @@ -800,7 +798,7 @@ int otx2_sq_aq_init(void *dev, u16 qidx, u16 sqb_aura) aq->sq.ena = 1; /* Only one SMQ is allocated, map all SQ's to that SMQ */ aq->sq.smq = pfvf->hw.txschq_list[NIX_TXSCH_LVL_SMQ][0]; - aq->sq.smq_rr_quantum = mtu_to_dwrr_weight(pfvf, pfvf->max_frs); + aq->sq.smq_rr_quantum = mtu_to_dwrr_weight(pfvf, pfvf->tx_max_pktlen); aq->sq.default_chan = pfvf->hw.tx_chan_base; aq->sq.sqe_stype = NIX_STYPE_STF; /* Cache SQB */ aq->sq.sqb_aura = sqb_aura; diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h index a05f6bdac01e..61e52812983f 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h @@ -326,7 +326,7 @@ struct otx2_nic { struct net_device *netdev; struct dev_hw_ops *hw_ops; void *iommu_domain; - u16 max_frs; + u16 tx_max_pktlen; u16 rbsize; /* Receive buffer size */ #define OTX2_FLAG_RX_TSTAMP_ENABLED BIT_ULL(0) diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index f24e920324eb..1e0d0c9c1dac 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -1312,16 +1312,14 @@ static int otx2_get_rbuf_size(struct otx2_nic *pf, int mtu) * NIX transfers entire data using 6 segments/buffers and writes * a CQE_RX descriptor with those segment addresses. First segment * has additional data prepended to packet. Also software omits a - * headroom of 128 bytes and sizeof(struct skb_shared_info) in - * each segment. Hence the total size of memory needed - * to receive a packet with 'mtu' is: + * headroom of 128 bytes in each segment. Hence the total size of + * memory needed to receive a packet with 'mtu' is: * frame size = mtu + additional data; - * memory = frame_size + (headroom + struct skb_shared_info size) * 6; + * memory = frame_size + headroom * 6; * each receive buffer size = memory / 6; */ frame_size = mtu + OTX2_ETH_HLEN + OTX2_HW_TIMESTAMP_LEN; - total_size = frame_size + (OTX2_HEAD_ROOM + - OTX2_DATA_ALIGN(sizeof(struct skb_shared_info))) * 6; + total_size = frame_size + OTX2_HEAD_ROOM * 6; rbuf_size = total_size / 6; return ALIGN(rbuf_size, 2048); @@ -1343,7 +1341,8 @@ static int otx2_init_hw_resources(struct otx2_nic *pf) hw->sqpool_cnt = hw->tot_tx_queues; hw->pool_cnt = hw->rqpool_cnt + hw->sqpool_cnt; - pf->max_frs = pf->netdev->mtu + OTX2_ETH_HLEN + OTX2_HW_TIMESTAMP_LEN; + /* Maximum hardware supported transmit length */ + pf->tx_max_pktlen = pf->netdev->max_mtu + OTX2_ETH_HLEN; pf->rbsize = otx2_get_rbuf_size(pf, pf->netdev->mtu); @@ -1807,7 +1806,7 @@ static netdev_tx_t otx2_xmit(struct sk_buff *skb, struct net_device *netdev) /* Check for minimum and maximum packet length */ if (skb->len <= ETH_HLEN || - (!skb_shinfo(skb)->gso_size && skb->len > pf->max_frs)) { + (!skb_shinfo(skb)->gso_size && skb->len > pf->tx_max_pktlen)) { dev_kfree_skb(skb); return NETDEV_TX_OK; } diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.c index 85b1f140d3dd..0ef68fdd1f26 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.c @@ -297,6 +297,7 @@ int otx2_ptp_init(struct otx2_nic *pfvf) error: return err; } +EXPORT_SYMBOL_GPL(otx2_ptp_init); void otx2_ptp_destroy(struct otx2_nic *pfvf) { @@ -309,6 +310,7 @@ void otx2_ptp_destroy(struct otx2_nic *pfvf) kfree(ptp); pfvf->ptp = NULL; } +EXPORT_SYMBOL_GPL(otx2_ptp_destroy); int otx2_ptp_clock_index(struct otx2_nic *pfvf) { @@ -317,6 +319,7 @@ int otx2_ptp_clock_index(struct otx2_nic *pfvf) return ptp_clock_index(pfvf->ptp->ptp_clock); } +EXPORT_SYMBOL_GPL(otx2_ptp_clock_index); int otx2_ptp_tstamp2time(struct otx2_nic *pfvf, u64 tstamp, u64 *tsns) { @@ -327,3 +330,8 @@ int otx2_ptp_tstamp2time(struct otx2_nic *pfvf, u64 tstamp, u64 *tsns) return 0; } +EXPORT_SYMBOL_GPL(otx2_ptp_tstamp2time); + +MODULE_AUTHOR("Sunil Goutham "); +MODULE_DESCRIPTION("Marvell RVU NIC PTP Driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c index 2d2b67319340..0cc6353254bf 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c @@ -181,8 +181,9 @@ static void otx2_set_rxtstamp(struct otx2_nic *pfvf, skb_hwtstamps(skb)->hwtstamp = ns_to_ktime(tsns); } -static void otx2_skb_add_frag(struct otx2_nic *pfvf, struct sk_buff *skb, - u64 iova, int len, struct nix_rx_parse_s *parse) +static bool otx2_skb_add_frag(struct otx2_nic *pfvf, struct sk_buff *skb, + u64 iova, int len, struct nix_rx_parse_s *parse, + int qidx) { struct page *page; int off = 0; @@ -203,11 +204,22 @@ static void otx2_skb_add_frag(struct otx2_nic *pfvf, struct sk_buff *skb, } page = virt_to_page(va); - skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page, - va - page_address(page) + off, len - off, pfvf->rbsize); + if (likely(skb_shinfo(skb)->nr_frags < MAX_SKB_FRAGS)) { + skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page, + va - page_address(page) + off, + len - off, pfvf->rbsize); - otx2_dma_unmap_page(pfvf, iova - OTX2_HEAD_ROOM, - pfvf->rbsize, DMA_FROM_DEVICE); + otx2_dma_unmap_page(pfvf, iova - OTX2_HEAD_ROOM, + pfvf->rbsize, DMA_FROM_DEVICE); + return true; + } + + /* If more than MAX_SKB_FRAGS fragments are received then + * give back those buffer pointers to hardware for reuse. + */ + pfvf->hw_ops->aura_freeptr(pfvf, qidx, iova & ~0x07ULL); + + return false; } static void otx2_set_rxhash(struct otx2_nic *pfvf, @@ -349,9 +361,9 @@ static void otx2_rcv_pkt_handler(struct otx2_nic *pfvf, seg_addr = &sg->seg_addr; seg_size = (void *)sg; for (seg = 0; seg < sg->segs; seg++, seg_addr++) { - otx2_skb_add_frag(pfvf, skb, *seg_addr, seg_size[seg], - parse); - cq->pool_ptrs++; + if (otx2_skb_add_frag(pfvf, skb, *seg_addr, + seg_size[seg], parse, cq->cq_idx)) + cq->pool_ptrs++; } start += sizeof(*sg); } diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h index 5c05774a8d05..f1a04cf9210c 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h @@ -39,9 +39,7 @@ #define RCV_FRAG_LEN(x) \ ((RCV_FRAG_LEN1(x) < 2048) ? 2048 : RCV_FRAG_LEN1(x)) -#define DMA_BUFFER_LEN(x) \ - ((x) - OTX2_HEAD_ROOM - \ - OTX2_DATA_ALIGN(sizeof(struct skb_shared_info))) +#define DMA_BUFFER_LEN(x) ((x) - OTX2_HEAD_ROOM) /* IRQ triggered when NIX_LF_CINTX_CNT[ECOUNT] * is equal to this value. diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c index 980219a7e6fe..e6cb8cd0787d 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c @@ -279,7 +279,6 @@ static void otx2vf_vfaf_mbox_destroy(struct otx2_nic *vf) struct mbox *mbox = &vf->mbox; if (vf->mbox_wq) { - flush_workqueue(vf->mbox_wq); destroy_workqueue(vf->mbox_wq); vf->mbox_wq = NULL; } diff --git a/drivers/net/ethernet/marvell/prestera/prestera_main.c b/drivers/net/ethernet/marvell/prestera/prestera_main.c index b667f560b931..d0d5a229d19d 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_main.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_main.c @@ -338,11 +338,14 @@ static int prestera_port_create(struct prestera_switch *sw, u32 id) goto err_port_init; } + eth_hw_addr_gen(dev, sw->base_mac, port->fp_id); /* firmware requires that port's MAC address consist of the first * 5 bytes of the base MAC address */ - memcpy(dev->dev_addr, sw->base_mac, dev->addr_len - 1); - dev->dev_addr[dev->addr_len - 1] = port->fp_id; + if (memcmp(dev->dev_addr, sw->base_mac, ETH_ALEN - 1)) { + dev_warn(prestera_dev(sw), "Port MAC address wraps for port(%u)\n", id); + dev_addr_mod(dev, 0, sw->base_mac, ETH_ALEN - 1); + } err = prestera_hw_port_mac_set(port, dev->dev_addr); if (err) { diff --git a/drivers/net/ethernet/marvell/pxa168_eth.c b/drivers/net/ethernet/marvell/pxa168_eth.c index 898b513f74e0..6c02e1740609 100644 --- a/drivers/net/ethernet/marvell/pxa168_eth.c +++ b/drivers/net/ethernet/marvell/pxa168_eth.c @@ -389,7 +389,7 @@ static void inverse_every_nibble(unsigned char *mac_addr) * Outputs * return the calculated entry. */ -static u32 hash_function(unsigned char *mac_addr_orig) +static u32 hash_function(const unsigned char *mac_addr_orig) { u32 hash_result; u32 addr0; @@ -434,7 +434,7 @@ static u32 hash_function(unsigned char *mac_addr_orig) * -ENOSPC if table full */ static int add_del_hash_entry(struct pxa168_eth_private *pep, - unsigned char *mac_addr, + const unsigned char *mac_addr, u32 rd, u32 skip, int del) { struct addr_table_entry *entry, *start; @@ -521,7 +521,7 @@ static int add_del_hash_entry(struct pxa168_eth_private *pep, */ static void update_hash_table_mac_address(struct pxa168_eth_private *pep, unsigned char *oaddr, - unsigned char *addr) + const unsigned char *addr) { /* Delete old entry */ if (oaddr) @@ -1436,9 +1436,13 @@ static int pxa168_eth_probe(struct platform_device *pdev) err = of_get_ethdev_address(pdev->dev.of_node, dev); if (err) { + u8 addr[ETH_ALEN]; + /* try reading the mac address, if set by the bootloader */ - pxa168_eth_get_mac_address(dev, dev->dev_addr); - if (!is_valid_ether_addr(dev->dev_addr)) { + pxa168_eth_get_mac_address(dev, addr); + if (is_valid_ether_addr(addr)) { + eth_hw_addr_set(dev, addr); + } else { dev_info(&pdev->dev, "Using random mac address\n"); eth_hw_addr_random(dev); } diff --git a/drivers/net/ethernet/marvell/skge.c b/drivers/net/ethernet/marvell/skge.c index ac48dcca268c..0c864e5bf0a6 100644 --- a/drivers/net/ethernet/marvell/skge.c +++ b/drivers/net/ethernet/marvell/skge.c @@ -3810,6 +3810,7 @@ static struct net_device *skge_devinit(struct skge_hw *hw, int port, { struct skge_port *skge; struct net_device *dev = alloc_etherdev(sizeof(*skge)); + u8 addr[ETH_ALEN]; if (!dev) return NULL; @@ -3862,7 +3863,8 @@ static struct net_device *skge_devinit(struct skge_hw *hw, int port, } /* read the mac address */ - memcpy_fromio(dev->dev_addr, hw->regs + B2_MAC_1 + port*8, ETH_ALEN); + memcpy_fromio(addr, hw->regs + B2_MAC_1 + port*8, ETH_ALEN); + eth_hw_addr_set(dev, addr); return dev; } diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c index 0da18b3f1c01..5abb55191e8e 100644 --- a/drivers/net/ethernet/marvell/sky2.c +++ b/drivers/net/ethernet/marvell/sky2.c @@ -4721,9 +4721,12 @@ static struct net_device *sky2_init_netdev(struct sky2_hw *hw, unsigned port, * 2) from internal registers set by bootloader */ ret = of_get_ethdev_address(hw->pdev->dev.of_node, dev); - if (ret) - memcpy_fromio(dev->dev_addr, hw->regs + B2_MAC_1 + port * 8, - ETH_ALEN); + if (ret) { + u8 addr[ETH_ALEN]; + + memcpy_fromio(addr, hw->regs + B2_MAC_1 + port * 8, ETH_ALEN); + eth_hw_addr_set(dev, addr); + } /* if the address is invalid, use a random value */ if (!is_valid_ether_addr(dev->dev_addr)) { diff --git a/drivers/net/ethernet/mediatek/mtk_star_emac.c b/drivers/net/ethernet/mediatek/mtk_star_emac.c index 1d5dd2015453..89ca7960b225 100644 --- a/drivers/net/ethernet/mediatek/mtk_star_emac.c +++ b/drivers/net/ethernet/mediatek/mtk_star_emac.c @@ -523,7 +523,7 @@ static void mtk_star_dma_resume_tx(struct mtk_star_priv *priv) static void mtk_star_set_mac_addr(struct net_device *ndev) { struct mtk_star_priv *priv = netdev_priv(ndev); - u8 *mac_addr = ndev->dev_addr; + const u8 *mac_addr = ndev->dev_addr; unsigned int high, low; high = mac_addr[0] << 8 | mac_addr[1] << 0; @@ -1544,7 +1544,7 @@ static int mtk_star_probe(struct platform_device *pdev) if (ret) return ret; - ret = eth_platform_get_mac_address(dev, ndev->dev_addr); + ret = platform_get_ethdev_address(dev, ndev); if (ret || !is_valid_ether_addr(ndev->dev_addr)) eth_hw_addr_random(ndev); diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c index 94ead263081f..e10b7b04b894 100644 --- a/drivers/net/ethernet/mellanox/mlx4/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c @@ -2480,7 +2480,6 @@ int mlx4_multi_func_init(struct mlx4_dev *dev) return 0; err_thread: - flush_workqueue(priv->mfunc.master.comm_wq); destroy_workqueue(priv->mfunc.master.comm_wq); err_slaves: while (i--) { @@ -2587,7 +2586,6 @@ void mlx4_multi_func_cleanup(struct mlx4_dev *dev) int i, port; if (mlx4_is_master(dev)) { - flush_workqueue(priv->mfunc.master.comm_wq); destroy_workqueue(priv->mfunc.master.comm_wq); for (i = 0; i < dev->num_slaves; i++) { for (port = 1; port <= MLX4_MAX_PORTS; port++) diff --git a/drivers/net/ethernet/mellanox/mlx4/en_main.c b/drivers/net/ethernet/mellanox/mlx4/en_main.c index 109472d6b61f..f1259bdb1a29 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_main.c @@ -237,7 +237,6 @@ static void mlx4_en_remove(struct mlx4_dev *dev, void *endev_ptr) if (mdev->pndev[i]) mlx4_en_destroy_netdev(mdev->pndev[i]); - flush_workqueue(mdev->workqueue); destroy_workqueue(mdev->workqueue); (void) mlx4_mr_free(dev, &mdev->mr); iounmap(mdev->uar_map); diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 9541f3a920c8..b187c210d4d6 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -4025,8 +4025,8 @@ static int mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id) goto err_params_unregister; pci_save_state(pdev); + devlink_set_features(devlink, DEVLINK_F_RELOAD); devlink_register(devlink); - devlink_reload_enable(devlink); return 0; err_params_unregister: @@ -4135,7 +4135,6 @@ static void mlx4_remove_one(struct pci_dev *pdev) struct devlink *devlink = priv_to_devlink(priv); int active_vfs = 0; - devlink_reload_disable(devlink); devlink_unregister(devlink); if (mlx4_is_slave(dev)) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index 63032cd6efb1..bdb271b604d9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -14,10 +14,10 @@ obj-$(CONFIG_MLX5_CORE) += mlx5_core.o mlx5_core-y := main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \ health.o mcg.o cq.o alloc.o port.o mr.o pd.o \ transobj.o vport.o sriov.o fs_cmd.o fs_core.o pci_irq.o \ - fs_counters.o fs_ft_pool.o rl.o lag.o dev.o events.o wq.o lib/gid.o \ + fs_counters.o fs_ft_pool.o rl.o lag/lag.o dev.o events.o wq.o lib/gid.o \ lib/devcom.o lib/pci_vsc.o lib/dm.o lib/fs_ttc.o diag/fs_tracepoint.o \ diag/fw_tracer.o diag/crdump.o devlink.o diag/rsc_dump.o \ - fw_reset.o qos.o + fw_reset.o qos.o lib/tout.o # # Netdev basic @@ -37,7 +37,7 @@ mlx5_core-$(CONFIG_MLX5_EN_ARFS) += en_arfs.o mlx5_core-$(CONFIG_MLX5_EN_RXNFC) += en_fs_ethtool.o mlx5_core-$(CONFIG_MLX5_CORE_EN_DCB) += en_dcbnl.o en/port_buffer.o mlx5_core-$(CONFIG_PCI_HYPERV_INTERFACE) += en/hv_vhca_stats.o -mlx5_core-$(CONFIG_MLX5_ESWITCH) += lag_mp.o lib/geneve.o lib/port_tun.o \ +mlx5_core-$(CONFIG_MLX5_ESWITCH) += lag/mp.o lag/port_sel.o lib/geneve.o lib/port_tun.o \ en_rep.o en/rep/bond.o en/mod_hdr.o \ en/mapping.o mlx5_core-$(CONFIG_MLX5_CLS_ACT) += en_tc.o en/rep/tc.o en/rep/neigh.o \ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 4dc3a822907a..f71ec4d9d68e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -45,6 +45,7 @@ #include "mlx5_core.h" #include "lib/eq.h" +#include "lib/tout.h" enum { CMD_IF_REV = 5, @@ -225,9 +226,13 @@ static void set_signature(struct mlx5_cmd_work_ent *ent, int csum) static void poll_timeout(struct mlx5_cmd_work_ent *ent) { - unsigned long poll_end = jiffies + msecs_to_jiffies(MLX5_CMD_TIMEOUT_MSEC + 1000); + struct mlx5_core_dev *dev = container_of(ent->cmd, struct mlx5_core_dev, cmd); + u64 cmd_to_ms = mlx5_tout_ms(dev, CMD); + unsigned long poll_end; u8 own; + poll_end = jiffies + msecs_to_jiffies(cmd_to_ms + 1000); + do { own = READ_ONCE(ent->lay->status_own); if (!(own & CMD_OWNER_HW)) { @@ -925,15 +930,18 @@ static void cmd_work_handler(struct work_struct *work) { struct mlx5_cmd_work_ent *ent = container_of(work, struct mlx5_cmd_work_ent, work); struct mlx5_cmd *cmd = ent->cmd; - struct mlx5_core_dev *dev = container_of(cmd, struct mlx5_core_dev, cmd); - unsigned long cb_timeout = msecs_to_jiffies(MLX5_CMD_TIMEOUT_MSEC); + bool poll_cmd = ent->polling; struct mlx5_cmd_layout *lay; + struct mlx5_core_dev *dev; + unsigned long cb_timeout; struct semaphore *sem; unsigned long flags; - bool poll_cmd = ent->polling; int alloc_ret; int cmd_mode; + dev = container_of(cmd, struct mlx5_core_dev, cmd); + cb_timeout = msecs_to_jiffies(mlx5_tout_ms(dev, CMD)); + complete(&ent->handling); sem = ent->page_queue ? &cmd->pages_sem : &cmd->sem; down(sem); @@ -1073,7 +1081,7 @@ static void wait_func_handle_exec_timeout(struct mlx5_core_dev *dev, static int wait_func(struct mlx5_core_dev *dev, struct mlx5_cmd_work_ent *ent) { - unsigned long timeout = msecs_to_jiffies(MLX5_CMD_TIMEOUT_MSEC); + unsigned long timeout = msecs_to_jiffies(mlx5_tout_ms(dev, CMD)); struct mlx5_cmd *cmd = &dev->cmd; int err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c index e8093c4e09d4..a8b84d53dfb0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c @@ -33,6 +33,7 @@ #include #include #include +#include #include "mlx5_core.h" /* intf dev list mutex */ @@ -537,6 +538,16 @@ int mlx5_rescan_drivers_locked(struct mlx5_core_dev *dev) return add_drivers(dev); } +static bool mlx5_same_hw_devs(struct mlx5_core_dev *dev, struct mlx5_core_dev *peer_dev) +{ + u64 fsystem_guid, psystem_guid; + + fsystem_guid = mlx5_query_nic_system_image_guid(dev); + psystem_guid = mlx5_query_nic_system_image_guid(peer_dev); + + return (fsystem_guid && psystem_guid && fsystem_guid == psystem_guid); +} + static u32 mlx5_gen_pci_id(const struct mlx5_core_dev *dev) { return (u32)((pci_domain_nr(dev->pdev->bus) << 16) | @@ -556,7 +567,8 @@ static int next_phys_dev(struct device *dev, const void *data) if (mdev == curr) return 0; - if (mlx5_gen_pci_id(mdev) != mlx5_gen_pci_id(curr)) + if (!mlx5_same_hw_devs(mdev, (struct mlx5_core_dev *)curr) && + mlx5_gen_pci_id(mdev) != mlx5_gen_pci_id(curr)) return 0; return 1; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c index b9a6cea03951..1c98652b244a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c @@ -454,7 +454,8 @@ static int mlx5_devlink_enable_roce_validate(struct devlink *devlink, u32 id, struct mlx5_core_dev *dev = devlink_priv(devlink); bool new_state = val.vbool; - if (new_state && !MLX5_CAP_GEN(dev, roce)) { + if (new_state && !MLX5_CAP_GEN(dev, roce) && + !MLX5_CAP_GEN(dev, roce_rw_supported)) { NL_SET_ERR_MSG_MOD(extack, "Device doesn't support RoCE"); return -EOPNOTSUPP; } @@ -796,6 +797,7 @@ static void mlx5_devlink_traps_unregister(struct devlink *devlink) int mlx5_devlink_register(struct devlink *devlink) { + struct mlx5_core_dev *dev = devlink_priv(devlink); int err; err = devlink_params_register(devlink, mlx5_devlink_params, @@ -813,6 +815,9 @@ int mlx5_devlink_register(struct devlink *devlink) if (err) goto traps_reg_err; + if (!mlx5_core_is_mp_slave(dev)) + devlink_set_features(devlink, DEVLINK_F_RELOAD); + return 0; traps_reg_err: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c index 87d65f6b5310..7841ef6c193c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c @@ -235,6 +235,9 @@ const char *parse_fs_dst(struct trace_seq *p, const char *ret = trace_seq_buffer_ptr(p); switch (dst->type) { + case MLX5_FLOW_DESTINATION_TYPE_UPLINK: + trace_seq_printf(p, "uplink\n"); + break; case MLX5_FLOW_DESTINATION_TYPE_VPORT: trace_seq_printf(p, "vport=%u\n", dst->vport.num); break; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c index f9cf9fb31547..da1bec04efff 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c @@ -1069,7 +1069,6 @@ void mlx5_fw_tracer_destroy(struct mlx5_fw_tracer *tracer) mlx5_fw_tracer_clean_saved_traces_array(tracer); mlx5_fw_tracer_free_strings_db(tracer); mlx5_fw_tracer_destroy_log_buf(tracer); - flush_workqueue(tracer->work_queue); destroy_workqueue(tracer->work_queue); kvfree(tracer); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c index 86e079310ac3..ae52e7f38306 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c @@ -24,7 +24,7 @@ int mlx5e_devlink_port_register(struct mlx5e_priv *priv) if (mlx5_core_is_pf(priv->mdev)) { attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL; - attrs.phys.port_number = PCI_FUNC(priv->mdev->pdev->devfn); + attrs.phys.port_number = mlx5_get_dev_index(priv->mdev); if (MLX5_ESWITCH_MANAGER(priv->mdev)) { mlx5e_devlink_get_port_parent_id(priv->mdev, &ppid); memcpy(attrs.switch_id.id, ppid.id, ppid.id_len); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h index a88a1a48229f..678ffbb48a25 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h @@ -125,15 +125,15 @@ struct mlx5e_ethtool_steering { void mlx5e_ethtool_init_steering(struct mlx5e_priv *priv); void mlx5e_ethtool_cleanup_steering(struct mlx5e_priv *priv); -int mlx5e_ethtool_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd); -int mlx5e_ethtool_get_rxnfc(struct net_device *dev, +int mlx5e_ethtool_set_rxnfc(struct mlx5e_priv *priv, struct ethtool_rxnfc *cmd); +int mlx5e_ethtool_get_rxnfc(struct mlx5e_priv *priv, struct ethtool_rxnfc *info, u32 *rule_locs); #else static inline void mlx5e_ethtool_init_steering(struct mlx5e_priv *priv) { } static inline void mlx5e_ethtool_cleanup_steering(struct mlx5e_priv *priv) { } -static inline int mlx5e_ethtool_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd) +static inline int mlx5e_ethtool_set_rxnfc(struct mlx5e_priv *priv, struct ethtool_rxnfc *cmd) { return -EOPNOTSUPP; } -static inline int mlx5e_ethtool_get_rxnfc(struct net_device *dev, +static inline int mlx5e_ethtool_get_rxnfc(struct mlx5e_priv *priv, struct ethtool_rxnfc *info, u32 *rule_locs) { return -EOPNOTSUPP; } #endif /* CONFIG_MLX5_EN_RXNFC */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/health.h b/drivers/net/ethernet/mellanox/mlx5/core/en/health.h index 018262d0164b..d5b7110a4265 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/health.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/health.h @@ -32,7 +32,6 @@ void mlx5e_reporter_rq_cqe_err(struct mlx5e_rq *rq); void mlx5e_reporter_rx_timeout(struct mlx5e_rq *rq); #define MLX5E_REPORTER_PER_Q_MAX_LEN 256 -#define MLX5E_REPORTER_FLUSH_TIMEOUT_MSEC 2000 struct mlx5e_err_ctx { int (*recover)(void *ctx); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c index 0eb125316fe2..74086eb556ae 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c @@ -6,6 +6,7 @@ #include "txrx.h" #include "devlink.h" #include "ptp.h" +#include "lib/tout.h" static int mlx5e_query_rq_state(struct mlx5_core_dev *dev, u32 rqn, u8 *state) { @@ -32,8 +33,10 @@ out: static int mlx5e_wait_for_icosq_flush(struct mlx5e_icosq *icosq) { - unsigned long exp_time = jiffies + - msecs_to_jiffies(MLX5E_REPORTER_FLUSH_TIMEOUT_MSEC); + struct mlx5_core_dev *dev = icosq->channel->mdev; + unsigned long exp_time; + + exp_time = jiffies + msecs_to_jiffies(mlx5_tout_ms(dev, FLUSH_ON_ERROR)); while (time_before(jiffies, exp_time)) { if (icosq->cc == icosq->pc) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c index bb682fd751c9..4f4bc8726ec4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c @@ -4,11 +4,14 @@ #include "health.h" #include "en/ptp.h" #include "en/devlink.h" +#include "lib/tout.h" static int mlx5e_wait_for_sq_flush(struct mlx5e_txqsq *sq) { - unsigned long exp_time = jiffies + - msecs_to_jiffies(MLX5E_REPORTER_FLUSH_TIMEOUT_MSEC); + struct mlx5_core_dev *dev = sq->mdev; + unsigned long exp_time; + + exp_time = jiffies + msecs_to_jiffies(mlx5_tout_ms(dev, FLUSH_ON_ERROR)); while (time_before(jiffies, exp_time)) { if (sq->cc == sq->pc) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c index 225748a9e52a..740cd6f088b8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c @@ -2141,6 +2141,7 @@ err_ct_tuples_nat_ht: err_ct_tuples_ht: rhashtable_destroy(&ct_priv->zone_ht); err_ct_zone_ht: + mlx5_chains_destroy_global_table(chains, ct_priv->ct_nat); err_ct_nat_tbl: mlx5_chains_destroy_global_table(chains, ct_priv->ct); err_ct_tbl: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c index b7461c17d601..d7e613d0139a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c @@ -10,8 +10,8 @@ #include "en_tc.h" #include "rep/tc.h" #include "rep/neigh.h" -#include "lag.h" -#include "lag_mp.h" +#include "lag/lag.h" +#include "lag/mp.h" struct mlx5e_tc_tun_route_attr { struct net_device *out_dev; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 7a97e0e21fd7..25926e581d18 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -2137,12 +2137,14 @@ int mlx5e_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info, return 0; } - return mlx5e_ethtool_get_rxnfc(dev, info, rule_locs); + return mlx5e_ethtool_get_rxnfc(priv, info, rule_locs); } int mlx5e_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd) { - return mlx5e_ethtool_set_rxnfc(dev, cmd); + struct mlx5e_priv *priv = netdev_priv(dev); + + return mlx5e_ethtool_set_rxnfc(priv, cmd); } static int query_port_status_opcode(struct mlx5_core_dev *mdev, u32 *status_opcode) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c index d226cc5ab1d1..aeff1d972a46 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c @@ -71,12 +71,12 @@ struct mlx5e_l2_hash_node { bool mpfs; }; -static inline int mlx5e_hash_l2(u8 *addr) +static inline int mlx5e_hash_l2(const u8 *addr) { return addr[5]; } -static void mlx5e_add_l2_to_hash(struct hlist_head *hash, u8 *addr) +static void mlx5e_add_l2_to_hash(struct hlist_head *hash, const u8 *addr) { struct mlx5e_l2_hash_node *hn; int ix = mlx5e_hash_l2(addr); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c index 03693fa74a70..81ebf281cdb4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c @@ -937,9 +937,8 @@ static int mlx5e_get_rss_hash_opt(struct mlx5e_priv *priv, return 0; } -int mlx5e_ethtool_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd) +int mlx5e_ethtool_set_rxnfc(struct mlx5e_priv *priv, struct ethtool_rxnfc *cmd) { - struct mlx5e_priv *priv = netdev_priv(dev); int err = 0; switch (cmd->cmd) { @@ -960,10 +959,9 @@ int mlx5e_ethtool_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd) return err; } -int mlx5e_ethtool_get_rxnfc(struct net_device *dev, +int mlx5e_ethtool_get_rxnfc(struct mlx5e_priv *priv, struct ethtool_rxnfc *info, u32 *rule_locs) { - struct mlx5e_priv *priv = netdev_priv(dev); int err = 0; switch (info->cmd) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 40de3aa31050..3af3da214a5b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -68,8 +68,8 @@ #include "lib/fs_chains.h" #include "diag/en_tc_tracepoint.h" #include -#include "lag.h" -#include "lag_mp.h" +#include "lag/lag.h" +#include "lag/mp.h" #define nic_chains(priv) ((priv)->fs.tc.chains) #define MLX5_MH_ACT_SZ MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto) @@ -1893,8 +1893,10 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv, bool needs_mapping, sets_mapping; int err; - if (!mlx5e_is_eswitch_flow(flow)) + if (!mlx5e_is_eswitch_flow(flow)) { + NL_SET_ERR_MSG_MOD(extack, "Match on tunnel is not supported"); return -EOPNOTSUPP; + } needs_mapping = !!flow->attr->chain; sets_mapping = flow_requires_tunnel_mapping(flow->attr->chain, f); @@ -2266,8 +2268,10 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, addr_type = match.key->addr_type; /* the HW doesn't support frag first/later */ - if (match.mask->flags & FLOW_DIS_FIRST_FRAG) + if (match.mask->flags & FLOW_DIS_FIRST_FRAG) { + NL_SET_ERR_MSG_MOD(extack, "Match on frag first/later is not supported"); return -EOPNOTSUPP; + } if (match.mask->flags & FLOW_DIS_IS_FRAGMENT) { MLX5_SET(fte_match_set_lyr_2_4, headers_c, frag, 1); @@ -2434,8 +2438,11 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, switch (ip_proto) { case IPPROTO_ICMP: if (!(MLX5_CAP_GEN(priv->mdev, flex_parser_protocols) & - MLX5_FLEX_PROTO_ICMP)) + MLX5_FLEX_PROTO_ICMP)) { + NL_SET_ERR_MSG_MOD(extack, + "Match on Flex protocols for ICMP is not supported"); return -EOPNOTSUPP; + } MLX5_SET(fte_match_set_misc3, misc_c_3, icmp_type, match.mask->type); MLX5_SET(fte_match_set_misc3, misc_v_3, icmp_type, @@ -2447,8 +2454,11 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, break; case IPPROTO_ICMPV6: if (!(MLX5_CAP_GEN(priv->mdev, flex_parser_protocols) & - MLX5_FLEX_PROTO_ICMPV6)) + MLX5_FLEX_PROTO_ICMPV6)) { + NL_SET_ERR_MSG_MOD(extack, + "Match on Flex protocols for ICMPV6 is not supported"); return -EOPNOTSUPP; + } MLX5_SET(fte_match_set_misc3, misc_c_3, icmpv6_type, match.mask->type); MLX5_SET(fte_match_set_misc3, misc_v_3, icmpv6_type, @@ -2554,15 +2564,19 @@ static int pedit_header_offsets[] = { #define pedit_header(_ph, _htype) ((void *)(_ph) + pedit_header_offsets[_htype]) static int set_pedit_val(u8 hdr_type, u32 mask, u32 val, u32 offset, - struct pedit_headers_action *hdrs) + struct pedit_headers_action *hdrs, + struct netlink_ext_ack *extack) { u32 *curr_pmask, *curr_pval; curr_pmask = (u32 *)(pedit_header(&hdrs->masks, hdr_type) + offset); curr_pval = (u32 *)(pedit_header(&hdrs->vals, hdr_type) + offset); - if (*curr_pmask & mask) /* disallow acting twice on the same location */ + if (*curr_pmask & mask) { /* disallow acting twice on the same location */ + NL_SET_ERR_MSG_MOD(extack, + "curr_pmask and new mask same. Acting twice on same location"); goto out_err; + } *curr_pmask |= mask; *curr_pval |= (val & mask); @@ -2895,7 +2909,7 @@ parse_pedit_to_modify_hdr(struct mlx5e_priv *priv, val = act->mangle.val; offset = act->mangle.offset; - err = set_pedit_val(htype, ~mask, val, offset, &hdrs[cmd]); + err = set_pedit_val(htype, ~mask, val, offset, &hdrs[cmd], extack); if (err) goto out_err; @@ -2914,8 +2928,10 @@ parse_pedit_to_reformat(const struct flow_action_entry *act, u32 mask, val, offset; u32 *p; - if (act->id != FLOW_ACTION_MANGLE) + if (act->id != FLOW_ACTION_MANGLE) { + NL_SET_ERR_MSG_MOD(extack, "Unsupported action id"); return -EOPNOTSUPP; + } if (act->mangle.htype != FLOW_ACT_MANGLE_HDR_TYPE_ETH) { NL_SET_ERR_MSG_MOD(extack, "Only Ethernet modification is supported"); @@ -3431,12 +3447,16 @@ parse_tc_nic_actions(struct mlx5e_priv *priv, u32 action = 0; int err, i; - if (!flow_action_has_entries(flow_action)) + if (!flow_action_has_entries(flow_action)) { + NL_SET_ERR_MSG_MOD(extack, "Flow action doesn't have any entries"); return -EINVAL; + } if (!flow_action_hw_stats_check(flow_action, extack, - FLOW_ACTION_HW_STATS_DELAYED_BIT)) + FLOW_ACTION_HW_STATS_DELAYED_BIT)) { + NL_SET_ERR_MSG_MOD(extack, "Flow action HW stats type is not supported"); return -EOPNOTSUPP; + } nic_attr = attr->nic_attr; nic_attr->flow_tag = MLX5_FS_DEFAULT_FLOW_TAG; @@ -3526,7 +3546,8 @@ parse_tc_nic_actions(struct mlx5e_priv *priv, flow_flag_set(flow, CT); break; default: - NL_SET_ERR_MSG_MOD(extack, "The offload action is not supported"); + NL_SET_ERR_MSG_MOD(extack, + "The offload action is not supported in NIC action"); return -EOPNOTSUPP; } } @@ -3564,19 +3585,25 @@ static bool is_merged_eswitch_vfs(struct mlx5e_priv *priv, static int parse_tc_vlan_action(struct mlx5e_priv *priv, const struct flow_action_entry *act, struct mlx5_esw_flow_attr *attr, - u32 *action) + u32 *action, + struct netlink_ext_ack *extack) { u8 vlan_idx = attr->total_vlan; - if (vlan_idx >= MLX5_FS_VLAN_DEPTH) + if (vlan_idx >= MLX5_FS_VLAN_DEPTH) { + NL_SET_ERR_MSG_MOD(extack, "Total vlans used is greater than supported"); return -EOPNOTSUPP; + } switch (act->id) { case FLOW_ACTION_VLAN_POP: if (vlan_idx) { if (!mlx5_eswitch_vlan_actions_supported(priv->mdev, - MLX5_FS_VLAN_DEPTH)) + MLX5_FS_VLAN_DEPTH)) { + NL_SET_ERR_MSG_MOD(extack, + "vlan pop action is not supported"); return -EOPNOTSUPP; + } *action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_POP_2; } else { @@ -3592,20 +3619,27 @@ static int parse_tc_vlan_action(struct mlx5e_priv *priv, if (vlan_idx) { if (!mlx5_eswitch_vlan_actions_supported(priv->mdev, - MLX5_FS_VLAN_DEPTH)) + MLX5_FS_VLAN_DEPTH)) { + NL_SET_ERR_MSG_MOD(extack, + "vlan push action is not supported for vlan depth > 1"); return -EOPNOTSUPP; + } *action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH_2; } else { if (!mlx5_eswitch_vlan_actions_supported(priv->mdev, 1) && (act->vlan.proto != htons(ETH_P_8021Q) || - act->vlan.prio)) + act->vlan.prio)) { + NL_SET_ERR_MSG_MOD(extack, + "vlan push action is not supported"); return -EOPNOTSUPP; + } *action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH; } break; default: + NL_SET_ERR_MSG_MOD(extack, "Unexpected action id for VLAN"); return -EINVAL; } @@ -3639,7 +3673,8 @@ static struct net_device *get_fdb_out_dev(struct net_device *uplink_dev, static int add_vlan_push_action(struct mlx5e_priv *priv, struct mlx5_flow_attr *attr, struct net_device **out_dev, - u32 *action) + u32 *action, + struct netlink_ext_ack *extack) { struct net_device *vlan_dev = *out_dev; struct flow_action_entry vlan_act = { @@ -3650,7 +3685,7 @@ static int add_vlan_push_action(struct mlx5e_priv *priv, }; int err; - err = parse_tc_vlan_action(priv, &vlan_act, attr->esw_attr, action); + err = parse_tc_vlan_action(priv, &vlan_act, attr->esw_attr, action, extack); if (err) return err; @@ -3661,14 +3696,15 @@ static int add_vlan_push_action(struct mlx5e_priv *priv, return -ENODEV; if (is_vlan_dev(*out_dev)) - err = add_vlan_push_action(priv, attr, out_dev, action); + err = add_vlan_push_action(priv, attr, out_dev, action, extack); return err; } static int add_vlan_pop_action(struct mlx5e_priv *priv, struct mlx5_flow_attr *attr, - u32 *action) + u32 *action, + struct netlink_ext_ack *extack) { struct flow_action_entry vlan_act = { .id = FLOW_ACTION_VLAN_POP, @@ -3678,7 +3714,7 @@ static int add_vlan_pop_action(struct mlx5e_priv *priv, nest_level = attr->parse_attr->filter_dev->lower_level - priv->netdev->lower_level; while (nest_level--) { - err = parse_tc_vlan_action(priv, &vlan_act, attr->esw_attr, action); + err = parse_tc_vlan_action(priv, &vlan_act, attr->esw_attr, action, extack); if (err) return err; } @@ -3800,12 +3836,16 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, int err, i, if_count = 0; bool mpls_push = false; - if (!flow_action_has_entries(flow_action)) + if (!flow_action_has_entries(flow_action)) { + NL_SET_ERR_MSG_MOD(extack, "Flow action doesn't have any entries"); return -EINVAL; + } if (!flow_action_hw_stats_check(flow_action, extack, - FLOW_ACTION_HW_STATS_DELAYED_BIT)) + FLOW_ACTION_HW_STATS_DELAYED_BIT)) { + NL_SET_ERR_MSG_MOD(extack, "Flow action HW stats type is not supported"); return -EOPNOTSUPP; + } esw_attr = attr->esw_attr; parse_attr = attr->parse_attr; @@ -3954,14 +3994,14 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, if (is_vlan_dev(out_dev)) { err = add_vlan_push_action(priv, attr, &out_dev, - &action); + &action, extack); if (err) return err; } if (is_vlan_dev(parse_attr->filter_dev)) { err = add_vlan_pop_action(priv, attr, - &action); + &action, extack); if (err) return err; } @@ -4010,10 +4050,13 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, break; case FLOW_ACTION_TUNNEL_ENCAP: info = act->tunnel; - if (info) + if (info) { encap = true; - else + } else { + NL_SET_ERR_MSG_MOD(extack, + "Zero tunnel attributes is not supported"); return -EOPNOTSUPP; + } break; case FLOW_ACTION_VLAN_PUSH: @@ -4027,7 +4070,7 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, act, parse_attr, hdrs, &action, extack); } else { - err = parse_tc_vlan_action(priv, act, esw_attr, &action); + err = parse_tc_vlan_action(priv, act, esw_attr, &action, extack); } if (err) return err; @@ -4081,7 +4124,8 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, flow_flag_set(flow, SAMPLE); break; default: - NL_SET_ERR_MSG_MOD(extack, "The offload action is not supported"); + NL_SET_ERR_MSG_MOD(extack, + "The offload action is not supported in FDB action"); return -EOPNOTSUPP; } } @@ -4755,8 +4799,10 @@ static int scan_tc_matchall_fdb_actions(struct mlx5e_priv *priv, return -EOPNOTSUPP; } - if (!flow_action_basic_hw_stats_check(flow_action, extack)) + if (!flow_action_basic_hw_stats_check(flow_action, extack)) { + NL_SET_ERR_MSG_MOD(extack, "Flow action HW stats type is not supported"); return -EOPNOTSUPP; + } flow_action_for_each(i, act, flow_action) { switch (act->id) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c index ed72246d1d83..588622ba38c1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c @@ -677,6 +677,10 @@ mlx5_esw_bridge_egress_flow_create(u16 vport_num, u16 esw_owner_vhca_id, const u if (!rule_spec) return ERR_PTR(-ENOMEM); + if (MLX5_CAP_ESW_FLOWTABLE(bridge->br_offloads->esw->dev, flow_source) && + vport_num == MLX5_VPORT_UPLINK) + rule_spec->flow_context.flow_source = + MLX5_FLOW_CONTEXT_FLOW_SOURCE_LOCAL_VPORT; rule_spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS; dmac_v = MLX5_ADDR_OF(fte_match_param, rule_spec->match_value, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c index 20af557ae30c..7f9b96d9537e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c @@ -36,7 +36,7 @@ static struct devlink_port *mlx5_esw_dl_port_alloc(struct mlx5_eswitch *esw, u16 return NULL; mlx5_esw_get_port_parent_id(dev, &ppid); - pfnum = PCI_FUNC(dev->pdev->devfn); + pfnum = mlx5_get_dev_index(dev); external = mlx5_core_is_ecpf_esw_manager(dev); if (external) controller_num = dev->priv.eswitch->offloads.host_number + 1; @@ -149,7 +149,7 @@ int mlx5_esw_devlink_sf_port_register(struct mlx5_eswitch *esw, struct devlink_p if (IS_ERR(vport)) return PTR_ERR(vport); - pfnum = PCI_FUNC(dev->pdev->devfn); + pfnum = mlx5_get_dev_index(dev); mlx5_esw_get_port_parent_id(dev, &ppid); memcpy(dl_port->attrs.switch_id.id, &ppid.id[0], ppid.id_len); dl_port->attrs.switch_id.id_len = ppid.id_len; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index 7461aafb321e..28467f11f04b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -433,7 +433,7 @@ enum mlx5_flow_match_level { }; /* current maximum for flow based vport multicasting */ -#define MLX5_MAX_FLOW_FWD_VPORTS 2 +#define MLX5_MAX_FLOW_FWD_VPORTS 32 enum { MLX5_ESW_DEST_ENCAP = BIT(0), diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index ca7e31a1a431..0ef126fd6a8e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -482,12 +482,12 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw, struct mlx5_flow_spec *spec, struct mlx5_flow_attr *attr) { - struct mlx5_flow_destination dest[MLX5_MAX_FLOW_FWD_VPORTS + 1] = {}; struct mlx5_flow_act flow_act = { .flags = FLOW_ACT_NO_APPEND, }; struct mlx5_esw_flow_attr *esw_attr = attr->esw_attr; struct mlx5_fs_chains *chains = esw_chains(esw); bool split = !!(esw_attr->split_count); struct mlx5_vport_tbl_attr fwd_attr; + struct mlx5_flow_destination *dest; struct mlx5_flow_handle *rule; struct mlx5_flow_table *fdb; int i = 0; @@ -495,6 +495,10 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw, if (esw->mode != MLX5_ESWITCH_OFFLOADS) return ERR_PTR(-EOPNOTSUPP); + dest = kcalloc(MLX5_MAX_FLOW_FWD_VPORTS + 1, sizeof(*dest), GFP_KERNEL); + if (!dest) + return ERR_PTR(-ENOMEM); + flow_act.action = attr->action; /* if per flow vlan pop/push is emulated, don't set that into the firmware */ if (!mlx5_eswitch_vlan_actions_supported(esw->dev, 1)) @@ -574,6 +578,7 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw, else atomic64_inc(&esw->offloads.num_flows); + kfree(dest); return rule; err_add_rule: @@ -584,6 +589,7 @@ err_add_rule: err_esw_get: esw_cleanup_dests(esw, attr); err_create_goto_table: + kfree(dest); return rule; } @@ -592,16 +598,20 @@ mlx5_eswitch_add_fwd_rule(struct mlx5_eswitch *esw, struct mlx5_flow_spec *spec, struct mlx5_flow_attr *attr) { - struct mlx5_flow_destination dest[MLX5_MAX_FLOW_FWD_VPORTS + 1] = {}; struct mlx5_flow_act flow_act = { .flags = FLOW_ACT_NO_APPEND, }; struct mlx5_esw_flow_attr *esw_attr = attr->esw_attr; struct mlx5_fs_chains *chains = esw_chains(esw); struct mlx5_vport_tbl_attr fwd_attr; + struct mlx5_flow_destination *dest; struct mlx5_flow_table *fast_fdb; struct mlx5_flow_table *fwd_fdb; struct mlx5_flow_handle *rule; int i, err = 0; + dest = kcalloc(MLX5_MAX_FLOW_FWD_VPORTS + 1, sizeof(*dest), GFP_KERNEL); + if (!dest) + return ERR_PTR(-ENOMEM); + fast_fdb = mlx5_chains_get_table(chains, attr->chain, attr->prio, 0); if (IS_ERR(fast_fdb)) { rule = ERR_CAST(fast_fdb); @@ -654,6 +664,7 @@ mlx5_eswitch_add_fwd_rule(struct mlx5_eswitch *esw, atomic64_inc(&esw->offloads.num_flows); + kfree(dest); return rule; err_chain_src_rewrite: esw_put_dest_tables_loop(esw, attr, 0, i); @@ -661,6 +672,7 @@ err_chain_src_rewrite: err_get_fwd: mlx5_chains_put_table(chains, attr->chain, attr->prio, 0); err_get_fast: + kfree(dest); return rule; } @@ -2798,7 +2810,7 @@ u32 mlx5_esw_match_metadata_alloc(struct mlx5_eswitch *esw) int id; /* Only 4 bits of pf_num */ - pf_num = PCI_FUNC(esw->dev->pdev->devfn); + pf_num = mlx5_get_dev_index(esw->dev); if (pf_num > max_pf_num) return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c index 7db8df64a60e..750b21124a1a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c @@ -185,6 +185,20 @@ static int mlx5_cmd_set_slave_root_fdb(struct mlx5_core_dev *master, return mlx5_cmd_exec(slave, in, sizeof(in), out, sizeof(out)); } +static int +mlx5_cmd_stub_destroy_match_definer(struct mlx5_flow_root_namespace *ns, + int definer_id) +{ + return 0; +} + +static int +mlx5_cmd_stub_create_match_definer(struct mlx5_flow_root_namespace *ns, + u16 format_id, u32 *match_mask) +{ + return 0; +} + static int mlx5_cmd_update_root_ft(struct mlx5_flow_root_namespace *ns, struct mlx5_flow_table *ft, u32 underlay_qpn, bool disconnect) @@ -563,8 +577,8 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev, case MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE: id = dst->dest_attr.ft->id; break; + case MLX5_FLOW_DESTINATION_TYPE_UPLINK: case MLX5_FLOW_DESTINATION_TYPE_VPORT: - id = dst->dest_attr.vport.num; MLX5_SET(dest_format_struct, in_dests, destination_eswitch_owner_vhca_id_valid, !!(dst->dest_attr.vport.flags & @@ -572,6 +586,12 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev, MLX5_SET(dest_format_struct, in_dests, destination_eswitch_owner_vhca_id, dst->dest_attr.vport.vhca_id); + if (type == MLX5_FLOW_DESTINATION_TYPE_UPLINK) { + /* destination_id is reserved */ + id = 0; + break; + } + id = dst->dest_attr.vport.num; if (extended_dest && dst->dest_attr.vport.pkt_reformat) { MLX5_SET(dest_format_struct, in_dests, @@ -909,6 +929,45 @@ static void mlx5_cmd_modify_header_dealloc(struct mlx5_flow_root_namespace *ns, mlx5_cmd_exec_in(dev, dealloc_modify_header_context, in); } +static int mlx5_cmd_destroy_match_definer(struct mlx5_flow_root_namespace *ns, + int definer_id) +{ + u32 in[MLX5_ST_SZ_DW(general_obj_in_cmd_hdr)] = {}; + u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)]; + + MLX5_SET(general_obj_in_cmd_hdr, in, opcode, + MLX5_CMD_OP_DESTROY_GENERAL_OBJECT); + MLX5_SET(general_obj_in_cmd_hdr, in, obj_type, + MLX5_OBJ_TYPE_MATCH_DEFINER); + MLX5_SET(general_obj_in_cmd_hdr, in, obj_id, definer_id); + + return mlx5_cmd_exec(ns->dev, in, sizeof(in), out, sizeof(out)); +} + +static int mlx5_cmd_create_match_definer(struct mlx5_flow_root_namespace *ns, + u16 format_id, u32 *match_mask) +{ + u32 out[MLX5_ST_SZ_DW(create_match_definer_out)] = {}; + u32 in[MLX5_ST_SZ_DW(create_match_definer_in)] = {}; + struct mlx5_core_dev *dev = ns->dev; + void *ptr; + int err; + + MLX5_SET(create_match_definer_in, in, general_obj_in_cmd_hdr.opcode, + MLX5_CMD_OP_CREATE_GENERAL_OBJECT); + MLX5_SET(create_match_definer_in, in, general_obj_in_cmd_hdr.obj_type, + MLX5_OBJ_TYPE_MATCH_DEFINER); + + ptr = MLX5_ADDR_OF(create_match_definer_in, in, obj_context); + MLX5_SET(match_definer, ptr, format_id, format_id); + + ptr = MLX5_ADDR_OF(match_definer, ptr, match_mask); + memcpy(ptr, match_mask, MLX5_FLD_SZ_BYTES(match_definer, match_mask)); + + err = mlx5_cmd_exec_inout(dev, create_match_definer, in, out); + return err ? err : MLX5_GET(general_obj_out_cmd_hdr, out, obj_id); +} + static const struct mlx5_flow_cmds mlx5_flow_cmds = { .create_flow_table = mlx5_cmd_create_flow_table, .destroy_flow_table = mlx5_cmd_destroy_flow_table, @@ -923,6 +982,8 @@ static const struct mlx5_flow_cmds mlx5_flow_cmds = { .packet_reformat_dealloc = mlx5_cmd_packet_reformat_dealloc, .modify_header_alloc = mlx5_cmd_modify_header_alloc, .modify_header_dealloc = mlx5_cmd_modify_header_dealloc, + .create_match_definer = mlx5_cmd_create_match_definer, + .destroy_match_definer = mlx5_cmd_destroy_match_definer, .set_peer = mlx5_cmd_stub_set_peer, .create_ns = mlx5_cmd_stub_create_ns, .destroy_ns = mlx5_cmd_stub_destroy_ns, @@ -942,6 +1003,8 @@ static const struct mlx5_flow_cmds mlx5_flow_cmd_stubs = { .packet_reformat_dealloc = mlx5_cmd_stub_packet_reformat_dealloc, .modify_header_alloc = mlx5_cmd_stub_modify_header_alloc, .modify_header_dealloc = mlx5_cmd_stub_modify_header_dealloc, + .create_match_definer = mlx5_cmd_stub_create_match_definer, + .destroy_match_definer = mlx5_cmd_stub_destroy_match_definer, .set_peer = mlx5_cmd_stub_set_peer, .create_ns = mlx5_cmd_stub_create_ns, .destroy_ns = mlx5_cmd_stub_destroy_ns, @@ -969,6 +1032,7 @@ const struct mlx5_flow_cmds *mlx5_fs_cmd_get_default(enum fs_flow_table_type typ case FS_FT_NIC_TX: case FS_FT_RDMA_RX: case FS_FT_RDMA_TX: + case FS_FT_PORT_SEL: return mlx5_fs_cmd_get_fw_cmds(); default: return mlx5_fs_cmd_get_stub_cmds(); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h index 5ecd33cdc087..220ec632d35a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h @@ -97,6 +97,10 @@ struct mlx5_flow_cmds { int (*create_ns)(struct mlx5_flow_root_namespace *ns); int (*destroy_ns)(struct mlx5_flow_root_namespace *ns); + int (*create_match_definer)(struct mlx5_flow_root_namespace *ns, + u16 format_id, u32 *match_mask); + int (*destroy_match_definer)(struct mlx5_flow_root_namespace *ns, + int definer_id); }; int mlx5_cmd_fc_alloc(struct mlx5_core_dev *dev, u32 *id); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index fe501ba88bea..873efde0d458 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -2191,6 +2191,10 @@ struct mlx5_flow_namespace *mlx5_get_flow_namespace(struct mlx5_core_dev *dev, if (steering->fdb_root_ns) return &steering->fdb_root_ns->ns; return NULL; + case MLX5_FLOW_NAMESPACE_PORT_SEL: + if (steering->port_sel_root_ns) + return &steering->port_sel_root_ns->ns; + return NULL; case MLX5_FLOW_NAMESPACE_SNIFFER_RX: if (steering->sniffer_rx_root_ns) return &steering->sniffer_rx_root_ns->ns; @@ -2596,6 +2600,7 @@ void mlx5_cleanup_fs(struct mlx5_core_dev *dev) steering->fdb_root_ns = NULL; kfree(steering->fdb_sub_ns); steering->fdb_sub_ns = NULL; + cleanup_root_ns(steering->port_sel_root_ns); cleanup_root_ns(steering->sniffer_rx_root_ns); cleanup_root_ns(steering->sniffer_tx_root_ns); cleanup_root_ns(steering->rdma_rx_root_ns); @@ -2634,6 +2639,21 @@ static int init_sniffer_rx_root_ns(struct mlx5_flow_steering *steering) return PTR_ERR_OR_ZERO(prio); } +#define PORT_SEL_NUM_LEVELS 3 +static int init_port_sel_root_ns(struct mlx5_flow_steering *steering) +{ + struct fs_prio *prio; + + steering->port_sel_root_ns = create_root_ns(steering, FS_FT_PORT_SEL); + if (!steering->port_sel_root_ns) + return -ENOMEM; + + /* Create single prio */ + prio = fs_create_prio(&steering->port_sel_root_ns->ns, 0, + PORT_SEL_NUM_LEVELS); + return PTR_ERR_OR_ZERO(prio); +} + static int init_rdma_rx_root_ns(struct mlx5_flow_steering *steering) { int err; @@ -3020,6 +3040,12 @@ int mlx5_init_fs(struct mlx5_core_dev *dev) goto err; } + if (MLX5_CAP_FLOWTABLE_PORT_SELECTION(dev, ft_support)) { + err = init_port_sel_root_ns(steering); + if (err) + goto err; + } + if (MLX5_CAP_FLOWTABLE_RDMA_RX(dev, ft_support) && MLX5_CAP_FLOWTABLE_RDMA_RX(dev, table_miss_action_domain)) { err = init_rdma_rx_root_ns(steering); @@ -3224,6 +3250,52 @@ void mlx5_packet_reformat_dealloc(struct mlx5_core_dev *dev, } EXPORT_SYMBOL(mlx5_packet_reformat_dealloc); +int mlx5_get_match_definer_id(struct mlx5_flow_definer *definer) +{ + return definer->id; +} + +struct mlx5_flow_definer * +mlx5_create_match_definer(struct mlx5_core_dev *dev, + enum mlx5_flow_namespace_type ns_type, u16 format_id, + u32 *match_mask) +{ + struct mlx5_flow_root_namespace *root; + struct mlx5_flow_definer *definer; + int id; + + root = get_root_namespace(dev, ns_type); + if (!root) + return ERR_PTR(-EOPNOTSUPP); + + definer = kzalloc(sizeof(*definer), GFP_KERNEL); + if (!definer) + return ERR_PTR(-ENOMEM); + + definer->ns_type = ns_type; + id = root->cmds->create_match_definer(root, format_id, match_mask); + if (id < 0) { + mlx5_core_warn(root->dev, "Failed to create match definer (%d)\n", id); + kfree(definer); + return ERR_PTR(id); + } + definer->id = id; + return definer; +} + +void mlx5_destroy_match_definer(struct mlx5_core_dev *dev, + struct mlx5_flow_definer *definer) +{ + struct mlx5_flow_root_namespace *root; + + root = get_root_namespace(dev, definer->ns_type); + if (WARN_ON(!root)) + return; + + root->cmds->destroy_match_definer(root, definer->id); + kfree(definer); +} + int mlx5_flow_namespace_set_peer(struct mlx5_flow_root_namespace *ns, struct mlx5_flow_root_namespace *peer_ns) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h index 98240badc342..7711db245c63 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -49,6 +49,11 @@ #define FDB_TC_MAX_PRIO 16 #define FDB_TC_LEVELS_PER_PRIO 2 +struct mlx5_flow_definer { + enum mlx5_flow_namespace_type ns_type; + u32 id; +}; + struct mlx5_modify_hdr { enum mlx5_flow_namespace_type ns_type; union { @@ -97,7 +102,8 @@ enum fs_flow_table_type { FS_FT_SNIFFER_TX = 0X6, FS_FT_RDMA_RX = 0X7, FS_FT_RDMA_TX = 0X8, - FS_FT_MAX_TYPE = FS_FT_RDMA_TX, + FS_FT_PORT_SEL = 0X9, + FS_FT_MAX_TYPE = FS_FT_PORT_SEL, }; enum fs_flow_table_op_mod { @@ -129,6 +135,7 @@ struct mlx5_flow_steering { struct mlx5_flow_root_namespace *rdma_rx_root_ns; struct mlx5_flow_root_namespace *rdma_tx_root_ns; struct mlx5_flow_root_namespace *egress_root_ns; + struct mlx5_flow_root_namespace *port_sel_root_ns; int esw_egress_acl_vports; int esw_ingress_acl_vports; }; @@ -341,7 +348,8 @@ struct mlx5_flow_root_namespace *find_root(struct fs_node *node); (type == FS_FT_SNIFFER_TX) ? MLX5_CAP_FLOWTABLE_SNIFFER_TX(mdev, cap) : \ (type == FS_FT_RDMA_RX) ? MLX5_CAP_FLOWTABLE_RDMA_RX(mdev, cap) : \ (type == FS_FT_RDMA_TX) ? MLX5_CAP_FLOWTABLE_RDMA_TX(mdev, cap) : \ - (BUILD_BUG_ON_ZERO(FS_FT_RDMA_TX != FS_FT_MAX_TYPE))\ + (type == FS_FT_PORT_SEL) ? MLX5_CAP_FLOWTABLE_PORT_SELECTION(mdev, cap) : \ + (BUILD_BUG_ON_ZERO(FS_FT_PORT_SEL != FS_FT_MAX_TYPE))\ ) #endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c index 016d26f809a5..1037e3629e7e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c @@ -35,6 +35,7 @@ #include #include "mlx5_core.h" #include "../../mlxfw/mlxfw.h" +#include "lib/tout.h" #include "accel/tls.h" enum { @@ -148,6 +149,12 @@ int mlx5_query_hca_caps(struct mlx5_core_dev *dev) if (err) return err; + if (MLX5_CAP_GEN(dev, port_selection_cap)) { + err = mlx5_core_get_caps(dev, MLX5_CAP_PORT_SELECTION); + if (err) + return err; + } + if (MLX5_CAP_GEN(dev, hca_cap_2)) { err = mlx5_core_get_caps(dev, MLX5_CAP_GENERAL_2); if (err) @@ -317,10 +324,9 @@ int mlx5_cmd_force_teardown_hca(struct mlx5_core_dev *dev) return 0; } -#define MLX5_FAST_TEARDOWN_WAIT_MS 3000 int mlx5_cmd_fast_teardown_hca(struct mlx5_core_dev *dev) { - unsigned long end, delay_ms = MLX5_FAST_TEARDOWN_WAIT_MS; + unsigned long end, delay_ms = mlx5_tout_ms(dev, TEARDOWN); u32 out[MLX5_ST_SZ_DW(teardown_hca_out)] = {}; u32 in[MLX5_ST_SZ_DW(teardown_hca_in)] = {}; int state; @@ -618,17 +624,18 @@ static void mlx5_fsm_release(struct mlxfw_dev *mlxfw_dev, u32 fwhandle) fwhandle, 0); } -#define MLX5_FSM_REACTIVATE_TOUT 5000 /* msecs */ static int mlx5_fsm_reactivate(struct mlxfw_dev *mlxfw_dev, u8 *status) { - unsigned long exp_time = jiffies + msecs_to_jiffies(MLX5_FSM_REACTIVATE_TOUT); struct mlx5_mlxfw_dev *mlx5_mlxfw_dev = container_of(mlxfw_dev, struct mlx5_mlxfw_dev, mlxfw_dev); struct mlx5_core_dev *dev = mlx5_mlxfw_dev->mlx5_core_dev; u32 out[MLX5_ST_SZ_DW(mirc_reg)]; u32 in[MLX5_ST_SZ_DW(mirc_reg)]; + unsigned long exp_time; int err; + exp_time = jiffies + msecs_to_jiffies(mlx5_tout_ms(dev, FSM_REACTIVATE)); + if (!MLX5_CAP_MCAM_REG2(dev, mirc)) return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c index 106b50e42b46..0b0234f9d694 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c @@ -3,6 +3,7 @@ #include "fw_reset.h" #include "diag/fw_tracer.h" +#include "lib/tout.h" enum { MLX5_FW_RESET_FLAGS_RESET_REQUESTED, @@ -228,8 +229,6 @@ static void mlx5_sync_reset_request_event(struct work_struct *work) mlx5_core_warn(dev, "PCI Sync FW Update Reset Ack. Device reset is expected.\n"); } -#define MLX5_PCI_LINK_UP_TIMEOUT 2000 - static int mlx5_pci_link_toggle(struct mlx5_core_dev *dev) { struct pci_bus *bridge_bus = dev->pdev->bus; @@ -286,7 +285,7 @@ static int mlx5_pci_link_toggle(struct mlx5_core_dev *dev) goto restore; } - timeout = jiffies + msecs_to_jiffies(MLX5_PCI_LINK_UP_TIMEOUT); + timeout = jiffies + msecs_to_jiffies(mlx5_tout_ms(dev, PCI_TOGGLE)); do { err = pci_read_config_word(bridge, cap + PCI_EXP_LNKSTA, ®16); if (err) @@ -299,8 +298,8 @@ static int mlx5_pci_link_toggle(struct mlx5_core_dev *dev) if (reg16 & PCI_EXP_LNKSTA_DLLLA) { mlx5_core_info(dev, "PCI Link up\n"); } else { - mlx5_core_err(dev, "PCI link not ready (0x%04x) after %d ms\n", - reg16, MLX5_PCI_LINK_UP_TIMEOUT); + mlx5_core_err(dev, "PCI link not ready (0x%04x) after %llu ms\n", + reg16, mlx5_tout_ms(dev, PCI_TOGGLE)); err = -ETIMEDOUT; } @@ -395,16 +394,16 @@ static int fw_reset_event_notifier(struct notifier_block *nb, unsigned long acti return NOTIFY_OK; } -#define MLX5_FW_RESET_TIMEOUT_MSEC 5000 int mlx5_fw_reset_wait_reset_done(struct mlx5_core_dev *dev) { - unsigned long timeout = msecs_to_jiffies(MLX5_FW_RESET_TIMEOUT_MSEC); + unsigned long pci_sync_update_timeout = mlx5_tout_ms(dev, PCI_SYNC_UPDATE); + unsigned long timeout = msecs_to_jiffies(pci_sync_update_timeout); struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset; int err; if (!wait_for_completion_timeout(&fw_reset->done, timeout)) { - mlx5_core_warn(dev, "FW sync reset timeout after %d seconds\n", - MLX5_FW_RESET_TIMEOUT_MSEC / 1000); + mlx5_core_warn(dev, "FW sync reset timeout after %lu seconds\n", + pci_sync_update_timeout / 1000); err = -ETIMEDOUT; goto out; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index 037e18dd4be0..6a4dd7f78958 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -40,10 +40,10 @@ #include "lib/eq.h" #include "lib/mlx5.h" #include "lib/pci_vsc.h" +#include "lib/tout.h" #include "diag/fw_tracer.h" enum { - MLX5_HEALTH_POLL_INTERVAL = 2 * HZ, MAX_MISSES = 3, }; @@ -219,11 +219,9 @@ unlock: mutex_unlock(&dev->intf_state_mutex); } -#define MLX5_CRDUMP_WAIT_MS 60000 -#define MLX5_FW_RESET_WAIT_MS 1000 void mlx5_error_sw_reset(struct mlx5_core_dev *dev) { - unsigned long end, delay_ms = MLX5_FW_RESET_WAIT_MS; + unsigned long end, delay_ms = mlx5_tout_ms(dev, PCI_TOGGLE); int lock = -EBUSY; mutex_lock(&dev->intf_state_mutex); @@ -237,7 +235,7 @@ void mlx5_error_sw_reset(struct mlx5_core_dev *dev) lock = lock_sem_sw_reset(dev, true); if (lock == -EBUSY) { - delay_ms = MLX5_CRDUMP_WAIT_MS; + delay_ms = mlx5_tout_ms(dev, FULL_CRDUMP); goto recover_from_sw_reset; } /* Execute SW reset */ @@ -307,13 +305,11 @@ static void mlx5_handle_bad_state(struct mlx5_core_dev *dev) mlx5_disable_device(dev); } -/* How much time to wait until health resetting the driver (in msecs) */ -#define MLX5_RECOVERY_WAIT_MSECS 60000 int mlx5_health_wait_pci_up(struct mlx5_core_dev *dev) { unsigned long end; - end = jiffies + msecs_to_jiffies(MLX5_RECOVERY_WAIT_MSECS); + end = jiffies + msecs_to_jiffies(mlx5_tout_ms(dev, FW_RESET)); while (sensor_pci_not_working(dev)) { if (time_after(jiffies, end)) return -ETIMEDOUT; @@ -674,13 +670,13 @@ static void mlx5_fw_reporters_destroy(struct mlx5_core_dev *dev) devlink_health_reporter_destroy(health->fw_fatal_reporter); } -static unsigned long get_next_poll_jiffies(void) +static unsigned long get_next_poll_jiffies(struct mlx5_core_dev *dev) { unsigned long next; get_random_bytes(&next, sizeof(next)); next %= HZ; - next += jiffies + MLX5_HEALTH_POLL_INTERVAL; + next += jiffies + msecs_to_jiffies(mlx5_tout_ms(dev, HEALTH_POLL_INTERVAL)); return next; } @@ -740,11 +736,12 @@ static void poll_health(struct timer_list *t) queue_work(health->wq, &health->report_work); out: - mod_timer(&health->timer, get_next_poll_jiffies()); + mod_timer(&health->timer, get_next_poll_jiffies(dev)); } void mlx5_start_health_poll(struct mlx5_core_dev *dev) { + u64 poll_interval_ms = mlx5_tout_ms(dev, HEALTH_POLL_INTERVAL); struct mlx5_core_health *health = &dev->priv.health; timer_setup(&health->timer, poll_health, 0); @@ -753,7 +750,7 @@ void mlx5_start_health_poll(struct mlx5_core_dev *dev) health->health = &dev->iseg->health; health->health_counter = &dev->iseg->health_counter; - health->timer.expires = round_jiffies(jiffies + MLX5_HEALTH_POLL_INTERVAL); + health->timer.expires = jiffies + msecs_to_jiffies(poll_interval_ms); add_timer(&health->timer); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c index 0c8594c7df21..ee0eb4a4b819 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c @@ -33,6 +33,11 @@ #include "en.h" #include "ipoib.h" +static u32 mlx5i_flow_type_mask(u32 flow_type) +{ + return flow_type & ~(FLOW_EXT | FLOW_MAC_EXT | FLOW_RSS); +} + static void mlx5i_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *drvinfo) { @@ -217,6 +222,27 @@ static int mlx5i_get_link_ksettings(struct net_device *netdev, return 0; } +#ifdef CONFIG_MLX5_EN_RXNFC +static int mlx5i_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd) +{ + struct mlx5e_priv *priv = mlx5i_epriv(dev); + struct ethtool_rx_flow_spec *fs = &cmd->fs; + + if (mlx5i_flow_type_mask(fs->flow_type) == ETHER_FLOW) + return -EINVAL; + + return mlx5e_ethtool_set_rxnfc(priv, cmd); +} + +static int mlx5i_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info, + u32 *rule_locs) +{ + struct mlx5e_priv *priv = mlx5i_epriv(dev); + + return mlx5e_ethtool_get_rxnfc(priv, info, rule_locs); +} +#endif + const struct ethtool_ops mlx5i_ethtool_ops = { .supported_coalesce_params = ETHTOOL_COALESCE_USECS | ETHTOOL_COALESCE_MAX_FRAMES | @@ -233,6 +259,10 @@ const struct ethtool_ops mlx5i_ethtool_ops = { .get_coalesce = mlx5i_get_coalesce, .set_coalesce = mlx5i_set_coalesce, .get_ts_info = mlx5i_get_ts_info, +#ifdef CONFIG_MLX5_EN_RXNFC + .get_rxnfc = mlx5i_get_rxnfc, + .set_rxnfc = mlx5i_set_rxnfc, +#endif .get_link_ksettings = mlx5i_get_link_ksettings, .get_link = ethtool_op_get_link, }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c index 269ebb53eda6..3b8d8ada1a01 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c @@ -219,7 +219,7 @@ void mlx5i_uninit_underlay_qp(struct mlx5e_priv *priv) int mlx5i_create_underlay_qp(struct mlx5e_priv *priv) { - unsigned char *dev_addr = priv->netdev->dev_addr; + const unsigned char *dev_addr = priv->netdev->dev_addr; u32 out[MLX5_ST_SZ_DW(create_qp_out)] = {}; u32 in[MLX5_ST_SZ_DW(create_qp_in)] = {}; struct mlx5i_priv *ipriv = priv->ppriv; @@ -336,6 +336,8 @@ static int mlx5i_create_flow_steering(struct mlx5e_priv *priv) goto err_destroy_arfs_tables; } + mlx5e_ethtool_init_steering(priv); + return 0; err_destroy_arfs_tables: @@ -348,6 +350,7 @@ static void mlx5i_destroy_flow_steering(struct mlx5e_priv *priv) { mlx5e_destroy_ttc_table(priv); mlx5e_arfs_destroy_tables(priv); + mlx5e_ethtool_cleanup_steering(priv); } static int mlx5i_init_rx(struct mlx5e_priv *priv) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c similarity index 92% rename from drivers/net/ethernet/mellanox/mlx5/core/lag.c rename to drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c index d2105c1635c3..48d2ea690d7a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c @@ -38,7 +38,7 @@ #include "mlx5_core.h" #include "eswitch.h" #include "lag.h" -#include "lag_mp.h" +#include "mp.h" /* General purpose, use for short periods of time. * Beware of lock dependencies (preferably, no locks should be acquired @@ -47,16 +47,21 @@ static DEFINE_SPINLOCK(lag_lock); static int mlx5_cmd_create_lag(struct mlx5_core_dev *dev, u8 remap_port1, - u8 remap_port2, bool shared_fdb) + u8 remap_port2, bool shared_fdb, u8 flags) { u32 in[MLX5_ST_SZ_DW(create_lag_in)] = {}; void *lag_ctx = MLX5_ADDR_OF(create_lag_in, in, ctx); MLX5_SET(create_lag_in, in, opcode, MLX5_CMD_OP_CREATE_LAG); - MLX5_SET(lagc, lag_ctx, tx_remap_affinity_1, remap_port1); - MLX5_SET(lagc, lag_ctx, tx_remap_affinity_2, remap_port2); MLX5_SET(lagc, lag_ctx, fdb_selection_mode, shared_fdb); + if (!(flags & MLX5_LAG_FLAG_HASH_BASED)) { + MLX5_SET(lagc, lag_ctx, tx_remap_affinity_1, remap_port1); + MLX5_SET(lagc, lag_ctx, tx_remap_affinity_2, remap_port2); + } else { + MLX5_SET(lagc, lag_ctx, port_select_mode, + MLX5_LAG_PORT_SELECT_MODE_PORT_SELECT_FT); + } return mlx5_cmd_exec_in(dev, create_lag, in); } @@ -199,6 +204,15 @@ static void mlx5_infer_tx_affinity_mapping(struct lag_tracker *tracker, *port1 = 2; } +static int _mlx5_modify_lag(struct mlx5_lag *ldev, u8 v2p_port1, u8 v2p_port2) +{ + struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev; + + if (ldev->flags & MLX5_LAG_FLAG_HASH_BASED) + return mlx5_lag_port_sel_modify(ldev, v2p_port1, v2p_port2); + return mlx5_cmd_modify_lag(dev0, v2p_port1, v2p_port2); +} + void mlx5_modify_lag(struct mlx5_lag *ldev, struct lag_tracker *tracker) { @@ -211,39 +225,56 @@ void mlx5_modify_lag(struct mlx5_lag *ldev, if (v2p_port1 != ldev->v2p_map[MLX5_LAG_P1] || v2p_port2 != ldev->v2p_map[MLX5_LAG_P2]) { - ldev->v2p_map[MLX5_LAG_P1] = v2p_port1; - ldev->v2p_map[MLX5_LAG_P2] = v2p_port2; - - mlx5_core_info(dev0, "modify lag map port 1:%d port 2:%d", - ldev->v2p_map[MLX5_LAG_P1], - ldev->v2p_map[MLX5_LAG_P2]); - - err = mlx5_cmd_modify_lag(dev0, v2p_port1, v2p_port2); - if (err) + err = _mlx5_modify_lag(ldev, v2p_port1, v2p_port2); + if (err) { mlx5_core_err(dev0, "Failed to modify LAG (%d)\n", err); + return; + } + ldev->v2p_map[MLX5_LAG_P1] = v2p_port1; + ldev->v2p_map[MLX5_LAG_P2] = v2p_port2; + mlx5_core_info(dev0, "modify lag map port 1:%d port 2:%d", + ldev->v2p_map[MLX5_LAG_P1], + ldev->v2p_map[MLX5_LAG_P2]); } } +static void mlx5_lag_set_port_sel_mode(struct mlx5_lag *ldev, + struct lag_tracker *tracker, u8 *flags) +{ + bool roce_lag = !!(*flags & MLX5_LAG_FLAG_ROCE); + struct lag_func *dev0 = &ldev->pf[MLX5_LAG_P1]; + + if (roce_lag || + !MLX5_CAP_PORT_SELECTION(dev0->dev, port_select_flow_table) || + tracker->tx_type != NETDEV_LAG_TX_TYPE_HASH) + return; + *flags |= MLX5_LAG_FLAG_HASH_BASED; +} + +static char *get_str_port_sel_mode(u8 flags) +{ + if (flags & MLX5_LAG_FLAG_HASH_BASED) + return "hash"; + return "queue_affinity"; +} + static int mlx5_create_lag(struct mlx5_lag *ldev, struct lag_tracker *tracker, - bool shared_fdb) + bool shared_fdb, u8 flags) { struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev; struct mlx5_core_dev *dev1 = ldev->pf[MLX5_LAG_P2].dev; u32 in[MLX5_ST_SZ_DW(destroy_lag_in)] = {}; int err; - mlx5_infer_tx_affinity_mapping(tracker, &ldev->v2p_map[MLX5_LAG_P1], - &ldev->v2p_map[MLX5_LAG_P2]); - - mlx5_core_info(dev0, "lag map port 1:%d port 2:%d shared_fdb:%d", + mlx5_core_info(dev0, "lag map port 1:%d port 2:%d shared_fdb:%d mode:%s", ldev->v2p_map[MLX5_LAG_P1], ldev->v2p_map[MLX5_LAG_P2], - shared_fdb); + shared_fdb, get_str_port_sel_mode(flags)); err = mlx5_cmd_create_lag(dev0, ldev->v2p_map[MLX5_LAG_P1], - ldev->v2p_map[MLX5_LAG_P2], shared_fdb); + ldev->v2p_map[MLX5_LAG_P2], shared_fdb, flags); if (err) { mlx5_core_err(dev0, "Failed to create LAG (%d)\n", @@ -279,16 +310,32 @@ int mlx5_activate_lag(struct mlx5_lag *ldev, struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev; int err; - err = mlx5_create_lag(ldev, tracker, shared_fdb); + mlx5_infer_tx_affinity_mapping(tracker, &ldev->v2p_map[MLX5_LAG_P1], + &ldev->v2p_map[MLX5_LAG_P2]); + mlx5_lag_set_port_sel_mode(ldev, tracker, &flags); + if (flags & MLX5_LAG_FLAG_HASH_BASED) { + err = mlx5_lag_port_sel_create(ldev, tracker->hash_type, + ldev->v2p_map[MLX5_LAG_P1], + ldev->v2p_map[MLX5_LAG_P2]); + if (err) { + mlx5_core_err(dev0, + "Failed to create LAG port selection(%d)\n", + err); + return err; + } + } + + err = mlx5_create_lag(ldev, tracker, shared_fdb, flags); if (err) { - if (roce_lag) { + if (flags & MLX5_LAG_FLAG_HASH_BASED) + mlx5_lag_port_sel_destroy(ldev); + if (roce_lag) mlx5_core_err(dev0, "Failed to activate RoCE LAG\n"); - } else { + else mlx5_core_err(dev0, "Failed to activate VF LAG\n" "Make sure all VFs are unbound prior to VF LAG activation or deactivation\n"); - } return err; } @@ -302,6 +349,7 @@ static int mlx5_deactivate_lag(struct mlx5_lag *ldev) struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev; u32 in[MLX5_ST_SZ_DW(destroy_lag_in)] = {}; bool roce_lag = __mlx5_lag_is_roce(ldev); + u8 flags = ldev->flags; int err; ldev->flags &= ~MLX5_LAG_MODE_FLAGS; @@ -324,6 +372,8 @@ static int mlx5_deactivate_lag(struct mlx5_lag *ldev) "Failed to deactivate VF LAG; driver restart required\n" "Make sure all VFs are unbound prior to VF LAG activation or deactivation\n"); } + } else if (flags & MLX5_LAG_FLAG_HASH_BASED) { + mlx5_lag_port_sel_destroy(ldev); } return err; @@ -592,8 +642,10 @@ static int mlx5_handle_changeupper_event(struct mlx5_lag *ldev, if (!(bond_status & 0x3)) return 0; - if (lag_upper_info) + if (lag_upper_info) { tracker->tx_type = lag_upper_info->tx_type; + tracker->hash_type = lag_upper_info->hash_type; + } /* Determine bonding status: * A device is considered bonded if both its physical ports are slaves @@ -692,7 +744,7 @@ static void mlx5_ldev_add_netdev(struct mlx5_lag *ldev, struct mlx5_core_dev *dev, struct net_device *netdev) { - unsigned int fn = PCI_FUNC(dev->pdev->devfn); + unsigned int fn = mlx5_get_dev_index(dev); if (fn >= MLX5_MAX_PORTS) return; @@ -722,7 +774,7 @@ static void mlx5_ldev_remove_netdev(struct mlx5_lag *ldev, static void mlx5_ldev_add_mdev(struct mlx5_lag *ldev, struct mlx5_core_dev *dev) { - unsigned int fn = PCI_FUNC(dev->pdev->devfn); + unsigned int fn = mlx5_get_dev_index(dev); if (fn >= MLX5_MAX_PORTS) return; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.h b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h similarity index 89% rename from drivers/net/ethernet/mellanox/mlx5/core/lag.h rename to drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h index d4bae528954e..e5d231c31b54 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h @@ -5,7 +5,8 @@ #define __MLX5_LAG_H__ #include "mlx5_core.h" -#include "lag_mp.h" +#include "mp.h" +#include "port_sel.h" enum { MLX5_LAG_P1, @@ -17,10 +18,12 @@ enum { MLX5_LAG_FLAG_SRIOV = 1 << 1, MLX5_LAG_FLAG_MULTIPATH = 1 << 2, MLX5_LAG_FLAG_READY = 1 << 3, + MLX5_LAG_FLAG_HASH_BASED = 1 << 4, }; #define MLX5_LAG_MODE_FLAGS (MLX5_LAG_FLAG_ROCE | MLX5_LAG_FLAG_SRIOV |\ - MLX5_LAG_FLAG_MULTIPATH) + MLX5_LAG_FLAG_MULTIPATH | \ + MLX5_LAG_FLAG_HASH_BASED) struct lag_func { struct mlx5_core_dev *dev; @@ -32,6 +35,7 @@ struct lag_tracker { enum netdev_lag_tx_type tx_type; struct netdev_lag_lower_state_info netdev_state[MLX5_MAX_PORTS]; unsigned int is_bonded:1; + enum netdev_lag_hash hash_type; }; /* LAG data of a ConnectX card. @@ -49,6 +53,7 @@ struct mlx5_lag { struct delayed_work bond_work; struct notifier_block nb; struct lag_mp lag_mp; + struct mlx5_lag_port_sel port_sel; }; static inline struct mlx5_lag * diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c similarity index 99% rename from drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c rename to drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c index 21fdaf708f1f..bf4d3cbefa63 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c @@ -3,8 +3,8 @@ #include #include -#include "lag.h" -#include "lag_mp.h" +#include "lag/lag.h" +#include "lag/mp.h" #include "mlx5_core.h" #include "eswitch.h" #include "lib/mlx5.h" diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.h b/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.h similarity index 100% rename from drivers/net/ethernet/mellanox/mlx5/core/lag_mp.h rename to drivers/net/ethernet/mellanox/mlx5/core/lag/mp.h diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c new file mode 100644 index 000000000000..adc836b3d857 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c @@ -0,0 +1,611 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. */ + +#include +#include "lag.h" + +enum { + MLX5_LAG_FT_LEVEL_TTC, + MLX5_LAG_FT_LEVEL_INNER_TTC, + MLX5_LAG_FT_LEVEL_DEFINER, +}; + +static struct mlx5_flow_group * +mlx5_create_hash_flow_group(struct mlx5_flow_table *ft, + struct mlx5_flow_definer *definer) +{ + int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); + struct mlx5_flow_group *fg; + u32 *in; + + in = kvzalloc(inlen, GFP_KERNEL); + if (!in) + return ERR_PTR(-ENOMEM); + + MLX5_SET(create_flow_group_in, in, match_definer_id, + mlx5_get_match_definer_id(definer)); + MLX5_SET(create_flow_group_in, in, start_flow_index, 0); + MLX5_SET(create_flow_group_in, in, end_flow_index, MLX5_MAX_PORTS - 1); + MLX5_SET(create_flow_group_in, in, group_type, + MLX5_CREATE_FLOW_GROUP_IN_GROUP_TYPE_HASH_SPLIT); + + fg = mlx5_create_flow_group(ft, in); + kvfree(in); + return fg; +} + +static int mlx5_lag_create_port_sel_table(struct mlx5_lag *ldev, + struct mlx5_lag_definer *lag_definer, + u8 port1, u8 port2) +{ + struct mlx5_core_dev *dev = ldev->pf[MLX5_LAG_P1].dev; + struct mlx5_flow_table_attr ft_attr = {}; + struct mlx5_flow_destination dest = {}; + MLX5_DECLARE_FLOW_ACT(flow_act); + struct mlx5_flow_namespace *ns; + int err, i; + + ft_attr.max_fte = MLX5_MAX_PORTS; + ft_attr.level = MLX5_LAG_FT_LEVEL_DEFINER; + + ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_PORT_SEL); + if (!ns) { + mlx5_core_warn(dev, "Failed to get port selection namespace\n"); + return -EOPNOTSUPP; + } + + lag_definer->ft = mlx5_create_flow_table(ns, &ft_attr); + if (IS_ERR(lag_definer->ft)) { + mlx5_core_warn(dev, "Failed to create port selection table\n"); + return PTR_ERR(lag_definer->ft); + } + + lag_definer->fg = mlx5_create_hash_flow_group(lag_definer->ft, + lag_definer->definer); + if (IS_ERR(lag_definer->fg)) { + err = PTR_ERR(lag_definer->fg); + goto destroy_ft; + } + + dest.type = MLX5_FLOW_DESTINATION_TYPE_UPLINK; + dest.vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID; + flow_act.flags |= FLOW_ACT_NO_APPEND; + for (i = 0; i < MLX5_MAX_PORTS; i++) { + u8 affinity = i == 0 ? port1 : port2; + + dest.vport.vhca_id = MLX5_CAP_GEN(ldev->pf[affinity - 1].dev, + vhca_id); + lag_definer->rules[i] = mlx5_add_flow_rules(lag_definer->ft, + NULL, &flow_act, + &dest, 1); + if (IS_ERR(lag_definer->rules[i])) { + err = PTR_ERR(lag_definer->rules[i]); + while (i--) + mlx5_del_flow_rules(lag_definer->rules[i]); + goto destroy_fg; + } + } + + return 0; + +destroy_fg: + mlx5_destroy_flow_group(lag_definer->fg); +destroy_ft: + mlx5_destroy_flow_table(lag_definer->ft); + return err; +} + +static int mlx5_lag_set_definer_inner(u32 *match_definer_mask, + enum mlx5_traffic_types tt) +{ + int format_id; + u8 *ipv6; + + switch (tt) { + case MLX5_TT_IPV4_UDP: + case MLX5_TT_IPV4_TCP: + format_id = 23; + MLX5_SET_TO_ONES(match_definer_format_23, match_definer_mask, + inner_l4_sport); + MLX5_SET_TO_ONES(match_definer_format_23, match_definer_mask, + inner_l4_dport); + MLX5_SET_TO_ONES(match_definer_format_23, match_definer_mask, + inner_ip_src_addr); + MLX5_SET_TO_ONES(match_definer_format_23, match_definer_mask, + inner_ip_dest_addr); + break; + case MLX5_TT_IPV4: + format_id = 23; + MLX5_SET_TO_ONES(match_definer_format_23, match_definer_mask, + inner_l3_type); + MLX5_SET_TO_ONES(match_definer_format_23, match_definer_mask, + inner_dmac_47_16); + MLX5_SET_TO_ONES(match_definer_format_23, match_definer_mask, + inner_dmac_15_0); + MLX5_SET_TO_ONES(match_definer_format_23, match_definer_mask, + inner_smac_47_16); + MLX5_SET_TO_ONES(match_definer_format_23, match_definer_mask, + inner_smac_15_0); + MLX5_SET_TO_ONES(match_definer_format_23, match_definer_mask, + inner_ip_src_addr); + MLX5_SET_TO_ONES(match_definer_format_23, match_definer_mask, + inner_ip_dest_addr); + break; + case MLX5_TT_IPV6_TCP: + case MLX5_TT_IPV6_UDP: + format_id = 31; + MLX5_SET_TO_ONES(match_definer_format_31, match_definer_mask, + inner_l4_sport); + MLX5_SET_TO_ONES(match_definer_format_31, match_definer_mask, + inner_l4_dport); + ipv6 = MLX5_ADDR_OF(match_definer_format_31, match_definer_mask, + inner_ip_dest_addr); + memset(ipv6, 0xff, 16); + ipv6 = MLX5_ADDR_OF(match_definer_format_31, match_definer_mask, + inner_ip_src_addr); + memset(ipv6, 0xff, 16); + break; + case MLX5_TT_IPV6: + format_id = 32; + ipv6 = MLX5_ADDR_OF(match_definer_format_32, match_definer_mask, + inner_ip_dest_addr); + memset(ipv6, 0xff, 16); + ipv6 = MLX5_ADDR_OF(match_definer_format_32, match_definer_mask, + inner_ip_src_addr); + memset(ipv6, 0xff, 16); + MLX5_SET_TO_ONES(match_definer_format_32, match_definer_mask, + inner_dmac_47_16); + MLX5_SET_TO_ONES(match_definer_format_32, match_definer_mask, + inner_dmac_15_0); + MLX5_SET_TO_ONES(match_definer_format_32, match_definer_mask, + inner_smac_47_16); + MLX5_SET_TO_ONES(match_definer_format_32, match_definer_mask, + inner_smac_15_0); + break; + default: + format_id = 23; + MLX5_SET_TO_ONES(match_definer_format_23, match_definer_mask, + inner_l3_type); + MLX5_SET_TO_ONES(match_definer_format_23, match_definer_mask, + inner_dmac_47_16); + MLX5_SET_TO_ONES(match_definer_format_23, match_definer_mask, + inner_dmac_15_0); + MLX5_SET_TO_ONES(match_definer_format_23, match_definer_mask, + inner_smac_47_16); + MLX5_SET_TO_ONES(match_definer_format_23, match_definer_mask, + inner_smac_15_0); + break; + } + + return format_id; +} + +static int mlx5_lag_set_definer(u32 *match_definer_mask, + enum mlx5_traffic_types tt, bool tunnel, + enum netdev_lag_hash hash) +{ + int format_id; + u8 *ipv6; + + if (tunnel) + return mlx5_lag_set_definer_inner(match_definer_mask, tt); + + switch (tt) { + case MLX5_TT_IPV4_UDP: + case MLX5_TT_IPV4_TCP: + format_id = 22; + MLX5_SET_TO_ONES(match_definer_format_22, match_definer_mask, + outer_l4_sport); + MLX5_SET_TO_ONES(match_definer_format_22, match_definer_mask, + outer_l4_dport); + MLX5_SET_TO_ONES(match_definer_format_22, match_definer_mask, + outer_ip_src_addr); + MLX5_SET_TO_ONES(match_definer_format_22, match_definer_mask, + outer_ip_dest_addr); + break; + case MLX5_TT_IPV4: + format_id = 22; + MLX5_SET_TO_ONES(match_definer_format_22, match_definer_mask, + outer_l3_type); + MLX5_SET_TO_ONES(match_definer_format_22, match_definer_mask, + outer_dmac_47_16); + MLX5_SET_TO_ONES(match_definer_format_22, match_definer_mask, + outer_dmac_15_0); + MLX5_SET_TO_ONES(match_definer_format_22, match_definer_mask, + outer_smac_47_16); + MLX5_SET_TO_ONES(match_definer_format_22, match_definer_mask, + outer_smac_15_0); + MLX5_SET_TO_ONES(match_definer_format_22, match_definer_mask, + outer_ip_src_addr); + MLX5_SET_TO_ONES(match_definer_format_22, match_definer_mask, + outer_ip_dest_addr); + break; + case MLX5_TT_IPV6_TCP: + case MLX5_TT_IPV6_UDP: + format_id = 29; + MLX5_SET_TO_ONES(match_definer_format_29, match_definer_mask, + outer_l4_sport); + MLX5_SET_TO_ONES(match_definer_format_29, match_definer_mask, + outer_l4_dport); + ipv6 = MLX5_ADDR_OF(match_definer_format_29, match_definer_mask, + outer_ip_dest_addr); + memset(ipv6, 0xff, 16); + ipv6 = MLX5_ADDR_OF(match_definer_format_29, match_definer_mask, + outer_ip_src_addr); + memset(ipv6, 0xff, 16); + break; + case MLX5_TT_IPV6: + format_id = 30; + ipv6 = MLX5_ADDR_OF(match_definer_format_30, match_definer_mask, + outer_ip_dest_addr); + memset(ipv6, 0xff, 16); + ipv6 = MLX5_ADDR_OF(match_definer_format_30, match_definer_mask, + outer_ip_src_addr); + memset(ipv6, 0xff, 16); + MLX5_SET_TO_ONES(match_definer_format_30, match_definer_mask, + outer_dmac_47_16); + MLX5_SET_TO_ONES(match_definer_format_30, match_definer_mask, + outer_dmac_15_0); + MLX5_SET_TO_ONES(match_definer_format_30, match_definer_mask, + outer_smac_47_16); + MLX5_SET_TO_ONES(match_definer_format_30, match_definer_mask, + outer_smac_15_0); + break; + default: + format_id = 0; + MLX5_SET_TO_ONES(match_definer_format_0, match_definer_mask, + outer_smac_47_16); + MLX5_SET_TO_ONES(match_definer_format_0, match_definer_mask, + outer_smac_15_0); + + if (hash == NETDEV_LAG_HASH_VLAN_SRCMAC) { + MLX5_SET_TO_ONES(match_definer_format_0, + match_definer_mask, + outer_first_vlan_vid); + break; + } + + MLX5_SET_TO_ONES(match_definer_format_0, match_definer_mask, + outer_ethertype); + MLX5_SET_TO_ONES(match_definer_format_0, match_definer_mask, + outer_dmac_47_16); + MLX5_SET_TO_ONES(match_definer_format_0, match_definer_mask, + outer_dmac_15_0); + break; + } + + return format_id; +} + +static struct mlx5_lag_definer * +mlx5_lag_create_definer(struct mlx5_lag *ldev, enum netdev_lag_hash hash, + enum mlx5_traffic_types tt, bool tunnel, u8 port1, + u8 port2) +{ + struct mlx5_core_dev *dev = ldev->pf[MLX5_LAG_P1].dev; + struct mlx5_lag_definer *lag_definer; + u32 *match_definer_mask; + int format_id, err; + + lag_definer = kzalloc(sizeof(*lag_definer), GFP_KERNEL); + if (!lag_definer) + return ERR_PTR(ENOMEM); + + match_definer_mask = kvzalloc(MLX5_FLD_SZ_BYTES(match_definer, + match_mask), + GFP_KERNEL); + if (!match_definer_mask) { + err = -ENOMEM; + goto free_lag_definer; + } + + format_id = mlx5_lag_set_definer(match_definer_mask, tt, tunnel, hash); + lag_definer->definer = + mlx5_create_match_definer(dev, MLX5_FLOW_NAMESPACE_PORT_SEL, + format_id, match_definer_mask); + if (IS_ERR(lag_definer->definer)) { + err = PTR_ERR(lag_definer->definer); + goto free_mask; + } + + err = mlx5_lag_create_port_sel_table(ldev, lag_definer, port1, port2); + if (err) + goto destroy_match_definer; + + kvfree(match_definer_mask); + + return lag_definer; + +destroy_match_definer: + mlx5_destroy_match_definer(dev, lag_definer->definer); +free_mask: + kvfree(match_definer_mask); +free_lag_definer: + kfree(lag_definer); + return ERR_PTR(err); +} + +static void mlx5_lag_destroy_definer(struct mlx5_lag *ldev, + struct mlx5_lag_definer *lag_definer) +{ + struct mlx5_core_dev *dev = ldev->pf[MLX5_LAG_P1].dev; + int i; + + for (i = 0; i < MLX5_MAX_PORTS; i++) + mlx5_del_flow_rules(lag_definer->rules[i]); + mlx5_destroy_flow_group(lag_definer->fg); + mlx5_destroy_flow_table(lag_definer->ft); + mlx5_destroy_match_definer(dev, lag_definer->definer); + kfree(lag_definer); +} + +static void mlx5_lag_destroy_definers(struct mlx5_lag *ldev) +{ + struct mlx5_lag_port_sel *port_sel = &ldev->port_sel; + int tt; + + for_each_set_bit(tt, port_sel->tt_map, MLX5_NUM_TT) { + if (port_sel->outer.definers[tt]) + mlx5_lag_destroy_definer(ldev, + port_sel->outer.definers[tt]); + if (port_sel->inner.definers[tt]) + mlx5_lag_destroy_definer(ldev, + port_sel->inner.definers[tt]); + } +} + +static int mlx5_lag_create_definers(struct mlx5_lag *ldev, + enum netdev_lag_hash hash_type, + u8 port1, u8 port2) +{ + struct mlx5_lag_port_sel *port_sel = &ldev->port_sel; + struct mlx5_lag_definer *lag_definer; + int tt, err; + + for_each_set_bit(tt, port_sel->tt_map, MLX5_NUM_TT) { + lag_definer = mlx5_lag_create_definer(ldev, hash_type, tt, + false, port1, port2); + if (IS_ERR(lag_definer)) { + err = PTR_ERR(lag_definer); + goto destroy_definers; + } + port_sel->outer.definers[tt] = lag_definer; + + if (!port_sel->tunnel) + continue; + + lag_definer = + mlx5_lag_create_definer(ldev, hash_type, tt, + true, port1, port2); + if (IS_ERR(lag_definer)) { + err = PTR_ERR(lag_definer); + goto destroy_definers; + } + port_sel->inner.definers[tt] = lag_definer; + } + + return 0; + +destroy_definers: + mlx5_lag_destroy_definers(ldev); + return err; +} + +static void set_tt_map(struct mlx5_lag_port_sel *port_sel, + enum netdev_lag_hash hash) +{ + port_sel->tunnel = false; + + switch (hash) { + case NETDEV_LAG_HASH_E34: + port_sel->tunnel = true; + fallthrough; + case NETDEV_LAG_HASH_L34: + set_bit(MLX5_TT_IPV4_TCP, port_sel->tt_map); + set_bit(MLX5_TT_IPV4_UDP, port_sel->tt_map); + set_bit(MLX5_TT_IPV6_TCP, port_sel->tt_map); + set_bit(MLX5_TT_IPV6_UDP, port_sel->tt_map); + set_bit(MLX5_TT_IPV4, port_sel->tt_map); + set_bit(MLX5_TT_IPV6, port_sel->tt_map); + set_bit(MLX5_TT_ANY, port_sel->tt_map); + break; + case NETDEV_LAG_HASH_E23: + port_sel->tunnel = true; + fallthrough; + case NETDEV_LAG_HASH_L23: + set_bit(MLX5_TT_IPV4, port_sel->tt_map); + set_bit(MLX5_TT_IPV6, port_sel->tt_map); + set_bit(MLX5_TT_ANY, port_sel->tt_map); + break; + default: + set_bit(MLX5_TT_ANY, port_sel->tt_map); + break; + } +} + +#define SET_IGNORE_DESTS_BITS(tt_map, dests) \ + do { \ + int idx; \ + \ + for_each_clear_bit(idx, tt_map, MLX5_NUM_TT) \ + set_bit(idx, dests); \ + } while (0) + +static void mlx5_lag_set_inner_ttc_params(struct mlx5_lag *ldev, + struct ttc_params *ttc_params) +{ + struct mlx5_core_dev *dev = ldev->pf[MLX5_LAG_P1].dev; + struct mlx5_lag_port_sel *port_sel = &ldev->port_sel; + struct mlx5_flow_table_attr *ft_attr; + int tt; + + ttc_params->ns = mlx5_get_flow_namespace(dev, + MLX5_FLOW_NAMESPACE_PORT_SEL); + ft_attr = &ttc_params->ft_attr; + ft_attr->level = MLX5_LAG_FT_LEVEL_INNER_TTC; + + for_each_set_bit(tt, port_sel->tt_map, MLX5_NUM_TT) { + ttc_params->dests[tt].type = + MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE; + ttc_params->dests[tt].ft = port_sel->inner.definers[tt]->ft; + } + SET_IGNORE_DESTS_BITS(port_sel->tt_map, ttc_params->ignore_dests); +} + +static void mlx5_lag_set_outer_ttc_params(struct mlx5_lag *ldev, + struct ttc_params *ttc_params) +{ + struct mlx5_core_dev *dev = ldev->pf[MLX5_LAG_P1].dev; + struct mlx5_lag_port_sel *port_sel = &ldev->port_sel; + struct mlx5_flow_table_attr *ft_attr; + int tt; + + ttc_params->ns = mlx5_get_flow_namespace(dev, + MLX5_FLOW_NAMESPACE_PORT_SEL); + ft_attr = &ttc_params->ft_attr; + ft_attr->level = MLX5_LAG_FT_LEVEL_TTC; + + for_each_set_bit(tt, port_sel->tt_map, MLX5_NUM_TT) { + ttc_params->dests[tt].type = + MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE; + ttc_params->dests[tt].ft = port_sel->outer.definers[tt]->ft; + } + SET_IGNORE_DESTS_BITS(port_sel->tt_map, ttc_params->ignore_dests); + + ttc_params->inner_ttc = port_sel->tunnel; + if (!port_sel->tunnel) + return; + + for (tt = 0; tt < MLX5_NUM_TUNNEL_TT; tt++) { + ttc_params->tunnel_dests[tt].type = + MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE; + ttc_params->tunnel_dests[tt].ft = + mlx5_get_ttc_flow_table(port_sel->inner.ttc); + } +} + +static int mlx5_lag_create_ttc_table(struct mlx5_lag *ldev) +{ + struct mlx5_core_dev *dev = ldev->pf[MLX5_LAG_P1].dev; + struct mlx5_lag_port_sel *port_sel = &ldev->port_sel; + struct ttc_params ttc_params = {}; + + mlx5_lag_set_outer_ttc_params(ldev, &ttc_params); + port_sel->outer.ttc = mlx5_create_ttc_table(dev, &ttc_params); + if (IS_ERR(port_sel->outer.ttc)) + return PTR_ERR(port_sel->outer.ttc); + + return 0; +} + +static int mlx5_lag_create_inner_ttc_table(struct mlx5_lag *ldev) +{ + struct mlx5_core_dev *dev = ldev->pf[MLX5_LAG_P1].dev; + struct mlx5_lag_port_sel *port_sel = &ldev->port_sel; + struct ttc_params ttc_params = {}; + + mlx5_lag_set_inner_ttc_params(ldev, &ttc_params); + port_sel->inner.ttc = mlx5_create_ttc_table(dev, &ttc_params); + if (IS_ERR(port_sel->inner.ttc)) + return PTR_ERR(port_sel->inner.ttc); + + return 0; +} + +int mlx5_lag_port_sel_create(struct mlx5_lag *ldev, + enum netdev_lag_hash hash_type, u8 port1, u8 port2) +{ + struct mlx5_lag_port_sel *port_sel = &ldev->port_sel; + int err; + + set_tt_map(port_sel, hash_type); + err = mlx5_lag_create_definers(ldev, hash_type, port1, port2); + if (err) + return err; + + if (port_sel->tunnel) { + err = mlx5_lag_create_inner_ttc_table(ldev); + if (err) + goto destroy_definers; + } + + err = mlx5_lag_create_ttc_table(ldev); + if (err) + goto destroy_inner; + + return 0; + +destroy_inner: + if (port_sel->tunnel) + mlx5_destroy_ttc_table(port_sel->inner.ttc); +destroy_definers: + mlx5_lag_destroy_definers(ldev); + return err; +} + +static int +mlx5_lag_modify_definers_destinations(struct mlx5_lag *ldev, + struct mlx5_lag_definer **definers, + u8 port1, u8 port2) +{ + struct mlx5_lag_port_sel *port_sel = &ldev->port_sel; + struct mlx5_flow_destination dest = {}; + int err; + int tt; + + dest.type = MLX5_FLOW_DESTINATION_TYPE_UPLINK; + dest.vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID; + + for_each_set_bit(tt, port_sel->tt_map, MLX5_NUM_TT) { + struct mlx5_flow_handle **rules = definers[tt]->rules; + + if (ldev->v2p_map[MLX5_LAG_P1] != port1) { + dest.vport.vhca_id = + MLX5_CAP_GEN(ldev->pf[port1 - 1].dev, vhca_id); + err = mlx5_modify_rule_destination(rules[MLX5_LAG_P1], + &dest, NULL); + if (err) + return err; + } + + if (ldev->v2p_map[MLX5_LAG_P2] != port2) { + dest.vport.vhca_id = + MLX5_CAP_GEN(ldev->pf[port2 - 1].dev, vhca_id); + err = mlx5_modify_rule_destination(rules[MLX5_LAG_P2], + &dest, NULL); + if (err) + return err; + } + } + + return 0; +} + +int mlx5_lag_port_sel_modify(struct mlx5_lag *ldev, u8 port1, u8 port2) +{ + struct mlx5_lag_port_sel *port_sel = &ldev->port_sel; + int err; + + err = mlx5_lag_modify_definers_destinations(ldev, + port_sel->outer.definers, + port1, port2); + if (err) + return err; + + if (!port_sel->tunnel) + return 0; + + return mlx5_lag_modify_definers_destinations(ldev, + port_sel->inner.definers, + port1, port2); +} + +void mlx5_lag_port_sel_destroy(struct mlx5_lag *ldev) +{ + struct mlx5_lag_port_sel *port_sel = &ldev->port_sel; + + mlx5_destroy_ttc_table(port_sel->outer.ttc); + if (port_sel->tunnel) + mlx5_destroy_ttc_table(port_sel->inner.ttc); + mlx5_lag_destroy_definers(ldev); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.h b/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.h new file mode 100644 index 000000000000..6d15b28a42fc --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.h @@ -0,0 +1,52 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. */ + +#ifndef __MLX5_LAG_FS_H__ +#define __MLX5_LAG_FS_H__ + +#include "lib/fs_ttc.h" + +struct mlx5_lag_definer { + struct mlx5_flow_definer *definer; + struct mlx5_flow_table *ft; + struct mlx5_flow_group *fg; + struct mlx5_flow_handle *rules[MLX5_MAX_PORTS]; +}; + +struct mlx5_lag_ttc { + struct mlx5_ttc_table *ttc; + struct mlx5_lag_definer *definers[MLX5_NUM_TT]; +}; + +struct mlx5_lag_port_sel { + DECLARE_BITMAP(tt_map, MLX5_NUM_TT); + bool tunnel; + struct mlx5_lag_ttc outer; + struct mlx5_lag_ttc inner; +}; + +#ifdef CONFIG_MLX5_ESWITCH + +int mlx5_lag_port_sel_modify(struct mlx5_lag *ldev, u8 port1, u8 port2); +void mlx5_lag_port_sel_destroy(struct mlx5_lag *ldev); +int mlx5_lag_port_sel_create(struct mlx5_lag *ldev, + enum netdev_lag_hash hash_type, u8 port1, + u8 port2); + +#else /* CONFIG_MLX5_ESWITCH */ +static inline int mlx5_lag_port_sel_create(struct mlx5_lag *ldev, + enum netdev_lag_hash hash_type, + u8 port1, u8 port2) +{ + return 0; +} + +static inline int mlx5_lag_port_sel_modify(struct mlx5_lag *ldev, u8 port1, + u8 port2) +{ + return 0; +} + +static inline void mlx5_lag_port_sel_destroy(struct mlx5_lag *ldev) {} +#endif /* CONFIG_MLX5_ESWITCH */ +#endif /* __MLX5_LAG_FS_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.c index 749d17c0057d..b63dec24747a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.c @@ -247,6 +247,8 @@ static int mlx5_generate_ttc_table_rules(struct mlx5_core_dev *dev, for (tt = 0; tt < MLX5_NUM_TT; tt++) { struct mlx5_ttc_rule *rule = &rules[tt]; + if (test_bit(tt, params->ignore_dests)) + continue; rule->rule = mlx5_generate_ttc_rule(dev, ft, ¶ms->dests[tt], ttc_rules[tt].etype, ttc_rules[tt].proto); @@ -266,6 +268,8 @@ static int mlx5_generate_ttc_table_rules(struct mlx5_core_dev *dev, if (!mlx5_tunnel_proto_supported_rx(dev, ttc_tunnel_rules[tt].proto)) continue; + if (test_bit(tt, params->ignore_tunnel_dests)) + continue; trules[tt] = mlx5_generate_ttc_rule(dev, ft, ¶ms->tunnel_dests[tt], ttc_tunnel_rules[tt].etype, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.h index ce95be8f8382..85fef0cd1c07 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.h @@ -43,7 +43,9 @@ struct ttc_params { struct mlx5_flow_namespace *ns; struct mlx5_flow_table_attr ft_attr; struct mlx5_flow_destination dests[MLX5_NUM_TT]; + DECLARE_BITMAP(ignore_dests, MLX5_NUM_TT); bool inner_ttc; + DECLARE_BITMAP(ignore_tunnel_dests, MLX5_NUM_TUNNEL_TT); struct mlx5_flow_destination tunnel_dests[MLX5_NUM_TUNNEL_TT]; }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/tout.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/tout.c new file mode 100644 index 000000000000..0dd96a6b140d --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/tout.c @@ -0,0 +1,162 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */ + +#include +#include "lib/tout.h" + +struct mlx5_timeouts { + u64 to[MAX_TIMEOUT_TYPES]; +}; + +static const u32 tout_def_sw_val[MAX_TIMEOUT_TYPES] = { + [MLX5_TO_FW_PRE_INIT_TIMEOUT_MS] = 120000, + [MLX5_TO_FW_PRE_INIT_WARN_MESSAGE_INTERVAL_MS] = 20000, + [MLX5_TO_FW_PRE_INIT_WAIT_MS] = 2, + [MLX5_TO_FW_INIT_MS] = 2000, + [MLX5_TO_CMD_MS] = 60000, + [MLX5_TO_PCI_TOGGLE_MS] = 2000, + [MLX5_TO_HEALTH_POLL_INTERVAL_MS] = 2000, + [MLX5_TO_FULL_CRDUMP_MS] = 60000, + [MLX5_TO_FW_RESET_MS] = 60000, + [MLX5_TO_FLUSH_ON_ERROR_MS] = 2000, + [MLX5_TO_PCI_SYNC_UPDATE_MS] = 5000, + [MLX5_TO_TEARDOWN_MS] = 3000, + [MLX5_TO_FSM_REACTIVATE_MS] = 5000, + [MLX5_TO_RECLAIM_PAGES_MS] = 5000, + [MLX5_TO_RECLAIM_VFS_PAGES_MS] = 120000 +}; + +static void tout_set(struct mlx5_core_dev *dev, u64 val, enum mlx5_timeouts_types type) +{ + dev->timeouts->to[type] = val; +} + +static void tout_set_def_val(struct mlx5_core_dev *dev) +{ + int i; + + for (i = MLX5_TO_FW_PRE_INIT_TIMEOUT_MS; i < MAX_TIMEOUT_TYPES; i++) + tout_set(dev, tout_def_sw_val[i], i); +} + +int mlx5_tout_init(struct mlx5_core_dev *dev) +{ + dev->timeouts = kmalloc(sizeof(*dev->timeouts), GFP_KERNEL); + if (!dev->timeouts) + return -ENOMEM; + + tout_set_def_val(dev); + return 0; +} + +void mlx5_tout_cleanup(struct mlx5_core_dev *dev) +{ + kfree(dev->timeouts); +} + +/* Time register consists of two fields to_multiplier(time out multiplier) + * and to_value(time out value). to_value is the quantity of the time units and + * to_multiplier is the type and should be one off these four values. + * 0x0: millisecond + * 0x1: seconds + * 0x2: minutes + * 0x3: hours + * this function converts the time stored in the two register fields into + * millisecond. + */ +static u64 tout_convert_reg_field_to_ms(u32 to_mul, u32 to_val) +{ + u64 msec = to_val; + + to_mul &= 0x3; + /* convert hours/minutes/seconds to miliseconds */ + if (to_mul) + msec *= 1000 * int_pow(60, to_mul - 1); + + return msec; +} + +static u64 tout_convert_iseg_to_ms(u32 iseg_to) +{ + return tout_convert_reg_field_to_ms(iseg_to >> 29, iseg_to & 0xfffff); +} + +static bool tout_is_supported(struct mlx5_core_dev *dev) +{ + return !!ioread32be(&dev->iseg->cmd_q_init_to); +} + +void mlx5_tout_query_iseg(struct mlx5_core_dev *dev) +{ + u32 to; + + if (!tout_is_supported(dev)) + return; + + to = ioread32be(&dev->iseg->cmd_q_init_to); + tout_set(dev, tout_convert_iseg_to_ms(to), MLX5_TO_FW_INIT_MS); + + to = ioread32be(&dev->iseg->cmd_exec_to); + tout_set(dev, tout_convert_iseg_to_ms(to), MLX5_TO_CMD_MS); +} + +u64 _mlx5_tout_ms(struct mlx5_core_dev *dev, enum mlx5_timeouts_types type) +{ + return dev->timeouts->to[type]; +} + +#define MLX5_TIMEOUT_QUERY(fld, reg_out) \ + ({ \ + struct mlx5_ifc_default_timeout_bits *time_field; \ + u32 to_multi, to_value; \ + u64 to_val_ms; \ + \ + time_field = MLX5_ADDR_OF(dtor_reg, reg_out, fld); \ + to_multi = MLX5_GET(default_timeout, time_field, to_multiplier); \ + to_value = MLX5_GET(default_timeout, time_field, to_value); \ + to_val_ms = tout_convert_reg_field_to_ms(to_multi, to_value); \ + to_val_ms; \ + }) + +#define MLX5_TIMEOUT_FILL(fld, reg_out, dev, to_type, to_extra) \ + ({ \ + u64 fw_to = MLX5_TIMEOUT_QUERY(fld, reg_out); \ + tout_set(dev, fw_to + (to_extra), to_type); \ + fw_to; \ + }) + +static int tout_query_dtor(struct mlx5_core_dev *dev) +{ + u64 pcie_toggle_to_val, tear_down_to_val; + u32 out[MLX5_ST_SZ_DW(dtor_reg)] = {}; + u32 in[MLX5_ST_SZ_DW(dtor_reg)] = {}; + int err; + + err = mlx5_core_access_reg(dev, in, sizeof(in), out, sizeof(out), MLX5_REG_DTOR, 0, 0); + if (err) + return err; + + pcie_toggle_to_val = MLX5_TIMEOUT_FILL(pcie_toggle_to, out, dev, MLX5_TO_PCI_TOGGLE_MS, 0); + MLX5_TIMEOUT_FILL(fw_reset_to, out, dev, MLX5_TO_FW_RESET_MS, pcie_toggle_to_val); + + tear_down_to_val = MLX5_TIMEOUT_FILL(tear_down_to, out, dev, MLX5_TO_TEARDOWN_MS, 0); + MLX5_TIMEOUT_FILL(pci_sync_update_to, out, dev, MLX5_TO_PCI_SYNC_UPDATE_MS, + tear_down_to_val); + + MLX5_TIMEOUT_FILL(health_poll_to, out, dev, MLX5_TO_HEALTH_POLL_INTERVAL_MS, 0); + MLX5_TIMEOUT_FILL(full_crdump_to, out, dev, MLX5_TO_FULL_CRDUMP_MS, 0); + MLX5_TIMEOUT_FILL(flush_on_err_to, out, dev, MLX5_TO_FLUSH_ON_ERROR_MS, 0); + MLX5_TIMEOUT_FILL(fsm_reactivate_to, out, dev, MLX5_TO_FSM_REACTIVATE_MS, 0); + MLX5_TIMEOUT_FILL(reclaim_pages_to, out, dev, MLX5_TO_RECLAIM_PAGES_MS, 0); + MLX5_TIMEOUT_FILL(reclaim_vfs_pages_to, out, dev, MLX5_TO_RECLAIM_VFS_PAGES_MS, 0); + + return 0; +} + +int mlx5_tout_query_dtor(struct mlx5_core_dev *dev) +{ + if (tout_is_supported(dev)) + return tout_query_dtor(dev); + + return 0; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/tout.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/tout.h new file mode 100644 index 000000000000..31faa5c17aa9 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/tout.h @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */ + +#ifndef MLX5_TIMEOUTS_H +#define MLX5_TIMEOUTS_H + +enum mlx5_timeouts_types { + /* pre init timeouts (not read from FW) */ + MLX5_TO_FW_PRE_INIT_TIMEOUT_MS, + MLX5_TO_FW_PRE_INIT_WARN_MESSAGE_INTERVAL_MS, + MLX5_TO_FW_PRE_INIT_WAIT_MS, + + /* init segment timeouts */ + MLX5_TO_FW_INIT_MS, + MLX5_TO_CMD_MS, + + /* DTOR timeouts */ + MLX5_TO_PCI_TOGGLE_MS, + MLX5_TO_HEALTH_POLL_INTERVAL_MS, + MLX5_TO_FULL_CRDUMP_MS, + MLX5_TO_FW_RESET_MS, + MLX5_TO_FLUSH_ON_ERROR_MS, + MLX5_TO_PCI_SYNC_UPDATE_MS, + MLX5_TO_TEARDOWN_MS, + MLX5_TO_FSM_REACTIVATE_MS, + MLX5_TO_RECLAIM_PAGES_MS, + MLX5_TO_RECLAIM_VFS_PAGES_MS, + + MAX_TIMEOUT_TYPES +}; + +struct mlx5_core_dev; +int mlx5_tout_init(struct mlx5_core_dev *dev); +void mlx5_tout_cleanup(struct mlx5_core_dev *dev); +void mlx5_tout_query_iseg(struct mlx5_core_dev *dev); +int mlx5_tout_query_dtor(struct mlx5_core_dev *dev); +u64 _mlx5_tout_ms(struct mlx5_core_dev *dev, enum mlx5_timeouts_types type); + +#define mlx5_tout_ms(dev, type) _mlx5_tout_ms(dev, MLX5_TO_##type##_MS) + +# endif /* MLX5_TIMEOUTS_H */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 5893fdd5aedb..f8446395163a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -60,6 +60,7 @@ #include "devlink.h" #include "fw_reset.h" #include "lib/mlx5.h" +#include "lib/tout.h" #include "fpga/core.h" #include "fpga/ipsec.h" #include "accel/ipsec.h" @@ -176,11 +177,6 @@ static struct mlx5_profile profile[] = { }, }; -#define FW_INIT_TIMEOUT_MILI 2000 -#define FW_INIT_WAIT_MS 2 -#define FW_PRE_INIT_TIMEOUT_MILI 120000 -#define FW_INIT_WARN_MESSAGE_INTERVAL 20000 - static int fw_initializing(struct mlx5_core_dev *dev) { return ioread32be(&dev->iseg->initializing) >> 31; @@ -193,8 +189,6 @@ static int wait_fw_init(struct mlx5_core_dev *dev, u32 max_wait_mili, unsigned long end = jiffies + msecs_to_jiffies(max_wait_mili); int err = 0; - BUILD_BUG_ON(FW_PRE_INIT_TIMEOUT_MILI < FW_INIT_WARN_MESSAGE_INTERVAL); - while (fw_initializing(dev)) { if (time_after(jiffies, end)) { err = -EBUSY; @@ -205,7 +199,7 @@ static int wait_fw_init(struct mlx5_core_dev *dev, u32 max_wait_mili, jiffies_to_msecs(end - warn) / 1000); warn = jiffies + msecs_to_jiffies(warn_time_mili); } - msleep(FW_INIT_WAIT_MS); + msleep(mlx5_tout_ms(dev, FW_PRE_INIT_WAIT)); } return err; @@ -564,15 +558,38 @@ static int handle_hca_cap(struct mlx5_core_dev *dev, void *set_ctx) MLX5_SET(cmd_hca_cap, set_hca_cap, num_total_dynamic_vf_msix, MLX5_CAP_GEN_MAX(dev, num_total_dynamic_vf_msix)); + if (MLX5_CAP_GEN(dev, roce_rw_supported)) + MLX5_SET(cmd_hca_cap, set_hca_cap, roce, mlx5_is_roce_init_enabled(dev)); + return set_caps(dev, set_ctx, MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE); } +/* Cached MLX5_CAP_GEN(dev, roce) can be out of sync this early in the + * boot process. + * In case RoCE cap is writable in FW and user/devlink requested to change the + * cap, we are yet to query the final state of the above cap. + * Hence, the need for this function. + * + * Returns + * True: + * 1) RoCE cap is read only in FW and already disabled + * OR: + * 2) RoCE cap is writable in FW and user/devlink requested it off. + * + * In any other case, return False. + */ +static bool is_roce_fw_disabled(struct mlx5_core_dev *dev) +{ + return (MLX5_CAP_GEN(dev, roce_rw_supported) && !mlx5_is_roce_init_enabled(dev)) || + (!MLX5_CAP_GEN(dev, roce_rw_supported) && !MLX5_CAP_GEN(dev, roce)); +} + static int handle_hca_cap_roce(struct mlx5_core_dev *dev, void *set_ctx) { void *set_hca_cap; int err; - if (!MLX5_CAP_GEN(dev, roce)) + if (is_roce_fw_disabled(dev)) return 0; err = mlx5_core_get_caps(dev, MLX5_CAP_ROCE); @@ -975,25 +992,34 @@ static int mlx5_function_setup(struct mlx5_core_dev *dev, bool boot) if (mlx5_core_is_pf(dev)) pcie_print_link_status(dev->pdev); + err = mlx5_tout_init(dev); + if (err) { + mlx5_core_err(dev, "Failed initializing timeouts, aborting\n"); + return err; + } + /* wait for firmware to accept initialization segments configurations */ - err = wait_fw_init(dev, FW_PRE_INIT_TIMEOUT_MILI, FW_INIT_WARN_MESSAGE_INTERVAL); + err = wait_fw_init(dev, mlx5_tout_ms(dev, FW_PRE_INIT_TIMEOUT), + mlx5_tout_ms(dev, FW_PRE_INIT_WARN_MESSAGE_INTERVAL)); if (err) { - mlx5_core_err(dev, "Firmware over %d MS in pre-initializing state, aborting\n", - FW_PRE_INIT_TIMEOUT_MILI); - return err; + mlx5_core_err(dev, "Firmware over %llu MS in pre-initializing state, aborting\n", + mlx5_tout_ms(dev, FW_PRE_INIT_TIMEOUT)); + goto err_tout_cleanup; } err = mlx5_cmd_init(dev); if (err) { mlx5_core_err(dev, "Failed initializing command interface, aborting\n"); - return err; + goto err_tout_cleanup; } - err = wait_fw_init(dev, FW_INIT_TIMEOUT_MILI, 0); + mlx5_tout_query_iseg(dev); + + err = wait_fw_init(dev, mlx5_tout_ms(dev, FW_INIT), 0); if (err) { - mlx5_core_err(dev, "Firmware over %d MS in initializing state, aborting\n", - FW_INIT_TIMEOUT_MILI); + mlx5_core_err(dev, "Firmware over %llu MS in initializing state, aborting\n", + mlx5_tout_ms(dev, FW_INIT)); goto err_cmd_cleanup; } @@ -1017,6 +1043,12 @@ static int mlx5_function_setup(struct mlx5_core_dev *dev, bool boot) goto err_disable_hca; } + err = mlx5_tout_query_dtor(dev); + if (err) { + mlx5_core_err(dev, "failed to read dtor\n"); + goto reclaim_boot_pages; + } + err = set_hca_ctrl(dev); if (err) { mlx5_core_err(dev, "set_hca_ctrl failed\n"); @@ -1062,6 +1094,8 @@ err_disable_hca: err_cmd_cleanup: mlx5_cmd_set_state(dev, MLX5_CMDIF_STATE_DOWN); mlx5_cmd_cleanup(dev); +err_tout_cleanup: + mlx5_tout_cleanup(dev); return err; } @@ -1080,6 +1114,7 @@ static int mlx5_function_teardown(struct mlx5_core_dev *dev, bool boot) mlx5_core_disable_hca(dev, 0); mlx5_cmd_set_state(dev, MLX5_CMDIF_STATE_DOWN); mlx5_cmd_cleanup(dev); + mlx5_tout_cleanup(dev); return 0; } @@ -1381,6 +1416,7 @@ static const int types[] = { MLX5_CAP_TLS, MLX5_CAP_VDPA_EMULATION, MLX5_CAP_IPSEC, + MLX5_CAP_PORT_SELECTION, }; static void mlx5_hca_caps_free(struct mlx5_core_dev *dev) @@ -1538,8 +1574,6 @@ static int probe_one(struct pci_dev *pdev, const struct pci_device_id *id) pci_save_state(pdev); devlink_register(devlink); - if (!mlx5_core_is_mp_slave(dev)) - devlink_reload_enable(devlink); return 0; err_init_one: @@ -1559,7 +1593,6 @@ static void remove_one(struct pci_dev *pdev) struct mlx5_core_dev *dev = pci_get_drvdata(pdev); struct devlink *devlink = priv_to_devlink(dev); - devlink_reload_disable(devlink); devlink_unregister(devlink); mlx5_crdump_disable(dev); mlx5_drain_health_wq(dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c index 110c0837f95b..f6b5451328fc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c @@ -38,6 +38,7 @@ #include #include "mlx5_core.h" #include "lib/eq.h" +#include "lib/tout.h" enum { MLX5_PAGES_CANT_GIVE = 0, @@ -64,11 +65,6 @@ struct fw_page { unsigned int free_count; }; -enum { - MAX_RECLAIM_TIME_MSECS = 5000, - MAX_RECLAIM_VFS_PAGES_TIME_MSECS = 2 * 1000 * 60, -}; - enum { MLX5_MAX_RECLAIM_TIME_MILI = 5000, MLX5_NUM_4K_IN_PAGE = PAGE_SIZE / MLX5_ADAPTER_PAGE_SIZE, @@ -641,7 +637,8 @@ static int optimal_reclaimed_pages(void) static int mlx5_reclaim_root_pages(struct mlx5_core_dev *dev, struct rb_root *root, u16 func_id) { - unsigned long end = jiffies + msecs_to_jiffies(MAX_RECLAIM_TIME_MSECS); + u64 recl_pages_to_jiffies = msecs_to_jiffies(mlx5_tout_ms(dev, RECLAIM_PAGES)); + unsigned long end = jiffies + recl_pages_to_jiffies; while (!RB_EMPTY_ROOT(root)) { int nclaimed; @@ -656,7 +653,7 @@ static int mlx5_reclaim_root_pages(struct mlx5_core_dev *dev, } if (nclaimed) - end = jiffies + msecs_to_jiffies(MAX_RECLAIM_TIME_MSECS); + end = jiffies + recl_pages_to_jiffies; if (time_after(jiffies, end)) { mlx5_core_warn(dev, "FW did not return all pages. giving up...\n"); @@ -727,7 +724,8 @@ void mlx5_pagealloc_stop(struct mlx5_core_dev *dev) int mlx5_wait_for_pages(struct mlx5_core_dev *dev, int *pages) { - unsigned long end = jiffies + msecs_to_jiffies(MAX_RECLAIM_VFS_PAGES_TIME_MSECS); + u64 recl_vf_pages_to_jiffies = msecs_to_jiffies(mlx5_tout_ms(dev, RECLAIM_VFS_PAGES)); + unsigned long end = jiffies + recl_vf_pages_to_jiffies; int prev_pages = *pages; /* In case of internal error we will free the pages manually later */ @@ -743,7 +741,7 @@ int mlx5_wait_for_pages(struct mlx5_core_dev *dev, int *pages) return -ETIMEDOUT; } if (*pages < prev_pages) { - end = jiffies + msecs_to_jiffies(MAX_RECLAIM_VFS_PAGES_TIME_MSECS); + end = jiffies + recl_vf_pages_to_jiffies; prev_pages = *pages; } msleep(50); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c index 3cf272fa2164..7b4783ce213e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c @@ -47,7 +47,6 @@ static int mlx5_sf_dev_probe(struct auxiliary_device *adev, const struct auxilia goto init_one_err; } devlink_register(devlink); - devlink_reload_enable(devlink); return 0; init_one_err: @@ -62,10 +61,8 @@ mdev_err: static void mlx5_sf_dev_remove(struct auxiliary_device *adev) { struct mlx5_sf_dev *sf_dev = container_of(adev, struct mlx5_sf_dev, adev); - struct devlink *devlink; + struct devlink *devlink = priv_to_devlink(sf_dev->mdev); - devlink = priv_to_devlink(sf_dev->mdev); - devlink_reload_disable(devlink); devlink_unregister(devlink); mlx5_uninit_one(sf_dev->mdev); iounmap(sf_dev->mdev->iseg); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c index 13891fdc607e..e1bb3acf45e6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c @@ -323,7 +323,7 @@ mlx5_sf_new_check_attr(struct mlx5_core_dev *dev, const struct devlink_port_new_ NL_SET_ERR_MSG_MOD(extack, "External controller is unsupported"); return -EOPNOTSUPP; } - if (new_attr->pfnum != PCI_FUNC(dev->pdev->devfn)) { + if (new_attr->pfnum != mlx5_get_dev_index(dev)) { NL_SET_ERR_MSG_MOD(extack, "Invalid pfnum supplied"); return -EOPNOTSUPP; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c index 50630112c8ff..07936841ce99 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c @@ -854,6 +854,7 @@ mlx5dr_action_create_mult_dest_tbl(struct mlx5dr_domain *dmn, struct mlx5dr_action *action; bool reformat_req = false; u32 num_of_ref = 0; + u32 ref_act_cnt; int ret; int i; @@ -862,11 +863,14 @@ mlx5dr_action_create_mult_dest_tbl(struct mlx5dr_domain *dmn, return NULL; } - hw_dests = kzalloc(sizeof(*hw_dests) * num_of_dests, GFP_KERNEL); + hw_dests = kcalloc(num_of_dests, sizeof(*hw_dests), GFP_KERNEL); if (!hw_dests) return NULL; - ref_actions = kzalloc(sizeof(*ref_actions) * num_of_dests * 2, GFP_KERNEL); + if (unlikely(check_mul_overflow(num_of_dests, 2u, &ref_act_cnt))) + goto free_hw_dests; + + ref_actions = kcalloc(ref_act_cnt, sizeof(*ref_actions), GFP_KERNEL); if (!ref_actions) goto free_hw_dests; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c index 230e920e3845..2632d5ae9bc0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c @@ -625,6 +625,19 @@ static void mlx5_cmd_dr_modify_header_dealloc(struct mlx5_flow_root_namespace *n mlx5dr_action_destroy(modify_hdr->action.dr_action); } +static int +mlx5_cmd_dr_destroy_match_definer(struct mlx5_flow_root_namespace *ns, + int definer_id) +{ + return -EOPNOTSUPP; +} + +static int mlx5_cmd_dr_create_match_definer(struct mlx5_flow_root_namespace *ns, + u16 format_id, u32 *match_mask) +{ + return -EOPNOTSUPP; +} + static int mlx5_cmd_dr_delete_fte(struct mlx5_flow_root_namespace *ns, struct mlx5_flow_table *ft, struct fs_fte *fte) @@ -727,6 +740,8 @@ static const struct mlx5_flow_cmds mlx5_flow_cmds_dr = { .packet_reformat_dealloc = mlx5_cmd_dr_packet_reformat_dealloc, .modify_header_alloc = mlx5_cmd_dr_modify_header_alloc, .modify_header_dealloc = mlx5_cmd_dr_modify_header_dealloc, + .create_match_definer = mlx5_cmd_dr_create_match_definer, + .destroy_match_definer = mlx5_cmd_dr_destroy_match_definer, .set_peer = mlx5_cmd_dr_set_peer, .create_ns = mlx5_cmd_dr_create_ns, .destroy_ns = mlx5_cmd_dr_destroy_ns, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c index 4c1440a95ad7..8846d30a380a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c @@ -421,19 +421,21 @@ int mlx5_query_nic_vport_system_image_guid(struct mlx5_core_dev *mdev, { u32 *out; int outlen = MLX5_ST_SZ_BYTES(query_nic_vport_context_out); + int err; out = kvzalloc(outlen, GFP_KERNEL); if (!out) return -ENOMEM; - mlx5_query_nic_vport_context(mdev, 0, out); + err = mlx5_query_nic_vport_context(mdev, 0, out); + if (err) + goto out; *system_image_guid = MLX5_GET64(query_nic_vport_context_out, out, nic_vport_context.system_image_guid); - +out: kvfree(out); - - return 0; + return err; } EXPORT_SYMBOL_GPL(mlx5_query_nic_vport_system_image_guid); @@ -1133,19 +1135,20 @@ EXPORT_SYMBOL_GPL(mlx5_nic_vport_unaffiliate_multiport); u64 mlx5_query_nic_system_image_guid(struct mlx5_core_dev *mdev) { int port_type_cap = MLX5_CAP_GEN(mdev, port_type); - u64 tmp = 0; + u64 tmp; + int err; if (mdev->sys_image_guid) return mdev->sys_image_guid; if (port_type_cap == MLX5_CAP_PORT_TYPE_ETH) - mlx5_query_nic_vport_system_image_guid(mdev, &tmp); + err = mlx5_query_nic_vport_system_image_guid(mdev, &tmp); else - mlx5_query_hca_vport_system_image_guid(mdev, &tmp); + err = mlx5_query_hca_vport_system_image_guid(mdev, &tmp); - mdev->sys_image_guid = tmp; + mdev->sys_image_guid = err ? 0 : tmp; - return tmp; + return mdev->sys_image_guid; } EXPORT_SYMBOL_GPL(mlx5_query_nic_system_image_guid); diff --git a/drivers/net/ethernet/mellanox/mlxfw/mlxfw.h b/drivers/net/ethernet/mellanox/mlxfw/mlxfw.h index 7654841a05c2..e6475ea77cd1 100644 --- a/drivers/net/ethernet/mellanox/mlxfw/mlxfw.h +++ b/drivers/net/ethernet/mellanox/mlxfw/mlxfw.h @@ -19,7 +19,7 @@ struct mlxfw_dev { static inline struct device *mlxfw_dev_dev(struct mlxfw_dev *mlxfw_dev) { - return mlxfw_dev->devlink->dev; + return devlink_to_dev(mlxfw_dev->devlink); } #define MLXFW_PRFX "mlxfw: " diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index 9e831e8b607a..3fd3812b8f31 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -2008,10 +2008,9 @@ __mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info, } if (!reload) { + devlink_set_features(devlink, DEVLINK_F_RELOAD); devlink_register(devlink); - devlink_reload_enable(devlink); } - return 0; err_driver_init: @@ -2075,10 +2074,9 @@ void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core, { struct devlink *devlink = priv_to_devlink(mlxsw_core); - if (!reload) { - devlink_reload_disable(devlink); + if (!reload) devlink_unregister(devlink); - } + if (devlink_is_reload_failed(devlink)) { if (!reload) /* Only the parts that were not de-initialized in the diff --git a/drivers/net/ethernet/mellanox/mlxsw/item.h b/drivers/net/ethernet/mellanox/mlxsw/item.h index e92cadc98128..ab70a873a01a 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/item.h +++ b/drivers/net/ethernet/mellanox/mlxsw/item.h @@ -270,11 +270,13 @@ static struct mlxsw_item __ITEM_NAME(_type, _cname, _iname) = { \ .size = {.bits = _sizebits,}, \ .name = #_type "_" #_cname "_" #_iname, \ }; \ -static inline u8 mlxsw_##_type##_##_cname##_##_iname##_get(const char *buf) \ +static inline u8 __maybe_unused \ +mlxsw_##_type##_##_cname##_##_iname##_get(const char *buf) \ { \ return __mlxsw_item_get8(buf, &__ITEM_NAME(_type, _cname, _iname), 0); \ } \ -static inline void mlxsw_##_type##_##_cname##_##_iname##_set(char *buf, u8 val)\ +static inline void __maybe_unused \ +mlxsw_##_type##_##_cname##_##_iname##_set(char *buf, u8 val) \ { \ __mlxsw_item_set8(buf, &__ITEM_NAME(_type, _cname, _iname), 0, val); \ } @@ -290,13 +292,13 @@ static struct mlxsw_item __ITEM_NAME(_type, _cname, _iname) = { \ .size = {.bits = _sizebits,}, \ .name = #_type "_" #_cname "_" #_iname, \ }; \ -static inline u8 \ +static inline u8 __maybe_unused \ mlxsw_##_type##_##_cname##_##_iname##_get(const char *buf, unsigned short index)\ { \ return __mlxsw_item_get8(buf, &__ITEM_NAME(_type, _cname, _iname), \ index); \ } \ -static inline void \ +static inline void __maybe_unused \ mlxsw_##_type##_##_cname##_##_iname##_set(char *buf, unsigned short index, \ u8 val) \ { \ @@ -311,11 +313,13 @@ static struct mlxsw_item __ITEM_NAME(_type, _cname, _iname) = { \ .size = {.bits = _sizebits,}, \ .name = #_type "_" #_cname "_" #_iname, \ }; \ -static inline u16 mlxsw_##_type##_##_cname##_##_iname##_get(const char *buf) \ +static inline u16 __maybe_unused \ +mlxsw_##_type##_##_cname##_##_iname##_get(const char *buf) \ { \ return __mlxsw_item_get16(buf, &__ITEM_NAME(_type, _cname, _iname), 0); \ } \ -static inline void mlxsw_##_type##_##_cname##_##_iname##_set(char *buf, u16 val)\ +static inline void __maybe_unused \ +mlxsw_##_type##_##_cname##_##_iname##_set(char *buf, u16 val) \ { \ __mlxsw_item_set16(buf, &__ITEM_NAME(_type, _cname, _iname), 0, val); \ } @@ -331,13 +335,13 @@ static struct mlxsw_item __ITEM_NAME(_type, _cname, _iname) = { \ .size = {.bits = _sizebits,}, \ .name = #_type "_" #_cname "_" #_iname, \ }; \ -static inline u16 \ +static inline u16 __maybe_unused \ mlxsw_##_type##_##_cname##_##_iname##_get(const char *buf, unsigned short index)\ { \ return __mlxsw_item_get16(buf, &__ITEM_NAME(_type, _cname, _iname), \ index); \ } \ -static inline void \ +static inline void __maybe_unused \ mlxsw_##_type##_##_cname##_##_iname##_set(char *buf, unsigned short index, \ u16 val) \ { \ @@ -352,11 +356,13 @@ static struct mlxsw_item __ITEM_NAME(_type, _cname, _iname) = { \ .size = {.bits = _sizebits,}, \ .name = #_type "_" #_cname "_" #_iname, \ }; \ -static inline u32 mlxsw_##_type##_##_cname##_##_iname##_get(const char *buf) \ +static inline u32 __maybe_unused \ +mlxsw_##_type##_##_cname##_##_iname##_get(const char *buf) \ { \ return __mlxsw_item_get32(buf, &__ITEM_NAME(_type, _cname, _iname), 0); \ } \ -static inline void mlxsw_##_type##_##_cname##_##_iname##_set(char *buf, u32 val)\ +static inline void __maybe_unused \ +mlxsw_##_type##_##_cname##_##_iname##_set(char *buf, u32 val) \ { \ __mlxsw_item_set32(buf, &__ITEM_NAME(_type, _cname, _iname), 0, val); \ } @@ -372,13 +378,13 @@ static struct mlxsw_item __ITEM_NAME(_type, _cname, _iname) = { \ .size = {.bits = _sizebits,}, \ .name = #_type "_" #_cname "_" #_iname, \ }; \ -static inline u32 \ +static inline u32 __maybe_unused \ mlxsw_##_type##_##_cname##_##_iname##_get(const char *buf, unsigned short index)\ { \ return __mlxsw_item_get32(buf, &__ITEM_NAME(_type, _cname, _iname), \ index); \ } \ -static inline void \ +static inline void __maybe_unused \ mlxsw_##_type##_##_cname##_##_iname##_set(char *buf, unsigned short index, \ u32 val) \ { \ @@ -393,11 +399,13 @@ static struct mlxsw_item __ITEM_NAME(_type, _cname, _iname) = { \ .size = {.bits = _sizebits,}, \ .name = #_type "_" #_cname "_" #_iname, \ }; \ -static inline u64 mlxsw_##_type##_##_cname##_##_iname##_get(const char *buf) \ +static inline u64 __maybe_unused \ +mlxsw_##_type##_##_cname##_##_iname##_get(const char *buf) \ { \ return __mlxsw_item_get64(buf, &__ITEM_NAME(_type, _cname, _iname), 0); \ } \ -static inline void mlxsw_##_type##_##_cname##_##_iname##_set(char *buf, u64 val)\ +static inline void __maybe_unused \ +mlxsw_##_type##_##_cname##_##_iname##_set(char *buf, u64 val) \ { \ __mlxsw_item_set64(buf, &__ITEM_NAME(_type, _cname, _iname), 0, val); \ } @@ -413,13 +421,13 @@ static struct mlxsw_item __ITEM_NAME(_type, _cname, _iname) = { \ .size = {.bits = _sizebits,}, \ .name = #_type "_" #_cname "_" #_iname, \ }; \ -static inline u64 \ +static inline u64 __maybe_unused \ mlxsw_##_type##_##_cname##_##_iname##_get(const char *buf, unsigned short index)\ { \ return __mlxsw_item_get64(buf, &__ITEM_NAME(_type, _cname, _iname), \ index); \ } \ -static inline void \ +static inline void __maybe_unused \ mlxsw_##_type##_##_cname##_##_iname##_set(char *buf, unsigned short index, \ u64 val) \ { \ @@ -433,19 +441,19 @@ static struct mlxsw_item __ITEM_NAME(_type, _cname, _iname) = { \ .size = {.bytes = _sizebytes,}, \ .name = #_type "_" #_cname "_" #_iname, \ }; \ -static inline void \ +static inline void __maybe_unused \ mlxsw_##_type##_##_cname##_##_iname##_memcpy_from(const char *buf, char *dst) \ { \ __mlxsw_item_memcpy_from(buf, dst, \ &__ITEM_NAME(_type, _cname, _iname), 0); \ } \ -static inline void \ +static inline void __maybe_unused \ mlxsw_##_type##_##_cname##_##_iname##_memcpy_to(char *buf, const char *src) \ { \ __mlxsw_item_memcpy_to(buf, src, \ &__ITEM_NAME(_type, _cname, _iname), 0); \ } \ -static inline char * \ +static inline char * __maybe_unused \ mlxsw_##_type##_##_cname##_##_iname##_data(char *buf) \ { \ return __mlxsw_item_data(buf, &__ITEM_NAME(_type, _cname, _iname), 0); \ @@ -460,7 +468,7 @@ static struct mlxsw_item __ITEM_NAME(_type, _cname, _iname) = { \ .size = {.bytes = _sizebytes,}, \ .name = #_type "_" #_cname "_" #_iname, \ }; \ -static inline void \ +static inline void __maybe_unused \ mlxsw_##_type##_##_cname##_##_iname##_memcpy_from(const char *buf, \ unsigned short index, \ char *dst) \ @@ -468,7 +476,7 @@ mlxsw_##_type##_##_cname##_##_iname##_memcpy_from(const char *buf, \ __mlxsw_item_memcpy_from(buf, dst, \ &__ITEM_NAME(_type, _cname, _iname), index); \ } \ -static inline void \ +static inline void __maybe_unused \ mlxsw_##_type##_##_cname##_##_iname##_memcpy_to(char *buf, \ unsigned short index, \ const char *src) \ @@ -476,7 +484,7 @@ mlxsw_##_type##_##_cname##_##_iname##_memcpy_to(char *buf, \ __mlxsw_item_memcpy_to(buf, src, \ &__ITEM_NAME(_type, _cname, _iname), index); \ } \ -static inline char * \ +static inline char * __maybe_unused \ mlxsw_##_type##_##_cname##_##_iname##_data(char *buf, unsigned short index) \ { \ return __mlxsw_item_data(buf, \ @@ -491,14 +499,14 @@ static struct mlxsw_item __ITEM_NAME(_type, _cname, _iname) = { \ .size = {.bytes = _sizebytes,}, \ .name = #_type "_" #_cname "_" #_iname, \ }; \ -static inline u8 \ +static inline u8 __maybe_unused \ mlxsw_##_type##_##_cname##_##_iname##_get(const char *buf, u16 index) \ { \ return __mlxsw_item_bit_array_get(buf, \ &__ITEM_NAME(_type, _cname, _iname), \ index); \ } \ -static inline void \ +static inline void __maybe_unused \ mlxsw_##_type##_##_cname##_##_iname##_set(char *buf, u16 index, u8 val) \ { \ return __mlxsw_item_bit_array_set(buf, \ diff --git a/drivers/net/ethernet/mellanox/mlxsw/minimal.c b/drivers/net/ethernet/mellanox/mlxsw/minimal.c index e0892f259adf..5d4dfa5ddbb5 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/minimal.c +++ b/drivers/net/ethernet/mellanox/mlxsw/minimal.c @@ -200,20 +200,16 @@ static int mlxsw_m_port_dev_addr_get(struct mlxsw_m_port *mlxsw_m_port) { struct mlxsw_m *mlxsw_m = mlxsw_m_port->mlxsw_m; - struct net_device *dev = mlxsw_m_port->dev; char ppad_pl[MLXSW_REG_PPAD_LEN]; + u8 addr[ETH_ALEN]; int err; mlxsw_reg_ppad_pack(ppad_pl, false, 0); err = mlxsw_reg_query(mlxsw_m->core, MLXSW_REG(ppad), ppad_pl); if (err) return err; - mlxsw_reg_ppad_mac_memcpy_from(ppad_pl, dev->dev_addr); - /* The last byte value in base mac address is guaranteed - * to be such it does not overflow when adding local_port - * value. - */ - dev->dev_addr[ETH_ALEN - 1] += mlxsw_m_port->module + 1; + mlxsw_reg_ppad_mac_memcpy_from(ppad_pl, addr); + eth_hw_addr_gen(mlxsw_m_port->dev, addr, mlxsw_m_port->module + 1); return 0; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index ed6c3356e4eb..48b817ba6d4e 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -4951,7 +4951,7 @@ enum mlxsw_reg_ppcnt_grp { MLXSW_REG_PPCNT_DISCARD_CNT = 0x6, MLXSW_REG_PPCNT_PRIO_CNT = 0x10, MLXSW_REG_PPCNT_TC_CNT = 0x11, - MLXSW_REG_PPCNT_TC_CONG_TC = 0x13, + MLXSW_REG_PPCNT_TC_CONG_CNT = 0x13, }; /* reg_ppcnt_grp @@ -5371,7 +5371,7 @@ MLXSW_ITEM64(reg, ppcnt, tx_pause_duration, MLXSW_ITEM64(reg, ppcnt, tx_pause_transition, MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x70, 0, 64); -/* Ethernet Per Traffic Group Counters */ +/* Ethernet Per Traffic Class Counters */ /* reg_ppcnt_tc_transmit_queue * Contains the transmit queue depth in cells of traffic class @@ -5398,6 +5398,12 @@ MLXSW_ITEM64(reg, ppcnt, tc_no_buffer_discard_uc, MLXSW_ITEM64(reg, ppcnt, wred_discard, MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x00, 0, 64); +/* reg_ppcnt_ecn_marked_tc + * Access: RO + */ +MLXSW_ITEM64(reg, ppcnt, ecn_marked_tc, + MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x08, 0, 64); + static inline void mlxsw_reg_ppcnt_pack(char *payload, u8 local_port, enum mlxsw_reg_ppcnt_grp grp, u8 prio_tc) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index d366786ce0f8..66c346a86ec5 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -316,11 +316,11 @@ static int mlxsw_sp_port_dev_addr_set(struct mlxsw_sp_port *mlxsw_sp_port, static int mlxsw_sp_port_dev_addr_init(struct mlxsw_sp_port *mlxsw_sp_port) { struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; - unsigned char *addr = mlxsw_sp_port->dev->dev_addr; - ether_addr_copy(addr, mlxsw_sp->base_mac); - addr[ETH_ALEN - 1] += mlxsw_sp_port->local_port; - return mlxsw_sp_port_dev_addr_set(mlxsw_sp_port, addr); + eth_hw_addr_gen(mlxsw_sp_port->dev, mlxsw_sp->base_mac, + mlxsw_sp_port->local_port); + return mlxsw_sp_port_dev_addr_set(mlxsw_sp_port, + mlxsw_sp_port->dev->dev_addr); } static int mlxsw_sp_port_max_mtu_get(struct mlxsw_sp_port *mlxsw_sp_port, int *p_max_mtu) @@ -824,12 +824,16 @@ mlxsw_sp_port_get_hw_xstats(struct net_device *dev, for (i = 0; i < TC_MAX_QUEUE; i++) { err = mlxsw_sp_port_get_stats_raw(dev, - MLXSW_REG_PPCNT_TC_CONG_TC, + MLXSW_REG_PPCNT_TC_CONG_CNT, i, ppcnt_pl); - if (!err) - xstats->wred_drop[i] = - mlxsw_reg_ppcnt_wred_discard_get(ppcnt_pl); + if (err) + goto tc_cnt; + xstats->wred_drop[i] = + mlxsw_reg_ppcnt_wred_discard_get(ppcnt_pl); + xstats->tc_ecn[i] = mlxsw_reg_ppcnt_ecn_marked_tc_get(ppcnt_pl); + +tc_cnt: err = mlxsw_sp_port_get_stats_raw(dev, MLXSW_REG_PPCNT_TC_CNT, i, ppcnt_pl); if (err) @@ -1035,6 +1039,8 @@ static int mlxsw_sp_setup_tc_block(struct mlxsw_sp_port *mlxsw_sp_port, return mlxsw_sp_setup_tc_block_clsact(mlxsw_sp_port, f, false); case FLOW_BLOCK_BINDER_TYPE_RED_EARLY_DROP: return mlxsw_sp_setup_tc_block_qevent_early_drop(mlxsw_sp_port, f); + case FLOW_BLOCK_BINDER_TYPE_RED_MARK: + return mlxsw_sp_setup_tc_block_qevent_mark(mlxsw_sp_port, f); default: return -EOPNOTSUPP; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index 0ebbd9b04b89..3ab57e98cad2 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -285,6 +285,7 @@ struct mlxsw_sp_port_vlan { /* No need an internal lock; At worse - miss a single periodic iteration */ struct mlxsw_sp_port_xstats { u64 ecn; + u64 tc_ecn[TC_MAX_QUEUE]; u64 wred_drop[TC_MAX_QUEUE]; u64 tail_drop[TC_MAX_QUEUE]; u64 backlog[TC_MAX_QUEUE]; @@ -1195,6 +1196,8 @@ int mlxsw_sp_setup_tc_fifo(struct mlxsw_sp_port *mlxsw_sp_port, struct tc_fifo_qopt_offload *p); int mlxsw_sp_setup_tc_block_qevent_early_drop(struct mlxsw_sp_port *mlxsw_sp_port, struct flow_block_offload *f); +int mlxsw_sp_setup_tc_block_qevent_mark(struct mlxsw_sp_port *mlxsw_sp_port, + struct flow_block_offload *f); /* spectrum_fid.c */ bool mlxsw_sp_fid_is_dummy(struct mlxsw_sp *mlxsw_sp, u16 fid_index); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c index 9958d503bf0e..ddb5ad88b350 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c @@ -50,12 +50,24 @@ struct mlxsw_sp_qdisc_ops { struct mlxsw_sp_qdisc *(*find_class)(struct mlxsw_sp_qdisc *mlxsw_sp_qdisc, u32 parent); unsigned int num_classes; + + u8 (*get_prio_bitmap)(struct mlxsw_sp_qdisc *mlxsw_sp_qdisc, + struct mlxsw_sp_qdisc *child); + int (*get_tclass_num)(struct mlxsw_sp_qdisc *mlxsw_sp_qdisc, + struct mlxsw_sp_qdisc *child); +}; + +struct mlxsw_sp_qdisc_ets_band { + u8 prio_bitmap; + int tclass_num; +}; + +struct mlxsw_sp_qdisc_ets_data { + struct mlxsw_sp_qdisc_ets_band bands[IEEE_8021QAZ_MAX_TCS]; }; struct mlxsw_sp_qdisc { u32 handle; - int tclass_num; - u8 prio_bitmap; union { struct red_stats red; } xstats_base; @@ -67,6 +79,10 @@ struct mlxsw_sp_qdisc { u64 backlog; } stats_base; + union { + struct mlxsw_sp_qdisc_ets_data *ets_data; + }; + struct mlxsw_sp_qdisc_ops *ops; struct mlxsw_sp_qdisc *parent; struct mlxsw_sp_qdisc *qdiscs; @@ -141,8 +157,7 @@ mlxsw_sp_qdisc_walk_cb_find(struct mlxsw_sp_qdisc *qdisc, void *data) } static struct mlxsw_sp_qdisc * -mlxsw_sp_qdisc_find(struct mlxsw_sp_port *mlxsw_sp_port, u32 parent, - bool root_only) +mlxsw_sp_qdisc_find(struct mlxsw_sp_port *mlxsw_sp_port, u32 parent) { struct mlxsw_sp_qdisc_state *qdisc_state = mlxsw_sp_port->qdisc; @@ -150,8 +165,6 @@ mlxsw_sp_qdisc_find(struct mlxsw_sp_port *mlxsw_sp_port, u32 parent, return NULL; if (parent == TC_H_ROOT) return &qdisc_state->root_qdisc; - if (root_only) - return NULL; return mlxsw_sp_qdisc_walk(&qdisc_state->root_qdisc, mlxsw_sp_qdisc_walk_cb_find, &parent); } @@ -187,6 +200,32 @@ mlxsw_sp_qdisc_reduce_parent_backlog(struct mlxsw_sp_qdisc *mlxsw_sp_qdisc) tmp->stats_base.backlog -= mlxsw_sp_qdisc->stats_base.backlog; } +static u8 mlxsw_sp_qdisc_get_prio_bitmap(struct mlxsw_sp_port *mlxsw_sp_port, + struct mlxsw_sp_qdisc *mlxsw_sp_qdisc) +{ + struct mlxsw_sp_qdisc *parent = mlxsw_sp_qdisc->parent; + + if (!parent) + return 0xff; + if (!parent->ops->get_prio_bitmap) + return mlxsw_sp_qdisc_get_prio_bitmap(mlxsw_sp_port, parent); + return parent->ops->get_prio_bitmap(parent, mlxsw_sp_qdisc); +} + +#define MLXSW_SP_PORT_DEFAULT_TCLASS 0 + +static int mlxsw_sp_qdisc_get_tclass_num(struct mlxsw_sp_port *mlxsw_sp_port, + struct mlxsw_sp_qdisc *mlxsw_sp_qdisc) +{ + struct mlxsw_sp_qdisc *parent = mlxsw_sp_qdisc->parent; + + if (!parent) + return MLXSW_SP_PORT_DEFAULT_TCLASS; + if (!parent->ops->get_tclass_num) + return mlxsw_sp_qdisc_get_tclass_num(mlxsw_sp_port, parent); + return parent->ops->get_tclass_num(parent, mlxsw_sp_qdisc); +} + static int mlxsw_sp_qdisc_destroy(struct mlxsw_sp_port *mlxsw_sp_port, struct mlxsw_sp_qdisc *mlxsw_sp_qdisc) @@ -194,6 +233,7 @@ mlxsw_sp_qdisc_destroy(struct mlxsw_sp_port *mlxsw_sp_port, struct mlxsw_sp_qdisc *root_qdisc = &mlxsw_sp_port->qdisc->root_qdisc; int err_hdroom = 0; int err = 0; + int i; if (!mlxsw_sp_qdisc) return 0; @@ -211,6 +251,9 @@ mlxsw_sp_qdisc_destroy(struct mlxsw_sp_port *mlxsw_sp_port, if (!mlxsw_sp_qdisc->ops) return 0; + for (i = 0; i < mlxsw_sp_qdisc->num_classes; i++) + mlxsw_sp_qdisc_destroy(mlxsw_sp_port, + &mlxsw_sp_qdisc->qdiscs[i]); mlxsw_sp_qdisc_reduce_parent_backlog(mlxsw_sp_qdisc); if (mlxsw_sp_qdisc->ops->destroy) err = mlxsw_sp_qdisc->ops->destroy(mlxsw_sp_port, @@ -226,6 +269,78 @@ mlxsw_sp_qdisc_destroy(struct mlxsw_sp_port *mlxsw_sp_port, return err_hdroom ?: err; } +struct mlxsw_sp_qdisc_tree_validate { + bool forbid_ets; + bool forbid_tbf; + bool forbid_red; +}; + +static int +__mlxsw_sp_qdisc_tree_validate(struct mlxsw_sp_qdisc *mlxsw_sp_qdisc, + struct mlxsw_sp_qdisc_tree_validate validate); + +static int +mlxsw_sp_qdisc_tree_validate_children(struct mlxsw_sp_qdisc *mlxsw_sp_qdisc, + struct mlxsw_sp_qdisc_tree_validate validate) +{ + unsigned int i; + int err; + + for (i = 0; i < mlxsw_sp_qdisc->num_classes; i++) { + err = __mlxsw_sp_qdisc_tree_validate(&mlxsw_sp_qdisc->qdiscs[i], + validate); + if (err) + return err; + } + + return 0; +} + +static int +__mlxsw_sp_qdisc_tree_validate(struct mlxsw_sp_qdisc *mlxsw_sp_qdisc, + struct mlxsw_sp_qdisc_tree_validate validate) +{ + if (!mlxsw_sp_qdisc->ops) + return 0; + + switch (mlxsw_sp_qdisc->ops->type) { + case MLXSW_SP_QDISC_FIFO: + break; + case MLXSW_SP_QDISC_RED: + if (validate.forbid_red) + return -EINVAL; + validate.forbid_red = true; + validate.forbid_ets = true; + break; + case MLXSW_SP_QDISC_TBF: + if (validate.forbid_tbf) + return -EINVAL; + validate.forbid_tbf = true; + validate.forbid_ets = true; + break; + case MLXSW_SP_QDISC_PRIO: + case MLXSW_SP_QDISC_ETS: + if (validate.forbid_ets) + return -EINVAL; + validate.forbid_ets = true; + break; + default: + WARN_ON(1); + return -EINVAL; + } + + return mlxsw_sp_qdisc_tree_validate_children(mlxsw_sp_qdisc, validate); +} + +static int mlxsw_sp_qdisc_tree_validate(struct mlxsw_sp_port *mlxsw_sp_port) +{ + struct mlxsw_sp_qdisc_tree_validate validate = {}; + struct mlxsw_sp_qdisc *mlxsw_sp_qdisc; + + mlxsw_sp_qdisc = &mlxsw_sp_port->qdisc->root_qdisc; + return __mlxsw_sp_qdisc_tree_validate(mlxsw_sp_qdisc, validate); +} + static int mlxsw_sp_qdisc_create(struct mlxsw_sp_port *mlxsw_sp_port, u32 handle, struct mlxsw_sp_qdisc *mlxsw_sp_qdisc, @@ -268,6 +383,10 @@ static int mlxsw_sp_qdisc_create(struct mlxsw_sp_port *mlxsw_sp_port, mlxsw_sp_qdisc->num_classes = ops->num_classes; mlxsw_sp_qdisc->ops = ops; mlxsw_sp_qdisc->handle = handle; + err = mlxsw_sp_qdisc_tree_validate(mlxsw_sp_port); + if (err) + goto err_replace; + err = ops->replace(mlxsw_sp_port, handle, mlxsw_sp_qdisc, params); if (err) goto err_replace; @@ -406,13 +525,17 @@ mlxsw_sp_qdisc_collect_tc_stats(struct mlxsw_sp_port *mlxsw_sp_port, u64 *p_tx_bytes, u64 *p_tx_packets, u64 *p_drops, u64 *p_backlog) { - int tclass_num = mlxsw_sp_qdisc->tclass_num; struct mlxsw_sp_port_xstats *xstats; u64 tx_bytes, tx_packets; + u8 prio_bitmap; + int tclass_num; + prio_bitmap = mlxsw_sp_qdisc_get_prio_bitmap(mlxsw_sp_port, + mlxsw_sp_qdisc); + tclass_num = mlxsw_sp_qdisc_get_tclass_num(mlxsw_sp_port, + mlxsw_sp_qdisc); xstats = &mlxsw_sp_port->periodic_hw_stats.xstats; - mlxsw_sp_qdisc_bstats_per_priority_get(xstats, - mlxsw_sp_qdisc->prio_bitmap, + mlxsw_sp_qdisc_bstats_per_priority_get(xstats, prio_bitmap, &tx_packets, &tx_bytes); *p_tx_packets += tx_packets; @@ -506,19 +629,24 @@ static void mlxsw_sp_setup_tc_qdisc_red_clean_stats(struct mlxsw_sp_port *mlxsw_sp_port, struct mlxsw_sp_qdisc *mlxsw_sp_qdisc) { - int tclass_num = mlxsw_sp_qdisc->tclass_num; struct mlxsw_sp_qdisc_stats *stats_base; struct mlxsw_sp_port_xstats *xstats; struct red_stats *red_base; + u8 prio_bitmap; + int tclass_num; + prio_bitmap = mlxsw_sp_qdisc_get_prio_bitmap(mlxsw_sp_port, + mlxsw_sp_qdisc); + tclass_num = mlxsw_sp_qdisc_get_tclass_num(mlxsw_sp_port, + mlxsw_sp_qdisc); xstats = &mlxsw_sp_port->periodic_hw_stats.xstats; stats_base = &mlxsw_sp_qdisc->stats_base; red_base = &mlxsw_sp_qdisc->xstats_base.red; - mlxsw_sp_qdisc_bstats_per_priority_get(xstats, - mlxsw_sp_qdisc->prio_bitmap, + mlxsw_sp_qdisc_bstats_per_priority_get(xstats, prio_bitmap, &stats_base->tx_packets, &stats_base->tx_bytes); + red_base->prob_mark = xstats->tc_ecn[tclass_num]; red_base->prob_drop = xstats->wred_drop[tclass_num]; red_base->pdrop = mlxsw_sp_xstats_tail_drop(xstats, tclass_num); @@ -532,8 +660,10 @@ static int mlxsw_sp_qdisc_red_destroy(struct mlxsw_sp_port *mlxsw_sp_port, struct mlxsw_sp_qdisc *mlxsw_sp_qdisc) { - return mlxsw_sp_tclass_congestion_disable(mlxsw_sp_port, - mlxsw_sp_qdisc->tclass_num); + int tclass_num = mlxsw_sp_qdisc_get_tclass_num(mlxsw_sp_port, + mlxsw_sp_qdisc); + + return mlxsw_sp_tclass_congestion_disable(mlxsw_sp_port, tclass_num); } static int @@ -563,6 +693,14 @@ mlxsw_sp_qdisc_red_check_params(struct mlxsw_sp_port *mlxsw_sp_port, return 0; } +static int +mlxsw_sp_qdisc_future_fifo_replace(struct mlxsw_sp_port *mlxsw_sp_port, + u32 handle, unsigned int band, + struct mlxsw_sp_qdisc *child_qdisc); +static void +mlxsw_sp_qdisc_future_fifos_init(struct mlxsw_sp_port *mlxsw_sp_port, + u32 handle); + static int mlxsw_sp_qdisc_red_replace(struct mlxsw_sp_port *mlxsw_sp_port, u32 handle, struct mlxsw_sp_qdisc *mlxsw_sp_qdisc, @@ -570,9 +708,19 @@ mlxsw_sp_qdisc_red_replace(struct mlxsw_sp_port *mlxsw_sp_port, u32 handle, { struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; struct tc_red_qopt_offload_params *p = params; - int tclass_num = mlxsw_sp_qdisc->tclass_num; + int tclass_num; u32 min, max; u64 prob; + int err; + + err = mlxsw_sp_qdisc_future_fifo_replace(mlxsw_sp_port, handle, 0, + &mlxsw_sp_qdisc->qdiscs[0]); + if (err) + return err; + mlxsw_sp_qdisc_future_fifos_init(mlxsw_sp_port, TC_H_UNSPEC); + + tclass_num = mlxsw_sp_qdisc_get_tclass_num(mlxsw_sp_port, + mlxsw_sp_qdisc); /* calculate probability in percentage */ prob = p->probability; @@ -615,22 +763,27 @@ mlxsw_sp_qdisc_get_red_xstats(struct mlxsw_sp_port *mlxsw_sp_port, void *xstats_ptr) { struct red_stats *xstats_base = &mlxsw_sp_qdisc->xstats_base.red; - int tclass_num = mlxsw_sp_qdisc->tclass_num; struct mlxsw_sp_port_xstats *xstats; struct red_stats *res = xstats_ptr; - int early_drops, pdrops; + int early_drops, marks, pdrops; + int tclass_num; + tclass_num = mlxsw_sp_qdisc_get_tclass_num(mlxsw_sp_port, + mlxsw_sp_qdisc); xstats = &mlxsw_sp_port->periodic_hw_stats.xstats; early_drops = xstats->wred_drop[tclass_num] - xstats_base->prob_drop; + marks = xstats->tc_ecn[tclass_num] - xstats_base->prob_mark; pdrops = mlxsw_sp_xstats_tail_drop(xstats, tclass_num) - xstats_base->pdrop; res->pdrop += pdrops; res->prob_drop += early_drops; + res->prob_mark += marks; xstats_base->pdrop += pdrops; xstats_base->prob_drop += early_drops; + xstats_base->prob_mark += marks; return 0; } @@ -639,16 +792,19 @@ mlxsw_sp_qdisc_get_red_stats(struct mlxsw_sp_port *mlxsw_sp_port, struct mlxsw_sp_qdisc *mlxsw_sp_qdisc, struct tc_qopt_offload_stats *stats_ptr) { - int tclass_num = mlxsw_sp_qdisc->tclass_num; struct mlxsw_sp_qdisc_stats *stats_base; struct mlxsw_sp_port_xstats *xstats; u64 overlimits; + int tclass_num; + tclass_num = mlxsw_sp_qdisc_get_tclass_num(mlxsw_sp_port, + mlxsw_sp_qdisc); xstats = &mlxsw_sp_port->periodic_hw_stats.xstats; stats_base = &mlxsw_sp_qdisc->stats_base; mlxsw_sp_qdisc_get_tc_stats(mlxsw_sp_port, mlxsw_sp_qdisc, stats_ptr); - overlimits = xstats->wred_drop[tclass_num] - stats_base->overlimits; + overlimits = xstats->wred_drop[tclass_num] + + xstats->tc_ecn[tclass_num] - stats_base->overlimits; stats_ptr->qstats->overlimits += overlimits; stats_base->overlimits += overlimits; @@ -660,11 +816,12 @@ static struct mlxsw_sp_qdisc * mlxsw_sp_qdisc_leaf_find_class(struct mlxsw_sp_qdisc *mlxsw_sp_qdisc, u32 parent) { - return NULL; + /* RED and TBF are formally classful qdiscs, but all class references, + * including X:0, just refer to the same one class. + */ + return &mlxsw_sp_qdisc->qdiscs[0]; } -#define MLXSW_SP_PORT_DEFAULT_TCLASS 0 - static struct mlxsw_sp_qdisc_ops mlxsw_sp_qdisc_ops_red = { .type = MLXSW_SP_QDISC_RED, .check_params = mlxsw_sp_qdisc_red_check_params, @@ -675,14 +832,19 @@ static struct mlxsw_sp_qdisc_ops mlxsw_sp_qdisc_ops_red = { .get_xstats = mlxsw_sp_qdisc_get_red_xstats, .clean_stats = mlxsw_sp_setup_tc_qdisc_red_clean_stats, .find_class = mlxsw_sp_qdisc_leaf_find_class, + .num_classes = 1, }; +static int mlxsw_sp_qdisc_graft(struct mlxsw_sp_port *mlxsw_sp_port, + struct mlxsw_sp_qdisc *mlxsw_sp_qdisc, + u8 band, u32 child_handle); + static int __mlxsw_sp_setup_tc_red(struct mlxsw_sp_port *mlxsw_sp_port, struct tc_red_qopt_offload *p) { struct mlxsw_sp_qdisc *mlxsw_sp_qdisc; - mlxsw_sp_qdisc = mlxsw_sp_qdisc_find(mlxsw_sp_port, p->parent, false); + mlxsw_sp_qdisc = mlxsw_sp_qdisc_find(mlxsw_sp_port, p->parent); if (!mlxsw_sp_qdisc) return -EOPNOTSUPP; @@ -704,6 +866,9 @@ static int __mlxsw_sp_setup_tc_red(struct mlxsw_sp_port *mlxsw_sp_port, case TC_RED_STATS: return mlxsw_sp_qdisc_get_stats(mlxsw_sp_port, mlxsw_sp_qdisc, &p->stats); + case TC_RED_GRAFT: + return mlxsw_sp_qdisc_graft(mlxsw_sp_port, mlxsw_sp_qdisc, 0, + p->child_handle); default: return -EOPNOTSUPP; } @@ -744,9 +909,12 @@ static int mlxsw_sp_qdisc_tbf_destroy(struct mlxsw_sp_port *mlxsw_sp_port, struct mlxsw_sp_qdisc *mlxsw_sp_qdisc) { + int tclass_num = mlxsw_sp_qdisc_get_tclass_num(mlxsw_sp_port, + mlxsw_sp_qdisc); + return mlxsw_sp_port_ets_maxrate_set(mlxsw_sp_port, MLXSW_REG_QEEC_HR_SUBGROUP, - mlxsw_sp_qdisc->tclass_num, 0, + tclass_num, 0, MLXSW_REG_QEEC_MAS_DIS, 0); } @@ -830,9 +998,19 @@ mlxsw_sp_qdisc_tbf_replace(struct mlxsw_sp_port *mlxsw_sp_port, u32 handle, { struct tc_tbf_qopt_offload_replace_params *p = params; u64 rate_kbps = mlxsw_sp_qdisc_tbf_rate_kbps(p); + int tclass_num; u8 burst_size; int err; + err = mlxsw_sp_qdisc_future_fifo_replace(mlxsw_sp_port, handle, 0, + &mlxsw_sp_qdisc->qdiscs[0]); + if (err) + return err; + mlxsw_sp_qdisc_future_fifos_init(mlxsw_sp_port, TC_H_UNSPEC); + + tclass_num = mlxsw_sp_qdisc_get_tclass_num(mlxsw_sp_port, + mlxsw_sp_qdisc); + err = mlxsw_sp_qdisc_tbf_bs(mlxsw_sp_port, p->max_size, &burst_size); if (WARN_ON_ONCE(err)) /* check_params above was supposed to reject this value. */ @@ -848,7 +1026,7 @@ mlxsw_sp_qdisc_tbf_replace(struct mlxsw_sp_port *mlxsw_sp_port, u32 handle, */ return mlxsw_sp_port_ets_maxrate_set(mlxsw_sp_port, MLXSW_REG_QEEC_HR_SUBGROUP, - mlxsw_sp_qdisc->tclass_num, 0, + tclass_num, 0, rate_kbps, burst_size); } @@ -881,6 +1059,7 @@ static struct mlxsw_sp_qdisc_ops mlxsw_sp_qdisc_ops_tbf = { .get_stats = mlxsw_sp_qdisc_get_tbf_stats, .clean_stats = mlxsw_sp_setup_tc_qdisc_leaf_clean_stats, .find_class = mlxsw_sp_qdisc_leaf_find_class, + .num_classes = 1, }; static int __mlxsw_sp_setup_tc_tbf(struct mlxsw_sp_port *mlxsw_sp_port, @@ -888,7 +1067,7 @@ static int __mlxsw_sp_setup_tc_tbf(struct mlxsw_sp_port *mlxsw_sp_port, { struct mlxsw_sp_qdisc *mlxsw_sp_qdisc; - mlxsw_sp_qdisc = mlxsw_sp_qdisc_find(mlxsw_sp_port, p->parent, false); + mlxsw_sp_qdisc = mlxsw_sp_qdisc_find(mlxsw_sp_port, p->parent); if (!mlxsw_sp_qdisc) return -EOPNOTSUPP; @@ -907,6 +1086,9 @@ static int __mlxsw_sp_setup_tc_tbf(struct mlxsw_sp_port *mlxsw_sp_port, case TC_TBF_STATS: return mlxsw_sp_qdisc_get_stats(mlxsw_sp_port, mlxsw_sp_qdisc, &p->stats); + case TC_TBF_GRAFT: + return mlxsw_sp_qdisc_graft(mlxsw_sp_port, mlxsw_sp_qdisc, 0, + p->child_handle); default: return -EOPNOTSUPP; } @@ -957,6 +1139,32 @@ static struct mlxsw_sp_qdisc_ops mlxsw_sp_qdisc_ops_fifo = { .clean_stats = mlxsw_sp_setup_tc_qdisc_leaf_clean_stats, }; +static int +mlxsw_sp_qdisc_future_fifo_replace(struct mlxsw_sp_port *mlxsw_sp_port, + u32 handle, unsigned int band, + struct mlxsw_sp_qdisc *child_qdisc) +{ + struct mlxsw_sp_qdisc_state *qdisc_state = mlxsw_sp_port->qdisc; + + if (handle == qdisc_state->future_handle && + qdisc_state->future_fifos[band]) + return mlxsw_sp_qdisc_replace(mlxsw_sp_port, TC_H_UNSPEC, + child_qdisc, + &mlxsw_sp_qdisc_ops_fifo, + NULL); + return 0; +} + +static void +mlxsw_sp_qdisc_future_fifos_init(struct mlxsw_sp_port *mlxsw_sp_port, + u32 handle) +{ + struct mlxsw_sp_qdisc_state *qdisc_state = mlxsw_sp_port->qdisc; + + qdisc_state->future_handle = handle; + memset(qdisc_state->future_fifos, 0, sizeof(qdisc_state->future_fifos)); +} + static int __mlxsw_sp_setup_tc_fifo(struct mlxsw_sp_port *mlxsw_sp_port, struct tc_fifo_qopt_offload *p) { @@ -965,16 +1173,15 @@ static int __mlxsw_sp_setup_tc_fifo(struct mlxsw_sp_port *mlxsw_sp_port, unsigned int band; u32 parent_handle; - mlxsw_sp_qdisc = mlxsw_sp_qdisc_find(mlxsw_sp_port, p->parent, false); + mlxsw_sp_qdisc = mlxsw_sp_qdisc_find(mlxsw_sp_port, p->parent); if (!mlxsw_sp_qdisc && p->handle == TC_H_UNSPEC) { parent_handle = TC_H_MAJ(p->parent); if (parent_handle != qdisc_state->future_handle) { /* This notifications is for a different Qdisc than * previously. Wipe the future cache. */ - memset(qdisc_state->future_fifos, 0, - sizeof(qdisc_state->future_fifos)); - qdisc_state->future_handle = parent_handle; + mlxsw_sp_qdisc_future_fifos_init(mlxsw_sp_port, + parent_handle); } band = TC_H_MIN(p->parent) - 1; @@ -1033,11 +1240,10 @@ static int __mlxsw_sp_qdisc_ets_destroy(struct mlxsw_sp_port *mlxsw_sp_port, mlxsw_sp_port_ets_set(mlxsw_sp_port, MLXSW_REG_QEEC_HR_SUBGROUP, i, 0, false, 0); - mlxsw_sp_qdisc_destroy(mlxsw_sp_port, - &mlxsw_sp_qdisc->qdiscs[i]); - mlxsw_sp_qdisc->qdiscs[i].prio_bitmap = 0; } + kfree(mlxsw_sp_qdisc->ets_data); + mlxsw_sp_qdisc->ets_data = NULL; return 0; } @@ -1066,6 +1272,31 @@ mlxsw_sp_qdisc_prio_check_params(struct mlxsw_sp_port *mlxsw_sp_port, return __mlxsw_sp_qdisc_ets_check_params(p->bands); } +static struct mlxsw_sp_qdisc * +mlxsw_sp_qdisc_walk_cb_clean_stats(struct mlxsw_sp_qdisc *mlxsw_sp_qdisc, + void *mlxsw_sp_port) +{ + u64 backlog; + + if (mlxsw_sp_qdisc->ops) { + backlog = mlxsw_sp_qdisc->stats_base.backlog; + if (mlxsw_sp_qdisc->ops->clean_stats) + mlxsw_sp_qdisc->ops->clean_stats(mlxsw_sp_port, + mlxsw_sp_qdisc); + mlxsw_sp_qdisc->stats_base.backlog = backlog; + } + + return NULL; +} + +static void +mlxsw_sp_qdisc_tree_clean_stats(struct mlxsw_sp_port *mlxsw_sp_port, + struct mlxsw_sp_qdisc *mlxsw_sp_qdisc) +{ + mlxsw_sp_qdisc_walk(mlxsw_sp_qdisc, mlxsw_sp_qdisc_walk_cb_clean_stats, + mlxsw_sp_port); +} + static int __mlxsw_sp_qdisc_ets_replace(struct mlxsw_sp_port *mlxsw_sp_port, struct mlxsw_sp_qdisc *mlxsw_sp_qdisc, @@ -1074,69 +1305,80 @@ __mlxsw_sp_qdisc_ets_replace(struct mlxsw_sp_port *mlxsw_sp_port, const unsigned int *weights, const u8 *priomap) { - struct mlxsw_sp_qdisc_state *qdisc_state = mlxsw_sp_port->qdisc; + struct mlxsw_sp_qdisc_ets_data *ets_data = mlxsw_sp_qdisc->ets_data; + struct mlxsw_sp_qdisc_ets_band *ets_band; struct mlxsw_sp_qdisc *child_qdisc; - int tclass, i, band, backlog; - u8 old_priomap; + u8 old_priomap, new_priomap; + int i, band; int err; + if (!ets_data) { + ets_data = kzalloc(sizeof(*ets_data), GFP_KERNEL); + if (!ets_data) + return -ENOMEM; + mlxsw_sp_qdisc->ets_data = ets_data; + + for (band = 0; band < mlxsw_sp_qdisc->num_classes; band++) { + int tclass_num = MLXSW_SP_PRIO_BAND_TO_TCLASS(band); + + ets_band = &ets_data->bands[band]; + ets_band->tclass_num = tclass_num; + } + } + for (band = 0; band < nbands; band++) { - tclass = MLXSW_SP_PRIO_BAND_TO_TCLASS(band); + int tclass_num; + child_qdisc = &mlxsw_sp_qdisc->qdiscs[band]; - old_priomap = child_qdisc->prio_bitmap; - child_qdisc->prio_bitmap = 0; + ets_band = &ets_data->bands[band]; + + tclass_num = ets_band->tclass_num; + old_priomap = ets_band->prio_bitmap; + new_priomap = 0; err = mlxsw_sp_port_ets_set(mlxsw_sp_port, MLXSW_REG_QEEC_HR_SUBGROUP, - tclass, 0, !!quanta[band], + tclass_num, 0, !!quanta[band], weights[band]); if (err) return err; for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) { if (priomap[i] == band) { - child_qdisc->prio_bitmap |= BIT(i); + new_priomap |= BIT(i); if (BIT(i) & old_priomap) continue; err = mlxsw_sp_port_prio_tc_set(mlxsw_sp_port, - i, tclass); + i, tclass_num); if (err) return err; } } - child_qdisc->tclass_num = tclass; + ets_band->prio_bitmap = new_priomap; - if (old_priomap != child_qdisc->prio_bitmap && - child_qdisc->ops && child_qdisc->ops->clean_stats) { - backlog = child_qdisc->stats_base.backlog; - child_qdisc->ops->clean_stats(mlxsw_sp_port, - child_qdisc); - child_qdisc->stats_base.backlog = backlog; - } + if (old_priomap != new_priomap) + mlxsw_sp_qdisc_tree_clean_stats(mlxsw_sp_port, + child_qdisc); - if (handle == qdisc_state->future_handle && - qdisc_state->future_fifos[band]) { - err = mlxsw_sp_qdisc_replace(mlxsw_sp_port, TC_H_UNSPEC, - child_qdisc, - &mlxsw_sp_qdisc_ops_fifo, - NULL); - if (err) - return err; - } + err = mlxsw_sp_qdisc_future_fifo_replace(mlxsw_sp_port, handle, + band, child_qdisc); + if (err) + return err; } for (; band < IEEE_8021QAZ_MAX_TCS; band++) { - tclass = MLXSW_SP_PRIO_BAND_TO_TCLASS(band); + ets_band = &ets_data->bands[band]; + ets_band->prio_bitmap = 0; + child_qdisc = &mlxsw_sp_qdisc->qdiscs[band]; - child_qdisc->prio_bitmap = 0; mlxsw_sp_qdisc_destroy(mlxsw_sp_port, child_qdisc); + mlxsw_sp_port_ets_set(mlxsw_sp_port, MLXSW_REG_QEEC_HR_SUBGROUP, - tclass, 0, false, 0); + ets_band->tclass_num, 0, false, 0); } - qdisc_state->future_handle = TC_H_UNSPEC; - memset(qdisc_state->future_fifos, 0, sizeof(qdisc_state->future_fifos)); + mlxsw_sp_qdisc_future_fifos_init(mlxsw_sp_port, TC_H_UNSPEC); return 0; } @@ -1238,6 +1480,31 @@ mlxsw_sp_qdisc_prio_find_class(struct mlxsw_sp_qdisc *mlxsw_sp_qdisc, return &mlxsw_sp_qdisc->qdiscs[band]; } +static struct mlxsw_sp_qdisc_ets_band * +mlxsw_sp_qdisc_ets_get_band(struct mlxsw_sp_qdisc *mlxsw_sp_qdisc, + struct mlxsw_sp_qdisc *child) +{ + unsigned int band = child - mlxsw_sp_qdisc->qdiscs; + + if (WARN_ON(band >= IEEE_8021QAZ_MAX_TCS)) + band = 0; + return &mlxsw_sp_qdisc->ets_data->bands[band]; +} + +static u8 +mlxsw_sp_qdisc_ets_get_prio_bitmap(struct mlxsw_sp_qdisc *mlxsw_sp_qdisc, + struct mlxsw_sp_qdisc *child) +{ + return mlxsw_sp_qdisc_ets_get_band(mlxsw_sp_qdisc, child)->prio_bitmap; +} + +static int +mlxsw_sp_qdisc_ets_get_tclass_num(struct mlxsw_sp_qdisc *mlxsw_sp_qdisc, + struct mlxsw_sp_qdisc *child) +{ + return mlxsw_sp_qdisc_ets_get_band(mlxsw_sp_qdisc, child)->tclass_num; +} + static struct mlxsw_sp_qdisc_ops mlxsw_sp_qdisc_ops_prio = { .type = MLXSW_SP_QDISC_PRIO, .check_params = mlxsw_sp_qdisc_prio_check_params, @@ -1248,6 +1515,8 @@ static struct mlxsw_sp_qdisc_ops mlxsw_sp_qdisc_ops_prio = { .clean_stats = mlxsw_sp_setup_tc_qdisc_prio_clean_stats, .find_class = mlxsw_sp_qdisc_prio_find_class, .num_classes = IEEE_8021QAZ_MAX_TCS, + .get_prio_bitmap = mlxsw_sp_qdisc_ets_get_prio_bitmap, + .get_tclass_num = mlxsw_sp_qdisc_ets_get_tclass_num, }; static int @@ -1299,6 +1568,8 @@ static struct mlxsw_sp_qdisc_ops mlxsw_sp_qdisc_ops_ets = { .clean_stats = mlxsw_sp_setup_tc_qdisc_prio_clean_stats, .find_class = mlxsw_sp_qdisc_prio_find_class, .num_classes = IEEE_8021QAZ_MAX_TCS, + .get_prio_bitmap = mlxsw_sp_qdisc_ets_get_prio_bitmap, + .get_tclass_num = mlxsw_sp_qdisc_ets_get_tclass_num, }; /* Linux allows linking of Qdiscs to arbitrary classes (so long as the resulting @@ -1326,10 +1597,9 @@ static struct mlxsw_sp_qdisc_ops mlxsw_sp_qdisc_ops_ets = { * grafted corresponds to the parent handle. If the two don't match, we * unoffload the child. */ -static int -__mlxsw_sp_qdisc_ets_graft(struct mlxsw_sp_port *mlxsw_sp_port, - struct mlxsw_sp_qdisc *mlxsw_sp_qdisc, - u8 band, u32 child_handle) +static int mlxsw_sp_qdisc_graft(struct mlxsw_sp_port *mlxsw_sp_port, + struct mlxsw_sp_qdisc *mlxsw_sp_qdisc, + u8 band, u32 child_handle) { struct mlxsw_sp_qdisc *old_qdisc; u32 parent; @@ -1362,21 +1632,12 @@ __mlxsw_sp_qdisc_ets_graft(struct mlxsw_sp_port *mlxsw_sp_port, return -EOPNOTSUPP; } -static int -mlxsw_sp_qdisc_prio_graft(struct mlxsw_sp_port *mlxsw_sp_port, - struct mlxsw_sp_qdisc *mlxsw_sp_qdisc, - struct tc_prio_qopt_offload_graft_params *p) -{ - return __mlxsw_sp_qdisc_ets_graft(mlxsw_sp_port, mlxsw_sp_qdisc, - p->band, p->child_handle); -} - static int __mlxsw_sp_setup_tc_prio(struct mlxsw_sp_port *mlxsw_sp_port, struct tc_prio_qopt_offload *p) { struct mlxsw_sp_qdisc *mlxsw_sp_qdisc; - mlxsw_sp_qdisc = mlxsw_sp_qdisc_find(mlxsw_sp_port, p->parent, true); + mlxsw_sp_qdisc = mlxsw_sp_qdisc_find(mlxsw_sp_port, p->parent); if (!mlxsw_sp_qdisc) return -EOPNOTSUPP; @@ -1396,8 +1657,9 @@ static int __mlxsw_sp_setup_tc_prio(struct mlxsw_sp_port *mlxsw_sp_port, return mlxsw_sp_qdisc_get_stats(mlxsw_sp_port, mlxsw_sp_qdisc, &p->stats); case TC_PRIO_GRAFT: - return mlxsw_sp_qdisc_prio_graft(mlxsw_sp_port, mlxsw_sp_qdisc, - &p->graft_params); + return mlxsw_sp_qdisc_graft(mlxsw_sp_port, mlxsw_sp_qdisc, + p->graft_params.band, + p->graft_params.child_handle); default: return -EOPNOTSUPP; } @@ -1420,7 +1682,7 @@ static int __mlxsw_sp_setup_tc_ets(struct mlxsw_sp_port *mlxsw_sp_port, { struct mlxsw_sp_qdisc *mlxsw_sp_qdisc; - mlxsw_sp_qdisc = mlxsw_sp_qdisc_find(mlxsw_sp_port, p->parent, true); + mlxsw_sp_qdisc = mlxsw_sp_qdisc_find(mlxsw_sp_port, p->parent); if (!mlxsw_sp_qdisc) return -EOPNOTSUPP; @@ -1440,9 +1702,9 @@ static int __mlxsw_sp_setup_tc_ets(struct mlxsw_sp_port *mlxsw_sp_port, return mlxsw_sp_qdisc_get_stats(mlxsw_sp_port, mlxsw_sp_qdisc, &p->stats); case TC_ETS_GRAFT: - return __mlxsw_sp_qdisc_ets_graft(mlxsw_sp_port, mlxsw_sp_qdisc, - p->graft_params.band, - p->graft_params.child_handle); + return mlxsw_sp_qdisc_graft(mlxsw_sp_port, mlxsw_sp_qdisc, + p->graft_params.band, + p->graft_params.child_handle); default: return -EOPNOTSUPP; } @@ -1472,6 +1734,7 @@ struct mlxsw_sp_qevent_binding { u32 handle; int tclass_num; enum mlxsw_sp_span_trigger span_trigger; + unsigned int action_mask; }; static LIST_HEAD(mlxsw_sp_qevent_block_cb_list); @@ -1482,8 +1745,10 @@ static int mlxsw_sp_qevent_span_configure(struct mlxsw_sp *mlxsw_sp, const struct mlxsw_sp_span_agent_parms *agent_parms, int *p_span_id) { + enum mlxsw_sp_span_trigger span_trigger = qevent_binding->span_trigger; struct mlxsw_sp_port *mlxsw_sp_port = qevent_binding->mlxsw_sp_port; struct mlxsw_sp_span_trigger_parms trigger_parms = {}; + bool ingress; int span_id; int err; @@ -1491,18 +1756,19 @@ static int mlxsw_sp_qevent_span_configure(struct mlxsw_sp *mlxsw_sp, if (err) return err; - err = mlxsw_sp_span_analyzed_port_get(mlxsw_sp_port, true); + ingress = mlxsw_sp_span_trigger_is_ingress(span_trigger); + err = mlxsw_sp_span_analyzed_port_get(mlxsw_sp_port, ingress); if (err) goto err_analyzed_port_get; trigger_parms.span_id = span_id; trigger_parms.probability_rate = 1; - err = mlxsw_sp_span_agent_bind(mlxsw_sp, qevent_binding->span_trigger, mlxsw_sp_port, + err = mlxsw_sp_span_agent_bind(mlxsw_sp, span_trigger, mlxsw_sp_port, &trigger_parms); if (err) goto err_agent_bind; - err = mlxsw_sp_span_trigger_enable(mlxsw_sp_port, qevent_binding->span_trigger, + err = mlxsw_sp_span_trigger_enable(mlxsw_sp_port, span_trigger, qevent_binding->tclass_num); if (err) goto err_trigger_enable; @@ -1511,10 +1777,10 @@ static int mlxsw_sp_qevent_span_configure(struct mlxsw_sp *mlxsw_sp, return 0; err_trigger_enable: - mlxsw_sp_span_agent_unbind(mlxsw_sp, qevent_binding->span_trigger, mlxsw_sp_port, + mlxsw_sp_span_agent_unbind(mlxsw_sp, span_trigger, mlxsw_sp_port, &trigger_parms); err_agent_bind: - mlxsw_sp_span_analyzed_port_put(mlxsw_sp_port, true); + mlxsw_sp_span_analyzed_port_put(mlxsw_sp_port, ingress); err_analyzed_port_get: mlxsw_sp_span_agent_put(mlxsw_sp, span_id); return err; @@ -1524,16 +1790,20 @@ static void mlxsw_sp_qevent_span_deconfigure(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_qevent_binding *qevent_binding, int span_id) { + enum mlxsw_sp_span_trigger span_trigger = qevent_binding->span_trigger; struct mlxsw_sp_port *mlxsw_sp_port = qevent_binding->mlxsw_sp_port; struct mlxsw_sp_span_trigger_parms trigger_parms = { .span_id = span_id, }; + bool ingress; - mlxsw_sp_span_trigger_disable(mlxsw_sp_port, qevent_binding->span_trigger, + ingress = mlxsw_sp_span_trigger_is_ingress(span_trigger); + + mlxsw_sp_span_trigger_disable(mlxsw_sp_port, span_trigger, qevent_binding->tclass_num); - mlxsw_sp_span_agent_unbind(mlxsw_sp, qevent_binding->span_trigger, mlxsw_sp_port, + mlxsw_sp_span_agent_unbind(mlxsw_sp, span_trigger, mlxsw_sp_port, &trigger_parms); - mlxsw_sp_span_analyzed_port_put(mlxsw_sp_port, true); + mlxsw_sp_span_analyzed_port_put(mlxsw_sp_port, ingress); mlxsw_sp_span_agent_put(mlxsw_sp, span_id); } @@ -1583,10 +1853,17 @@ static void mlxsw_sp_qevent_trap_deconfigure(struct mlxsw_sp *mlxsw_sp, mlxsw_sp_qevent_span_deconfigure(mlxsw_sp, qevent_binding, mall_entry->trap.span_id); } -static int mlxsw_sp_qevent_entry_configure(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_mall_entry *mall_entry, - struct mlxsw_sp_qevent_binding *qevent_binding) +static int +mlxsw_sp_qevent_entry_configure(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_mall_entry *mall_entry, + struct mlxsw_sp_qevent_binding *qevent_binding, + struct netlink_ext_ack *extack) { + if (!(BIT(mall_entry->type) & qevent_binding->action_mask)) { + NL_SET_ERR_MSG(extack, "Action not supported at this qevent"); + return -EOPNOTSUPP; + } + switch (mall_entry->type) { case MLXSW_SP_MALL_ACTION_TYPE_MIRROR: return mlxsw_sp_qevent_mirror_configure(mlxsw_sp, mall_entry, qevent_binding); @@ -1614,15 +1891,17 @@ static void mlxsw_sp_qevent_entry_deconfigure(struct mlxsw_sp *mlxsw_sp, } } -static int mlxsw_sp_qevent_binding_configure(struct mlxsw_sp_qevent_block *qevent_block, - struct mlxsw_sp_qevent_binding *qevent_binding) +static int +mlxsw_sp_qevent_binding_configure(struct mlxsw_sp_qevent_block *qevent_block, + struct mlxsw_sp_qevent_binding *qevent_binding, + struct netlink_ext_ack *extack) { struct mlxsw_sp_mall_entry *mall_entry; int err; list_for_each_entry(mall_entry, &qevent_block->mall_entry_list, list) { err = mlxsw_sp_qevent_entry_configure(qevent_block->mlxsw_sp, mall_entry, - qevent_binding); + qevent_binding, extack); if (err) goto err_entry_configure; } @@ -1646,13 +1925,17 @@ static void mlxsw_sp_qevent_binding_deconfigure(struct mlxsw_sp_qevent_block *qe qevent_binding); } -static int mlxsw_sp_qevent_block_configure(struct mlxsw_sp_qevent_block *qevent_block) +static int +mlxsw_sp_qevent_block_configure(struct mlxsw_sp_qevent_block *qevent_block, + struct netlink_ext_ack *extack) { struct mlxsw_sp_qevent_binding *qevent_binding; int err; list_for_each_entry(qevent_binding, &qevent_block->binding_list, list) { - err = mlxsw_sp_qevent_binding_configure(qevent_block, qevent_binding); + err = mlxsw_sp_qevent_binding_configure(qevent_block, + qevent_binding, + extack); if (err) goto err_binding_configure; } @@ -1737,7 +2020,7 @@ static int mlxsw_sp_qevent_mall_replace(struct mlxsw_sp *mlxsw_sp, list_add_tail(&mall_entry->list, &qevent_block->mall_entry_list); - err = mlxsw_sp_qevent_block_configure(qevent_block); + err = mlxsw_sp_qevent_block_configure(qevent_block, f->common.extack); if (err) goto err_block_configure; @@ -1825,7 +2108,8 @@ static void mlxsw_sp_qevent_block_release(void *cb_priv) static struct mlxsw_sp_qevent_binding * mlxsw_sp_qevent_binding_create(struct mlxsw_sp_port *mlxsw_sp_port, u32 handle, int tclass_num, - enum mlxsw_sp_span_trigger span_trigger) + enum mlxsw_sp_span_trigger span_trigger, + unsigned int action_mask) { struct mlxsw_sp_qevent_binding *binding; @@ -1837,6 +2121,7 @@ mlxsw_sp_qevent_binding_create(struct mlxsw_sp_port *mlxsw_sp_port, u32 handle, binding->handle = handle; binding->tclass_num = tclass_num; binding->span_trigger = span_trigger; + binding->action_mask = action_mask; return binding; } @@ -1862,9 +2147,11 @@ mlxsw_sp_qevent_binding_lookup(struct mlxsw_sp_qevent_block *block, return NULL; } -static int mlxsw_sp_setup_tc_block_qevent_bind(struct mlxsw_sp_port *mlxsw_sp_port, - struct flow_block_offload *f, - enum mlxsw_sp_span_trigger span_trigger) +static int +mlxsw_sp_setup_tc_block_qevent_bind(struct mlxsw_sp_port *mlxsw_sp_port, + struct flow_block_offload *f, + enum mlxsw_sp_span_trigger span_trigger, + unsigned int action_mask) { struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; struct mlxsw_sp_qevent_binding *qevent_binding; @@ -1872,6 +2159,7 @@ static int mlxsw_sp_setup_tc_block_qevent_bind(struct mlxsw_sp_port *mlxsw_sp_po struct flow_block_cb *block_cb; struct mlxsw_sp_qdisc *qdisc; bool register_block = false; + int tclass_num; int err; block_cb = flow_block_cb_lookup(f->block, mlxsw_sp_qevent_block_cb, mlxsw_sp); @@ -1904,14 +2192,19 @@ static int mlxsw_sp_setup_tc_block_qevent_bind(struct mlxsw_sp_port *mlxsw_sp_po goto err_binding_exists; } - qevent_binding = mlxsw_sp_qevent_binding_create(mlxsw_sp_port, f->sch->handle, - qdisc->tclass_num, span_trigger); + tclass_num = mlxsw_sp_qdisc_get_tclass_num(mlxsw_sp_port, qdisc); + qevent_binding = mlxsw_sp_qevent_binding_create(mlxsw_sp_port, + f->sch->handle, + tclass_num, + span_trigger, + action_mask); if (IS_ERR(qevent_binding)) { err = PTR_ERR(qevent_binding); goto err_binding_create; } - err = mlxsw_sp_qevent_binding_configure(qevent_block, qevent_binding); + err = mlxsw_sp_qevent_binding_configure(qevent_block, qevent_binding, + f->extack); if (err) goto err_binding_configure; @@ -1963,15 +2256,19 @@ static void mlxsw_sp_setup_tc_block_qevent_unbind(struct mlxsw_sp_port *mlxsw_sp } } -static int mlxsw_sp_setup_tc_block_qevent(struct mlxsw_sp_port *mlxsw_sp_port, - struct flow_block_offload *f, - enum mlxsw_sp_span_trigger span_trigger) +static int +mlxsw_sp_setup_tc_block_qevent(struct mlxsw_sp_port *mlxsw_sp_port, + struct flow_block_offload *f, + enum mlxsw_sp_span_trigger span_trigger, + unsigned int action_mask) { f->driver_block_list = &mlxsw_sp_qevent_block_cb_list; switch (f->command) { case FLOW_BLOCK_BIND: - return mlxsw_sp_setup_tc_block_qevent_bind(mlxsw_sp_port, f, span_trigger); + return mlxsw_sp_setup_tc_block_qevent_bind(mlxsw_sp_port, f, + span_trigger, + action_mask); case FLOW_BLOCK_UNBIND: mlxsw_sp_setup_tc_block_qevent_unbind(mlxsw_sp_port, f, span_trigger); return 0; @@ -1983,7 +2280,22 @@ static int mlxsw_sp_setup_tc_block_qevent(struct mlxsw_sp_port *mlxsw_sp_port, int mlxsw_sp_setup_tc_block_qevent_early_drop(struct mlxsw_sp_port *mlxsw_sp_port, struct flow_block_offload *f) { - return mlxsw_sp_setup_tc_block_qevent(mlxsw_sp_port, f, MLXSW_SP_SPAN_TRIGGER_EARLY_DROP); + unsigned int action_mask = BIT(MLXSW_SP_MALL_ACTION_TYPE_MIRROR) | + BIT(MLXSW_SP_MALL_ACTION_TYPE_TRAP); + + return mlxsw_sp_setup_tc_block_qevent(mlxsw_sp_port, f, + MLXSW_SP_SPAN_TRIGGER_EARLY_DROP, + action_mask); +} + +int mlxsw_sp_setup_tc_block_qevent_mark(struct mlxsw_sp_port *mlxsw_sp_port, + struct flow_block_offload *f) +{ + unsigned int action_mask = BIT(MLXSW_SP_MALL_ACTION_TYPE_MIRROR); + + return mlxsw_sp_setup_tc_block_qevent(mlxsw_sp_port, f, + MLXSW_SP_SPAN_TRIGGER_ECN, + action_mask); } int mlxsw_sp_tc_qdisc_init(struct mlxsw_sp_port *mlxsw_sp_port) @@ -1995,8 +2307,6 @@ int mlxsw_sp_tc_qdisc_init(struct mlxsw_sp_port *mlxsw_sp_port) return -ENOMEM; mutex_init(&qdisc_state->lock); - qdisc_state->root_qdisc.prio_bitmap = 0xff; - qdisc_state->root_qdisc.tclass_num = MLXSW_SP_PORT_DEFAULT_TCLASS; mlxsw_sp_port->qdisc = qdisc_state; return 0; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c index 3398cc01e5ec..f5f819aa9a65 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c @@ -1650,6 +1650,22 @@ void mlxsw_sp_span_trigger_disable(struct mlxsw_sp_port *mlxsw_sp_port, return trigger_entry->ops->disable(trigger_entry, mlxsw_sp_port, tc); } +bool mlxsw_sp_span_trigger_is_ingress(enum mlxsw_sp_span_trigger trigger) +{ + switch (trigger) { + case MLXSW_SP_SPAN_TRIGGER_INGRESS: + case MLXSW_SP_SPAN_TRIGGER_EARLY_DROP: + case MLXSW_SP_SPAN_TRIGGER_TAIL_DROP: + return true; + case MLXSW_SP_SPAN_TRIGGER_EGRESS: + case MLXSW_SP_SPAN_TRIGGER_ECN: + return false; + } + + WARN_ON_ONCE(1); + return false; +} + static int mlxsw_sp1_span_init(struct mlxsw_sp *mlxsw_sp) { size_t arr_size = ARRAY_SIZE(mlxsw_sp1_span_entry_ops_arr); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h index efaefd1ae863..82e711afb02b 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h @@ -120,6 +120,7 @@ int mlxsw_sp_span_trigger_enable(struct mlxsw_sp_port *mlxsw_sp_port, enum mlxsw_sp_span_trigger trigger, u8 tc); void mlxsw_sp_span_trigger_disable(struct mlxsw_sp_port *mlxsw_sp_port, enum mlxsw_sp_span_trigger trigger, u8 tc); +bool mlxsw_sp_span_trigger_is_ingress(enum mlxsw_sp_span_trigger trigger); extern const struct mlxsw_sp_span_ops mlxsw_sp1_span_ops; extern const struct mlxsw_sp_span_ops mlxsw_sp2_span_ops; diff --git a/drivers/net/ethernet/micrel/ks8842.c b/drivers/net/ethernet/micrel/ks8842.c index 37ccf8c570b5..c11b118dc415 100644 --- a/drivers/net/ethernet/micrel/ks8842.c +++ b/drivers/net/ethernet/micrel/ks8842.c @@ -348,13 +348,15 @@ static void ks8842_reset_hw(struct ks8842_adapter *adapter) ks8842_write16(adapter, 32, 0x1, REG_SW_ID_AND_ENABLE); } -static void ks8842_read_mac_addr(struct ks8842_adapter *adapter, u8 *dest) +static void ks8842_init_mac_addr(struct ks8842_adapter *adapter) { + u8 addr[ETH_ALEN]; int i; u16 mac; for (i = 0; i < ETH_ALEN; i++) - dest[ETH_ALEN - i - 1] = ks8842_read8(adapter, 2, REG_MARL + i); + addr[ETH_ALEN - i - 1] = ks8842_read8(adapter, 2, REG_MARL + i); + eth_hw_addr_set(adapter->netdev, addr); if (adapter->conf_flags & MICREL_KS884X) { /* @@ -380,7 +382,7 @@ static void ks8842_read_mac_addr(struct ks8842_adapter *adapter, u8 *dest) } } -static void ks8842_write_mac_addr(struct ks8842_adapter *adapter, u8 *mac) +static void ks8842_write_mac_addr(struct ks8842_adapter *adapter, const u8 *mac) { unsigned long flags; unsigned i; @@ -1195,7 +1197,7 @@ static int ks8842_probe(struct platform_device *pdev) } if (i == netdev->addr_len) { - ks8842_read_mac_addr(adapter, netdev->dev_addr); + ks8842_init_mac_addr(adapter); if (!is_valid_ether_addr(netdev->dev_addr)) eth_hw_addr_random(netdev); diff --git a/drivers/net/ethernet/micrel/ks8851.h b/drivers/net/ethernet/micrel/ks8851.h index e2eb0caeac82..6f34a61739b6 100644 --- a/drivers/net/ethernet/micrel/ks8851.h +++ b/drivers/net/ethernet/micrel/ks8851.h @@ -427,7 +427,7 @@ struct ks8851_net { int ks8851_probe_common(struct net_device *netdev, struct device *dev, int msg_en); -int ks8851_remove_common(struct device *dev); +void ks8851_remove_common(struct device *dev); int ks8851_suspend(struct device *dev); int ks8851_resume(struct device *dev); diff --git a/drivers/net/ethernet/micrel/ks8851_common.c b/drivers/net/ethernet/micrel/ks8851_common.c index 2c4e5e602be7..691206f19ea7 100644 --- a/drivers/net/ethernet/micrel/ks8851_common.c +++ b/drivers/net/ethernet/micrel/ks8851_common.c @@ -165,6 +165,7 @@ static void ks8851_read_mac_addr(struct net_device *dev) { struct ks8851_net *ks = netdev_priv(dev); unsigned long flags; + u8 addr[ETH_ALEN]; u16 reg; int i; @@ -172,9 +173,10 @@ static void ks8851_read_mac_addr(struct net_device *dev) for (i = 0; i < ETH_ALEN; i += 2) { reg = ks8851_rdreg16(ks, KS_MAR(i)); - dev->dev_addr[i] = reg >> 8; - dev->dev_addr[i + 1] = reg & 0xff; + addr[i] = reg >> 8; + addr[i + 1] = reg & 0xff; } + eth_hw_addr_set(dev, addr); ks8851_unlock(ks, &flags); } @@ -1247,7 +1249,7 @@ err_reg_io: } EXPORT_SYMBOL_GPL(ks8851_probe_common); -int ks8851_remove_common(struct device *dev) +void ks8851_remove_common(struct device *dev) { struct ks8851_net *priv = dev_get_drvdata(dev); @@ -1261,8 +1263,6 @@ int ks8851_remove_common(struct device *dev) gpio_set_value(priv->gpio, 0); regulator_disable(priv->vdd_reg); regulator_disable(priv->vdd_io); - - return 0; } EXPORT_SYMBOL_GPL(ks8851_remove_common); diff --git a/drivers/net/ethernet/micrel/ks8851_par.c b/drivers/net/ethernet/micrel/ks8851_par.c index 2e8fcce50f9d..2e25798c610e 100644 --- a/drivers/net/ethernet/micrel/ks8851_par.c +++ b/drivers/net/ethernet/micrel/ks8851_par.c @@ -327,7 +327,9 @@ static int ks8851_probe_par(struct platform_device *pdev) static int ks8851_remove_par(struct platform_device *pdev) { - return ks8851_remove_common(&pdev->dev); + ks8851_remove_common(&pdev->dev); + + return 0; } static const struct of_device_id ks8851_match_table[] = { diff --git a/drivers/net/ethernet/micrel/ks8851_spi.c b/drivers/net/ethernet/micrel/ks8851_spi.c index 479406ecbaa3..0303e727e99f 100644 --- a/drivers/net/ethernet/micrel/ks8851_spi.c +++ b/drivers/net/ethernet/micrel/ks8851_spi.c @@ -454,7 +454,9 @@ static int ks8851_probe_spi(struct spi_device *spi) static int ks8851_remove_spi(struct spi_device *spi) { - return ks8851_remove_common(&spi->dev); + ks8851_remove_common(&spi->dev); + + return 0; } static const struct of_device_id ks8851_match_table[] = { diff --git a/drivers/net/ethernet/micrel/ksz884x.c b/drivers/net/ethernet/micrel/ksz884x.c index a1f7f45b9d08..99c0c1491af2 100644 --- a/drivers/net/ethernet/micrel/ksz884x.c +++ b/drivers/net/ethernet/micrel/ksz884x.c @@ -4033,7 +4033,7 @@ static void hw_set_add_addr(struct ksz_hw *hw) } } -static int hw_add_addr(struct ksz_hw *hw, u8 *mac_addr) +static int hw_add_addr(struct ksz_hw *hw, const u8 *mac_addr) { int i; int j = ADDITIONAL_ENTRIES; @@ -4054,7 +4054,7 @@ static int hw_add_addr(struct ksz_hw *hw, u8 *mac_addr) return -1; } -static int hw_del_addr(struct ksz_hw *hw, u8 *mac_addr) +static int hw_del_addr(struct ksz_hw *hw, const u8 *mac_addr) { int i; @@ -7007,9 +7007,12 @@ static int pcidev_init(struct pci_dev *pdev, const struct pci_device_id *id) if (MAIN_PORT == i) eth_hw_addr_set(dev, hw_priv->hw.override_addr); else { - eth_hw_addr_set(dev, sw->other_addr); + u8 addr[ETH_ALEN]; + + ether_addr_copy(addr, sw->other_addr); if (ether_addr_equal(sw->other_addr, hw->override_addr)) - dev->dev_addr[5] += port->first_port; + addr[5] += port->first_port; + eth_hw_addr_set(dev, addr); } dev->netdev_ops = &netdev_ops; diff --git a/drivers/net/ethernet/microchip/encx24j600.c b/drivers/net/ethernet/microchip/encx24j600.c index 79167c3a3179..b90efc80fb59 100644 --- a/drivers/net/ethernet/microchip/encx24j600.c +++ b/drivers/net/ethernet/microchip/encx24j600.c @@ -1001,6 +1001,7 @@ static int encx24j600_spi_probe(struct spi_device *spi) struct net_device *ndev; struct encx24j600_priv *priv; u16 eidled; + u8 addr[ETH_ALEN]; ndev = alloc_etherdev(sizeof(struct encx24j600_priv)); @@ -1056,7 +1057,8 @@ static int encx24j600_spi_probe(struct spi_device *spi) } /* Get the MAC address from the chip */ - encx24j600_hw_get_macaddr(priv, ndev->dev_addr); + encx24j600_hw_get_macaddr(priv, addr); + eth_hw_addr_set(ndev, addr); ndev->ethtool_ops = &encx24j600_ethtool_ops; diff --git a/drivers/net/ethernet/microchip/lan743x_main.h b/drivers/net/ethernet/microchip/lan743x_main.h index 6080028c1df2..34c22eea0124 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.h +++ b/drivers/net/ethernet/microchip/lan743x_main.h @@ -279,6 +279,7 @@ #define PTP_GENERAL_CONFIG_CLOCK_EVENT_1MS_ (3) #define PTP_GENERAL_CONFIG_CLOCK_EVENT_10MS_ (4) #define PTP_GENERAL_CONFIG_CLOCK_EVENT_200MS_ (5) +#define PTP_GENERAL_CONFIG_CLOCK_EVENT_TOGGLE_ (6) #define PTP_GENERAL_CONFIG_CLOCK_EVENT_X_SET_(channel, value) \ (((value) & 0x7) << (1 + ((channel) << 2))) #define PTP_GENERAL_CONFIG_RELOAD_ADD_X_(channel) (BIT((channel) << 2)) diff --git a/drivers/net/ethernet/microchip/lan743x_ptp.c b/drivers/net/ethernet/microchip/lan743x_ptp.c index ab6d719d40f0..9380e396f648 100644 --- a/drivers/net/ethernet/microchip/lan743x_ptp.c +++ b/drivers/net/ethernet/microchip/lan743x_ptp.c @@ -491,9 +491,10 @@ static int lan743x_ptp_perout(struct lan743x_adapter *adapter, int on, int perout_pin = 0; unsigned int index = perout_request->index; struct lan743x_ptp_perout *perout = &ptp->perout[index]; + int ret = 0; /* Reject requests with unsupported flags */ - if (perout_request->flags) + if (perout_request->flags & ~PTP_PEROUT_DUTY_CYCLE) return -EOPNOTSUPP; if (on) { @@ -518,6 +519,7 @@ static int lan743x_ptp_perout(struct lan743x_adapter *adapter, int on, netif_warn(adapter, drv, adapter->netdev, "Failed to reserve event channel %d for PEROUT\n", index); + ret = -EBUSY; goto failed; } @@ -529,6 +531,7 @@ static int lan743x_ptp_perout(struct lan743x_adapter *adapter, int on, netif_warn(adapter, drv, adapter->netdev, "Failed to reserve gpio %d for PEROUT\n", perout_pin); + ret = -EBUSY; goto failed; } @@ -540,27 +543,93 @@ static int lan743x_ptp_perout(struct lan743x_adapter *adapter, int on, period_sec += perout_request->period.nsec / 1000000000; period_nsec = perout_request->period.nsec % 1000000000; - if (period_sec == 0) { - if (period_nsec >= 400000000) { + if (perout_request->flags & PTP_PEROUT_DUTY_CYCLE) { + struct timespec64 ts_on, ts_period; + s64 wf_high, period64, half; + s32 reminder; + + ts_on.tv_sec = perout_request->on.sec; + ts_on.tv_nsec = perout_request->on.nsec; + wf_high = timespec64_to_ns(&ts_on); + ts_period.tv_sec = perout_request->period.sec; + ts_period.tv_nsec = perout_request->period.nsec; + period64 = timespec64_to_ns(&ts_period); + + if (period64 < 200) { + netif_warn(adapter, drv, adapter->netdev, + "perout period too small, minimum is 200nS\n"); + ret = -EOPNOTSUPP; + goto failed; + } + if (wf_high >= period64) { + netif_warn(adapter, drv, adapter->netdev, + "pulse width must be smaller than period\n"); + ret = -EINVAL; + goto failed; + } + + /* Check if we can do 50% toggle on an even value of period. + * If the period number is odd, then check if the requested + * pulse width is the same as one of pre-defined width values. + * Otherwise, return failure. + */ + half = div_s64_rem(period64, 2, &reminder); + if (!reminder) { + if (half == wf_high) { + /* It's 50% match. Use the toggle option */ + pulse_width = PTP_GENERAL_CONFIG_CLOCK_EVENT_TOGGLE_; + /* In this case, devide period value by 2 */ + ts_period = ns_to_timespec64(div_s64(period64, 2)); + period_sec = ts_period.tv_sec; + period_nsec = ts_period.tv_nsec; + + goto program; + } + } + /* if we can't do toggle, then the width option needs to be the exact match */ + if (wf_high == 200000000) { pulse_width = PTP_GENERAL_CONFIG_CLOCK_EVENT_200MS_; - } else if (period_nsec >= 20000000) { + } else if (wf_high == 10000000) { pulse_width = PTP_GENERAL_CONFIG_CLOCK_EVENT_10MS_; - } else if (period_nsec >= 2000000) { + } else if (wf_high == 1000000) { pulse_width = PTP_GENERAL_CONFIG_CLOCK_EVENT_1MS_; - } else if (period_nsec >= 200000) { + } else if (wf_high == 100000) { pulse_width = PTP_GENERAL_CONFIG_CLOCK_EVENT_100US_; - } else if (period_nsec >= 20000) { + } else if (wf_high == 10000) { pulse_width = PTP_GENERAL_CONFIG_CLOCK_EVENT_10US_; - } else if (period_nsec >= 200) { + } else if (wf_high == 100) { pulse_width = PTP_GENERAL_CONFIG_CLOCK_EVENT_100NS_; } else { netif_warn(adapter, drv, adapter->netdev, - "perout period too small, minimum is 200nS\n"); + "duty cycle specified is not supported\n"); + ret = -EOPNOTSUPP; goto failed; } } else { - pulse_width = PTP_GENERAL_CONFIG_CLOCK_EVENT_200MS_; + if (period_sec == 0) { + if (period_nsec >= 400000000) { + pulse_width = PTP_GENERAL_CONFIG_CLOCK_EVENT_200MS_; + } else if (period_nsec >= 20000000) { + pulse_width = PTP_GENERAL_CONFIG_CLOCK_EVENT_10MS_; + } else if (period_nsec >= 2000000) { + pulse_width = PTP_GENERAL_CONFIG_CLOCK_EVENT_1MS_; + } else if (period_nsec >= 200000) { + pulse_width = PTP_GENERAL_CONFIG_CLOCK_EVENT_100US_; + } else if (period_nsec >= 20000) { + pulse_width = PTP_GENERAL_CONFIG_CLOCK_EVENT_10US_; + } else if (period_nsec >= 200) { + pulse_width = PTP_GENERAL_CONFIG_CLOCK_EVENT_100NS_; + } else { + netif_warn(adapter, drv, adapter->netdev, + "perout period too small, minimum is 200nS\n"); + ret = -EOPNOTSUPP; + goto failed; + } + } else { + pulse_width = PTP_GENERAL_CONFIG_CLOCK_EVENT_200MS_; + } } +program: /* turn off by setting target far in future */ lan743x_csr_write(adapter, @@ -599,7 +668,7 @@ static int lan743x_ptp_perout(struct lan743x_adapter *adapter, int on, failed: lan743x_ptp_perout_off(adapter, index); - return -ENODEV; + return ret; } static int lan743x_ptpci_enable(struct ptp_clock_info *ptpci, diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_netdev.c b/drivers/net/ethernet/microchip/sparx5/sparx5_netdev.c index b21ebaa32d7e..e042f117dc7a 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_netdev.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_netdev.c @@ -200,7 +200,6 @@ struct net_device *sparx5_create_netdev(struct sparx5 *sparx5, u32 portno) { struct sparx5_port *spx5_port; struct net_device *ndev; - u64 val; ndev = devm_alloc_etherdev(sparx5->dev, sizeof(struct sparx5_port)); if (!ndev) @@ -216,8 +215,7 @@ struct net_device *sparx5_create_netdev(struct sparx5 *sparx5, u32 portno) ndev->netdev_ops = &sparx5_port_netdev_ops; ndev->ethtool_ops = &sparx5_ethtool_ops; - val = ether_addr_to_u64(sparx5->base_mac) + portno + 1; - u64_to_ether_addr(val, ndev->dev_addr); + eth_hw_addr_gen(ndev, sparx5->base_mac, portno + 1); return ndev; } diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index 520a75b57866..4e5ae687d2e2 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -162,48 +162,117 @@ static int ocelot_vlant_set_mask(struct ocelot *ocelot, u16 vid, u32 mask) return ocelot_vlant_wait_for_completion(ocelot); } -static void ocelot_port_set_native_vlan(struct ocelot *ocelot, int port, - struct ocelot_vlan native_vlan) +static int ocelot_port_num_untagged_vlans(struct ocelot *ocelot, int port) +{ + struct ocelot_bridge_vlan *vlan; + int num_untagged = 0; + + list_for_each_entry(vlan, &ocelot->vlans, list) { + if (!(vlan->portmask & BIT(port))) + continue; + + if (vlan->untagged & BIT(port)) + num_untagged++; + } + + return num_untagged; +} + +static int ocelot_port_num_tagged_vlans(struct ocelot *ocelot, int port) +{ + struct ocelot_bridge_vlan *vlan; + int num_tagged = 0; + + list_for_each_entry(vlan, &ocelot->vlans, list) { + if (!(vlan->portmask & BIT(port))) + continue; + + if (!(vlan->untagged & BIT(port))) + num_tagged++; + } + + return num_tagged; +} + +/* We use native VLAN when we have to mix egress-tagged VLANs with exactly + * _one_ egress-untagged VLAN (_the_ native VLAN) + */ +static bool ocelot_port_uses_native_vlan(struct ocelot *ocelot, int port) +{ + return ocelot_port_num_tagged_vlans(ocelot, port) && + ocelot_port_num_untagged_vlans(ocelot, port) == 1; +} + +static struct ocelot_bridge_vlan * +ocelot_port_find_native_vlan(struct ocelot *ocelot, int port) +{ + struct ocelot_bridge_vlan *vlan; + + list_for_each_entry(vlan, &ocelot->vlans, list) + if (vlan->portmask & BIT(port) && vlan->untagged & BIT(port)) + return vlan; + + return NULL; +} + +/* Keep in sync REW_TAG_CFG_TAG_CFG and, if applicable, + * REW_PORT_VLAN_CFG_PORT_VID, with the bridge VLAN table and VLAN awareness + * state of the port. + */ +static void ocelot_port_manage_port_tag(struct ocelot *ocelot, int port) { struct ocelot_port *ocelot_port = ocelot->ports[port]; - u32 val = 0; - - ocelot_port->native_vlan = native_vlan; - - ocelot_rmw_gix(ocelot, REW_PORT_VLAN_CFG_PORT_VID(native_vlan.vid), - REW_PORT_VLAN_CFG_PORT_VID_M, - REW_PORT_VLAN_CFG, port); + enum ocelot_port_tag_config tag_cfg; + bool uses_native_vlan = false; if (ocelot_port->vlan_aware) { - if (native_vlan.valid) - /* Tag all frames except when VID == DEFAULT_VLAN */ - val = REW_TAG_CFG_TAG_CFG(1); + uses_native_vlan = ocelot_port_uses_native_vlan(ocelot, port); + + if (uses_native_vlan) + tag_cfg = OCELOT_PORT_TAG_NATIVE; + else if (ocelot_port_num_untagged_vlans(ocelot, port)) + tag_cfg = OCELOT_PORT_TAG_DISABLED; else - /* Tag all frames */ - val = REW_TAG_CFG_TAG_CFG(3); + tag_cfg = OCELOT_PORT_TAG_TRUNK; } else { - /* Port tagging disabled. */ - val = REW_TAG_CFG_TAG_CFG(0); + tag_cfg = OCELOT_PORT_TAG_DISABLED; } - ocelot_rmw_gix(ocelot, val, + + ocelot_rmw_gix(ocelot, REW_TAG_CFG_TAG_CFG(tag_cfg), REW_TAG_CFG_TAG_CFG_M, REW_TAG_CFG, port); + + if (uses_native_vlan) { + struct ocelot_bridge_vlan *native_vlan; + + /* Not having a native VLAN is impossible, because + * ocelot_port_num_untagged_vlans has returned 1. + * So there is no use in checking for NULL here. + */ + native_vlan = ocelot_port_find_native_vlan(ocelot, port); + + ocelot_rmw_gix(ocelot, + REW_PORT_VLAN_CFG_PORT_VID(native_vlan->vid), + REW_PORT_VLAN_CFG_PORT_VID_M, + REW_PORT_VLAN_CFG, port); + } } /* Default vlan to clasify for untagged frames (may be zero) */ static void ocelot_port_set_pvid(struct ocelot *ocelot, int port, - struct ocelot_vlan pvid_vlan) + const struct ocelot_bridge_vlan *pvid_vlan) { struct ocelot_port *ocelot_port = ocelot->ports[port]; + u16 pvid = OCELOT_VLAN_UNAWARE_PVID; u32 val = 0; ocelot_port->pvid_vlan = pvid_vlan; - if (!ocelot_port->vlan_aware) - pvid_vlan.vid = 0; + if (ocelot_port->vlan_aware && pvid_vlan) + pvid = pvid_vlan->vid; ocelot_rmw_gix(ocelot, - ANA_PORT_VLAN_CFG_VLAN_VID(pvid_vlan.vid), + ANA_PORT_VLAN_CFG_VLAN_VID(pvid), ANA_PORT_VLAN_CFG_VLAN_VID_M, ANA_PORT_VLAN_CFG, port); @@ -212,7 +281,7 @@ static void ocelot_port_set_pvid(struct ocelot *ocelot, int port, * classified to VLAN 0, but that is always in our RX filter, so it * would get accepted were it not for this setting. */ - if (!pvid_vlan.valid && ocelot_port->vlan_aware) + if (!pvid_vlan && ocelot_port->vlan_aware) val = ANA_PORT_DROP_CFG_DROP_PRIO_S_TAGGED_ENA | ANA_PORT_DROP_CFG_DROP_PRIO_C_TAGGED_ENA; @@ -222,31 +291,90 @@ static void ocelot_port_set_pvid(struct ocelot *ocelot, int port, ANA_PORT_DROP_CFG, port); } -static int ocelot_vlan_member_set(struct ocelot *ocelot, u32 vlan_mask, u16 vid) +static struct ocelot_bridge_vlan *ocelot_bridge_vlan_find(struct ocelot *ocelot, + u16 vid) { + struct ocelot_bridge_vlan *vlan; + + list_for_each_entry(vlan, &ocelot->vlans, list) + if (vlan->vid == vid) + return vlan; + + return NULL; +} + +static int ocelot_vlan_member_add(struct ocelot *ocelot, int port, u16 vid, + bool untagged) +{ + struct ocelot_bridge_vlan *vlan = ocelot_bridge_vlan_find(ocelot, vid); + unsigned long portmask; int err; - err = ocelot_vlant_set_mask(ocelot, vid, vlan_mask); - if (err) - return err; + if (vlan) { + portmask = vlan->portmask | BIT(port); - ocelot->vlan_mask[vid] = vlan_mask; + err = ocelot_vlant_set_mask(ocelot, vid, portmask); + if (err) + return err; + + vlan->portmask = portmask; + /* Bridge VLANs can be overwritten with a different + * egress-tagging setting, so make sure to override an untagged + * with a tagged VID if that's going on. + */ + if (untagged) + vlan->untagged |= BIT(port); + else + vlan->untagged &= ~BIT(port); + + return 0; + } + + vlan = kzalloc(sizeof(*vlan), GFP_KERNEL); + if (!vlan) + return -ENOMEM; + + portmask = BIT(port); + + err = ocelot_vlant_set_mask(ocelot, vid, portmask); + if (err) { + kfree(vlan); + return err; + } + + vlan->vid = vid; + vlan->portmask = portmask; + if (untagged) + vlan->untagged = BIT(port); + INIT_LIST_HEAD(&vlan->list); + list_add_tail(&vlan->list, &ocelot->vlans); return 0; } -static int ocelot_vlan_member_add(struct ocelot *ocelot, int port, u16 vid) -{ - return ocelot_vlan_member_set(ocelot, - ocelot->vlan_mask[vid] | BIT(port), - vid); -} - static int ocelot_vlan_member_del(struct ocelot *ocelot, int port, u16 vid) { - return ocelot_vlan_member_set(ocelot, - ocelot->vlan_mask[vid] & ~BIT(port), - vid); + struct ocelot_bridge_vlan *vlan = ocelot_bridge_vlan_find(ocelot, vid); + unsigned long portmask; + int err; + + if (!vlan) + return 0; + + portmask = vlan->portmask & ~BIT(port); + + err = ocelot_vlant_set_mask(ocelot, vid, portmask); + if (err) + return err; + + vlan->portmask = portmask; + if (vlan->portmask) + return 0; + + list_del(&vlan->list); + kfree(vlan); + + return 0; } int ocelot_port_vlan_filtering(struct ocelot *ocelot, int port, @@ -279,7 +407,7 @@ int ocelot_port_vlan_filtering(struct ocelot *ocelot, int port, ANA_PORT_VLAN_CFG, port); ocelot_port_set_pvid(ocelot, port, ocelot_port->pvid_vlan); - ocelot_port_set_native_vlan(ocelot, port, ocelot_port->native_vlan); + ocelot_port_manage_port_tag(ocelot, port); return 0; } @@ -288,14 +416,20 @@ EXPORT_SYMBOL(ocelot_port_vlan_filtering); int ocelot_vlan_prepare(struct ocelot *ocelot, int port, u16 vid, bool pvid, bool untagged, struct netlink_ext_ack *extack) { - struct ocelot_port *ocelot_port = ocelot->ports[port]; - - /* Deny changing the native VLAN, but always permit deleting it */ - if (untagged && ocelot_port->native_vlan.vid != vid && - ocelot_port->native_vlan.valid) { - NL_SET_ERR_MSG_MOD(extack, - "Port already has a native VLAN"); - return -EBUSY; + if (untagged) { + /* We are adding an egress-tagged VLAN */ + if (ocelot_port_uses_native_vlan(ocelot, port)) { + NL_SET_ERR_MSG_MOD(extack, + "Port with egress-tagged VLANs cannot have more than one egress-untagged (native) VLAN"); + return -EBUSY; + } + } else { + /* We are adding an egress-tagged VLAN */ + if (ocelot_port_num_untagged_vlans(ocelot, port) > 1) { + NL_SET_ERR_MSG_MOD(extack, + "Port with more than one egress-untagged VLAN cannot have egress-tagged VLANs"); + return -EBUSY; + } } return 0; @@ -307,27 +441,17 @@ int ocelot_vlan_add(struct ocelot *ocelot, int port, u16 vid, bool pvid, { int err; - err = ocelot_vlan_member_add(ocelot, port, vid); + err = ocelot_vlan_member_add(ocelot, port, vid, untagged); if (err) return err; /* Default ingress vlan classification */ - if (pvid) { - struct ocelot_vlan pvid_vlan; - - pvid_vlan.vid = vid; - pvid_vlan.valid = true; - ocelot_port_set_pvid(ocelot, port, pvid_vlan); - } + if (pvid) + ocelot_port_set_pvid(ocelot, port, + ocelot_bridge_vlan_find(ocelot, vid)); /* Untagged egress vlan clasification */ - if (untagged) { - struct ocelot_vlan native_vlan; - - native_vlan.vid = vid; - native_vlan.valid = true; - ocelot_port_set_native_vlan(ocelot, port, native_vlan); - } + ocelot_port_manage_port_tag(ocelot, port); return 0; } @@ -343,18 +467,11 @@ int ocelot_vlan_del(struct ocelot *ocelot, int port, u16 vid) return err; /* Ingress */ - if (ocelot_port->pvid_vlan.vid == vid) { - struct ocelot_vlan pvid_vlan = {0}; - - ocelot_port_set_pvid(ocelot, port, pvid_vlan); - } + if (ocelot_port->pvid_vlan && ocelot_port->pvid_vlan->vid == vid) + ocelot_port_set_pvid(ocelot, port, NULL); /* Egress */ - if (ocelot_port->native_vlan.vid == vid) { - struct ocelot_vlan native_vlan = {0}; - - ocelot_port_set_native_vlan(ocelot, port, native_vlan); - } + ocelot_port_manage_port_tag(ocelot, port); return 0; } @@ -372,13 +489,13 @@ static void ocelot_vlan_init(struct ocelot *ocelot) /* Configure the port VLAN memberships */ for (vid = 1; vid < VLAN_N_VID; vid++) - ocelot_vlan_member_set(ocelot, 0, vid); + ocelot_vlant_set_mask(ocelot, vid, 0); /* Because VLAN filtering is enabled, we need VID 0 to get untagged * traffic. It is added automatically if 8021q module is loaded, but * we can't rely on it since module may be not loaded. */ - ocelot_vlan_member_set(ocelot, all_ports, 0); + ocelot_vlant_set_mask(ocelot, OCELOT_VLAN_UNAWARE_PVID, all_ports); /* Set vlan ingress filter mask to all ports but the CPU port by * default. @@ -1680,12 +1797,11 @@ void ocelot_port_bridge_leave(struct ocelot *ocelot, int port, struct net_device *bridge) { struct ocelot_port *ocelot_port = ocelot->ports[port]; - struct ocelot_vlan pvid = {0}, native_vlan = {0}; ocelot_port->bridge = NULL; - ocelot_port_set_pvid(ocelot, port, pvid); - ocelot_port_set_native_vlan(ocelot, port, native_vlan); + ocelot_port_set_pvid(ocelot, port, NULL); + ocelot_port_manage_port_tag(ocelot, port); ocelot_apply_bridge_fwd_mask(ocelot); } EXPORT_SYMBOL(ocelot_port_bridge_leave); @@ -2071,9 +2187,10 @@ static void ocelot_cpu_port_init(struct ocelot *ocelot) OCELOT_TAG_PREFIX_NONE); /* Configure the CPU port to be VLAN aware */ - ocelot_write_gix(ocelot, ANA_PORT_VLAN_CFG_VLAN_VID(0) | - ANA_PORT_VLAN_CFG_VLAN_AWARE_ENA | - ANA_PORT_VLAN_CFG_VLAN_POP_CNT(1), + ocelot_write_gix(ocelot, + ANA_PORT_VLAN_CFG_VLAN_VID(OCELOT_VLAN_UNAWARE_PVID) | + ANA_PORT_VLAN_CFG_VLAN_AWARE_ENA | + ANA_PORT_VLAN_CFG_VLAN_POP_CNT(1), ANA_PORT_VLAN_CFG, cpu); } @@ -2130,6 +2247,7 @@ int ocelot_init(struct ocelot *ocelot) INIT_LIST_HEAD(&ocelot->multicast); INIT_LIST_HEAD(&ocelot->pgids); + INIT_LIST_HEAD(&ocelot->vlans); ocelot_detect_features(ocelot); ocelot_mact_init(ocelot); ocelot_vlan_init(ocelot); diff --git a/drivers/net/ethernet/mscc/ocelot.h b/drivers/net/ethernet/mscc/ocelot.h index 1952d6a1b98a..e43da09b8f91 100644 --- a/drivers/net/ethernet/mscc/ocelot.h +++ b/drivers/net/ethernet/mscc/ocelot.h @@ -25,6 +25,7 @@ #include "ocelot_rew.h" #include "ocelot_qs.h" +#define OCELOT_VLAN_UNAWARE_PVID 0 #define OCELOT_BUFFER_CELL_SZ 60 #define OCELOT_STATS_CHECK_DELAY (2 * HZ) diff --git a/drivers/net/ethernet/mscc/ocelot_mrp.c b/drivers/net/ethernet/mscc/ocelot_mrp.c index 4b0941f09f71..1fa58546abdc 100644 --- a/drivers/net/ethernet/mscc/ocelot_mrp.c +++ b/drivers/net/ethernet/mscc/ocelot_mrp.c @@ -116,16 +116,16 @@ static void ocelot_mrp_save_mac(struct ocelot *ocelot, struct ocelot_port *port) { ocelot_mact_learn(ocelot, PGID_BLACKHOLE, mrp_test_dmac, - port->pvid_vlan.vid, ENTRYTYPE_LOCKED); + OCELOT_VLAN_UNAWARE_PVID, ENTRYTYPE_LOCKED); ocelot_mact_learn(ocelot, PGID_BLACKHOLE, mrp_control_dmac, - port->pvid_vlan.vid, ENTRYTYPE_LOCKED); + OCELOT_VLAN_UNAWARE_PVID, ENTRYTYPE_LOCKED); } static void ocelot_mrp_del_mac(struct ocelot *ocelot, struct ocelot_port *port) { - ocelot_mact_forget(ocelot, mrp_test_dmac, port->pvid_vlan.vid); - ocelot_mact_forget(ocelot, mrp_control_dmac, port->pvid_vlan.vid); + ocelot_mact_forget(ocelot, mrp_test_dmac, OCELOT_VLAN_UNAWARE_PVID); + ocelot_mact_forget(ocelot, mrp_control_dmac, OCELOT_VLAN_UNAWARE_PVID); } int ocelot_mrp_add(struct ocelot *ocelot, int port, diff --git a/drivers/net/ethernet/mscc/ocelot_net.c b/drivers/net/ethernet/mscc/ocelot_net.c index 9992bf06311d..e3fc4548f642 100644 --- a/drivers/net/ethernet/mscc/ocelot_net.c +++ b/drivers/net/ethernet/mscc/ocelot_net.c @@ -418,7 +418,7 @@ static int ocelot_vlan_vid_del(struct net_device *dev, u16 vid) * with VLAN filtering feature. We need to keep it to receive * untagged traffic. */ - if (vid == 0) + if (vid == OCELOT_VLAN_UNAWARE_PVID) return 0; ret = ocelot_vlan_del(ocelot, port, vid); @@ -553,7 +553,7 @@ static int ocelot_mc_unsync(struct net_device *dev, const unsigned char *addr) struct ocelot_mact_work_ctx w; ether_addr_copy(w.forget.addr, addr); - w.forget.vid = ocelot_port->pvid_vlan.vid; + w.forget.vid = OCELOT_VLAN_UNAWARE_PVID; w.type = OCELOT_MACT_FORGET; return ocelot_enqueue_mact_action(ocelot, &w); @@ -567,7 +567,7 @@ static int ocelot_mc_sync(struct net_device *dev, const unsigned char *addr) struct ocelot_mact_work_ctx w; ether_addr_copy(w.learn.addr, addr); - w.learn.vid = ocelot_port->pvid_vlan.vid; + w.learn.vid = OCELOT_VLAN_UNAWARE_PVID; w.learn.pgid = PGID_CPU; w.learn.entry_type = ENTRYTYPE_LOCKED; w.type = OCELOT_MACT_LEARN; @@ -602,9 +602,9 @@ static int ocelot_port_set_mac_address(struct net_device *dev, void *p) /* Learn the new net device MAC address in the mac table. */ ocelot_mact_learn(ocelot, PGID_CPU, addr->sa_data, - ocelot_port->pvid_vlan.vid, ENTRYTYPE_LOCKED); + OCELOT_VLAN_UNAWARE_PVID, ENTRYTYPE_LOCKED); /* Then forget the previous one. */ - ocelot_mact_forget(ocelot, dev->dev_addr, ocelot_port->pvid_vlan.vid); + ocelot_mact_forget(ocelot, dev->dev_addr, OCELOT_VLAN_UNAWARE_PVID); eth_hw_addr_set(dev, addr->sa_data); return 0; @@ -1705,10 +1705,9 @@ int ocelot_probe_port(struct ocelot *ocelot, int port, struct regmap *target, NETIF_F_HW_TC; dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_TC; - eth_hw_addr_set(dev, ocelot->base_mac); - dev->dev_addr[ETH_ALEN - 1] += port; + eth_hw_addr_gen(dev, ocelot->base_mac, port); ocelot_mact_learn(ocelot, PGID_CPU, dev->dev_addr, - ocelot_port->pvid_vlan.vid, ENTRYTYPE_LOCKED); + OCELOT_VLAN_UNAWARE_PVID, ENTRYTYPE_LOCKED); ocelot_init_port(ocelot, port); diff --git a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c index 32760f87bf8a..5736fcdafd7a 100644 --- a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c +++ b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c @@ -796,7 +796,8 @@ static int myri10ge_load_firmware(struct myri10ge_priv *mgp, int adopt) return status; } -static int myri10ge_update_mac_address(struct myri10ge_priv *mgp, u8 * addr) +static int myri10ge_update_mac_address(struct myri10ge_priv *mgp, + const u8 * addr) { struct myri10ge_cmd cmd; int status; @@ -3738,7 +3739,6 @@ static int myri10ge_probe(struct pci_dev *pdev, const struct pci_device_id *ent) struct net_device *netdev; struct myri10ge_priv *mgp; struct device *dev = &pdev->dev; - int i; int status = -ENXIO; int dac_enabled; unsigned hdr_offset, ss_offset; @@ -3828,8 +3828,7 @@ static int myri10ge_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (status) goto abort_with_ioremap; - for (i = 0; i < ETH_ALEN; i++) - netdev->dev_addr[i] = mgp->mac_addr[i]; + eth_hw_addr_set(netdev, mgp->mac_addr); myri10ge_select_firmware(mgp); diff --git a/drivers/net/ethernet/natsemi/natsemi.c b/drivers/net/ethernet/natsemi/natsemi.c index 3f982033944b..82a22711ce45 100644 --- a/drivers/net/ethernet/natsemi/natsemi.c +++ b/drivers/net/ethernet/natsemi/natsemi.c @@ -809,6 +809,7 @@ static int natsemi_probe1(struct pci_dev *pdev, const struct pci_device_id *ent) unsigned long iosize; void __iomem *ioaddr; const int pcibar = 1; /* PCI base address register */ + u8 addr[ETH_ALEN]; int prev_eedata; u32 tmp; @@ -859,10 +860,11 @@ static int natsemi_probe1(struct pci_dev *pdev, const struct pci_device_id *ent) prev_eedata = eeprom_read(ioaddr, 6); for (i = 0; i < 3; i++) { int eedata = eeprom_read(ioaddr, i + 7); - dev->dev_addr[i*2] = (eedata << 1) + (prev_eedata >> 15); - dev->dev_addr[i*2+1] = eedata >> 7; + addr[i*2] = (eedata << 1) + (prev_eedata >> 15); + addr[i*2+1] = eedata >> 7; prev_eedata = eedata; } + eth_hw_addr_set(dev, addr); np = netdev_priv(dev); np->ioaddr = ioaddr; diff --git a/drivers/net/ethernet/natsemi/ns83820.c b/drivers/net/ethernet/natsemi/ns83820.c index 72794d158871..49ea130c9067 100644 --- a/drivers/net/ethernet/natsemi/ns83820.c +++ b/drivers/net/ethernet/natsemi/ns83820.c @@ -1649,9 +1649,11 @@ failed: return ret; } -static void ns83820_getmac(struct ns83820 *dev, u8 *mac) +static void ns83820_getmac(struct ns83820 *dev, struct net_device *ndev) { + u8 mac[ETH_ALEN]; unsigned i; + for (i=0; i<3; i++) { u32 data; @@ -1661,9 +1663,10 @@ static void ns83820_getmac(struct ns83820 *dev, u8 *mac) writel(i*2, dev->base + RFCR); data = readl(dev->base + RFDR); - *mac++ = data; - *mac++ = data >> 8; + mac[i * 2] = data; + mac[i * 2 + 1] = data >> 8; } + eth_hw_addr_set(ndev, mac); } static void ns83820_set_multicast(struct net_device *ndev) @@ -2136,7 +2139,7 @@ static int ns83820_init_one(struct pci_dev *pci_dev, /* Disable Wake On Lan */ writel(0, dev->base + WCSR); - ns83820_getmac(dev, ndev->dev_addr); + ns83820_getmac(dev, ndev); /* Yes, we support dumb IP checksum on transmit */ ndev->features |= NETIF_F_SG; diff --git a/drivers/net/ethernet/neterion/s2io.c b/drivers/net/ethernet/neterion/s2io.c index ade47c4fdae0..d1c32c65db05 100644 --- a/drivers/net/ethernet/neterion/s2io.c +++ b/drivers/net/ethernet/neterion/s2io.c @@ -5217,7 +5217,7 @@ static int s2io_set_mac_addr(struct net_device *dev, void *p) * as defined in errno.h file on failure. */ -static int do_s2io_prog_unicast(struct net_device *dev, u8 *addr) +static int do_s2io_prog_unicast(struct net_device *dev, const u8 *addr) { struct s2io_nic *sp = netdev_priv(dev); register u64 mac_addr = 0, perm_addr = 0; diff --git a/drivers/net/ethernet/neterion/s2io.h b/drivers/net/ethernet/neterion/s2io.h index 5a6032212c19..a4266d1544ab 100644 --- a/drivers/net/ethernet/neterion/s2io.h +++ b/drivers/net/ethernet/neterion/s2io.h @@ -1073,7 +1073,7 @@ static void s2io_reset(struct s2io_nic * sp); static int s2io_poll_msix(struct napi_struct *napi, int budget); static int s2io_poll_inta(struct napi_struct *napi, int budget); static void s2io_init_pci(struct s2io_nic * sp); -static int do_s2io_prog_unicast(struct net_device *dev, u8 *addr); +static int do_s2io_prog_unicast(struct net_device *dev, const u8 *addr); static void s2io_alarm_handle(struct timer_list *t); static irqreturn_t s2io_msix_ring_handle(int irq, void *dev_id); diff --git a/drivers/net/ethernet/netronome/nfp/abm/qdisc.c b/drivers/net/ethernet/netronome/nfp/abm/qdisc.c index 2473fb5f75e5..2a5cc64227e9 100644 --- a/drivers/net/ethernet/netronome/nfp/abm/qdisc.c +++ b/drivers/net/ethernet/netronome/nfp/abm/qdisc.c @@ -458,7 +458,7 @@ nfp_abm_qdisc_graft(struct nfp_abm_link *alink, u32 handle, u32 child_handle, static void nfp_abm_stats_calculate(struct nfp_alink_stats *new, struct nfp_alink_stats *old, - struct gnet_stats_basic_packed *bstats, + struct gnet_stats_basic_sync *bstats, struct gnet_stats_queue *qstats) { _bstats_update(bstats, new->tx_bytes - old->tx_bytes, diff --git a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c index ab70179728f6..dfb4468fe287 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c +++ b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c @@ -837,7 +837,7 @@ nfp_tunnel_put_ipv6_off(struct nfp_app *app, struct nfp_ipv6_addr_entry *entry) } static int -__nfp_tunnel_offload_mac(struct nfp_app *app, u8 *mac, u16 idx, bool del) +__nfp_tunnel_offload_mac(struct nfp_app *app, const u8 *mac, u16 idx, bool del) { struct nfp_tun_mac_addr_offload payload; @@ -886,7 +886,7 @@ static bool nfp_tunnel_is_mac_idx_global(u16 nfp_mac_idx) } static struct nfp_tun_offloaded_mac * -nfp_tunnel_lookup_offloaded_macs(struct nfp_app *app, u8 *mac) +nfp_tunnel_lookup_offloaded_macs(struct nfp_app *app, const u8 *mac) { struct nfp_flower_priv *priv = app->priv; @@ -1005,7 +1005,7 @@ err_free_ida: static int nfp_tunnel_del_shared_mac(struct nfp_app *app, struct net_device *netdev, - u8 *mac, bool mod) + const u8 *mac, bool mod) { struct nfp_flower_priv *priv = app->priv; struct nfp_flower_repr_priv *repr_priv; diff --git a/drivers/net/ethernet/nvidia/forcedeth.c b/drivers/net/ethernet/nvidia/forcedeth.c index 3f269f914dac..9b530d7509a4 100644 --- a/drivers/net/ethernet/nvidia/forcedeth.c +++ b/drivers/net/ethernet/nvidia/forcedeth.c @@ -5711,6 +5711,7 @@ static int nv_probe(struct pci_dev *pci_dev, const struct pci_device_id *id) u32 phystate_orig = 0, phystate; int phyinitialized = 0; static int printed_version; + u8 mac[ETH_ALEN]; if (!printed_version++) pr_info("Reverse Engineered nForce ethernet driver. Version %s.\n", @@ -5884,50 +5885,52 @@ static int nv_probe(struct pci_dev *pci_dev, const struct pci_device_id *id) txreg = readl(base + NvRegTransmitPoll); if (id->driver_data & DEV_HAS_CORRECT_MACADDR) { /* mac address is already in correct order */ - dev->dev_addr[0] = (np->orig_mac[0] >> 0) & 0xff; - dev->dev_addr[1] = (np->orig_mac[0] >> 8) & 0xff; - dev->dev_addr[2] = (np->orig_mac[0] >> 16) & 0xff; - dev->dev_addr[3] = (np->orig_mac[0] >> 24) & 0xff; - dev->dev_addr[4] = (np->orig_mac[1] >> 0) & 0xff; - dev->dev_addr[5] = (np->orig_mac[1] >> 8) & 0xff; + mac[0] = (np->orig_mac[0] >> 0) & 0xff; + mac[1] = (np->orig_mac[0] >> 8) & 0xff; + mac[2] = (np->orig_mac[0] >> 16) & 0xff; + mac[3] = (np->orig_mac[0] >> 24) & 0xff; + mac[4] = (np->orig_mac[1] >> 0) & 0xff; + mac[5] = (np->orig_mac[1] >> 8) & 0xff; } else if (txreg & NVREG_TRANSMITPOLL_MAC_ADDR_REV) { /* mac address is already in correct order */ - dev->dev_addr[0] = (np->orig_mac[0] >> 0) & 0xff; - dev->dev_addr[1] = (np->orig_mac[0] >> 8) & 0xff; - dev->dev_addr[2] = (np->orig_mac[0] >> 16) & 0xff; - dev->dev_addr[3] = (np->orig_mac[0] >> 24) & 0xff; - dev->dev_addr[4] = (np->orig_mac[1] >> 0) & 0xff; - dev->dev_addr[5] = (np->orig_mac[1] >> 8) & 0xff; + mac[0] = (np->orig_mac[0] >> 0) & 0xff; + mac[1] = (np->orig_mac[0] >> 8) & 0xff; + mac[2] = (np->orig_mac[0] >> 16) & 0xff; + mac[3] = (np->orig_mac[0] >> 24) & 0xff; + mac[4] = (np->orig_mac[1] >> 0) & 0xff; + mac[5] = (np->orig_mac[1] >> 8) & 0xff; /* * Set orig mac address back to the reversed version. * This flag will be cleared during low power transition. * Therefore, we should always put back the reversed address. */ - np->orig_mac[0] = (dev->dev_addr[5] << 0) + (dev->dev_addr[4] << 8) + - (dev->dev_addr[3] << 16) + (dev->dev_addr[2] << 24); - np->orig_mac[1] = (dev->dev_addr[1] << 0) + (dev->dev_addr[0] << 8); + np->orig_mac[0] = (mac[5] << 0) + (mac[4] << 8) + + (mac[3] << 16) + (mac[2] << 24); + np->orig_mac[1] = (mac[1] << 0) + (mac[0] << 8); } else { /* need to reverse mac address to correct order */ - dev->dev_addr[0] = (np->orig_mac[1] >> 8) & 0xff; - dev->dev_addr[1] = (np->orig_mac[1] >> 0) & 0xff; - dev->dev_addr[2] = (np->orig_mac[0] >> 24) & 0xff; - dev->dev_addr[3] = (np->orig_mac[0] >> 16) & 0xff; - dev->dev_addr[4] = (np->orig_mac[0] >> 8) & 0xff; - dev->dev_addr[5] = (np->orig_mac[0] >> 0) & 0xff; + mac[0] = (np->orig_mac[1] >> 8) & 0xff; + mac[1] = (np->orig_mac[1] >> 0) & 0xff; + mac[2] = (np->orig_mac[0] >> 24) & 0xff; + mac[3] = (np->orig_mac[0] >> 16) & 0xff; + mac[4] = (np->orig_mac[0] >> 8) & 0xff; + mac[5] = (np->orig_mac[0] >> 0) & 0xff; writel(txreg|NVREG_TRANSMITPOLL_MAC_ADDR_REV, base + NvRegTransmitPoll); dev_dbg(&pci_dev->dev, "%s: set workaround bit for reversed mac addr\n", __func__); } - if (!is_valid_ether_addr(dev->dev_addr)) { + if (is_valid_ether_addr(mac)) { + eth_hw_addr_set(dev, mac); + } else { /* * Bad mac address. At least one bios sets the mac address * to 01:23:45:67:89:ab */ dev_err(&pci_dev->dev, "Invalid MAC address detected: %pM - Please complain to your hardware vendor.\n", - dev->dev_addr); + mac); eth_hw_addr_random(dev); dev_err(&pci_dev->dev, "Using random MAC address: %pM\n", dev->dev_addr); diff --git a/drivers/net/ethernet/nxp/lpc_eth.c b/drivers/net/ethernet/nxp/lpc_eth.c index 0d289db71b2b..bc39558fe82b 100644 --- a/drivers/net/ethernet/nxp/lpc_eth.c +++ b/drivers/net/ethernet/nxp/lpc_eth.c @@ -419,7 +419,7 @@ struct netdata_local { /* * MAC support functions */ -static void __lpc_set_mac(struct netdata_local *pldat, u8 *mac) +static void __lpc_set_mac(struct netdata_local *pldat, const u8 *mac) { u32 tmp; @@ -1231,6 +1231,7 @@ static int lpc_eth_drv_probe(struct platform_device *pdev) struct net_device *ndev; dma_addr_t dma_handle; struct resource *res; + u8 addr[ETH_ALEN]; int irq, ret; /* Setup network interface for RMII or MII mode */ @@ -1346,7 +1347,8 @@ static int lpc_eth_drv_probe(struct platform_device *pdev) pldat->phy_node = of_parse_phandle(np, "phy-handle", 0); /* Get MAC address from current HW setting (POR state is all zeros) */ - __lpc_get_mac(pldat, ndev->dev_addr); + __lpc_get_mac(pldat, addr); + eth_hw_addr_set(ndev, addr); if (!is_valid_ether_addr(ndev->dev_addr)) { of_get_ethdev_address(np, ndev); diff --git a/drivers/net/ethernet/packetengines/hamachi.c b/drivers/net/ethernet/packetengines/hamachi.c index 1a6336a56d3d..9c408328be0d 100644 --- a/drivers/net/ethernet/packetengines/hamachi.c +++ b/drivers/net/ethernet/packetengines/hamachi.c @@ -592,6 +592,7 @@ static int hamachi_init_one(struct pci_dev *pdev, void *ring_space; dma_addr_t ring_dma; int ret = -ENOMEM; + u8 addr[ETH_ALEN]; /* when built into the kernel, we only print version if device is found */ #ifndef MODULE @@ -628,8 +629,8 @@ static int hamachi_init_one(struct pci_dev *pdev, SET_NETDEV_DEV(dev, &pdev->dev); for (i = 0; i < 6; i++) - dev->dev_addr[i] = 1 ? read_eeprom(ioaddr, 4 + i) - : readb(ioaddr + StationAddr + i); + addr[i] = read_eeprom(ioaddr, 4 + i); + eth_hw_addr_set(dev, addr); #if ! defined(final_version) if (hamachi_debug > 4) diff --git a/drivers/net/ethernet/packetengines/yellowfin.c b/drivers/net/ethernet/packetengines/yellowfin.c index f5cd8f51be7c..12105f62cbdd 100644 --- a/drivers/net/ethernet/packetengines/yellowfin.c +++ b/drivers/net/ethernet/packetengines/yellowfin.c @@ -384,6 +384,7 @@ static int yellowfin_init_one(struct pci_dev *pdev, #else int bar = 1; #endif + u8 addr[ETH_ALEN]; /* when built into the kernel, we only print version if device is found */ #ifndef MODULE @@ -416,12 +417,13 @@ static int yellowfin_init_one(struct pci_dev *pdev, if (drv_flags & DontUseEeprom) for (i = 0; i < 6; i++) - dev->dev_addr[i] = ioread8(ioaddr + StnAddr + i); + addr[i] = ioread8(ioaddr + StnAddr + i); else { int ee_offset = (read_eeprom(ioaddr, 6) == 0xff ? 0x100 : 0); for (i = 0; i < 6; i++) - dev->dev_addr[i] = read_eeprom(ioaddr, ee_offset + i); + addr[i] = read_eeprom(ioaddr, ee_offset + i); } + eth_hw_addr_set(dev, addr); /* Reset the chip. */ iowrite32(0x80000000, ioaddr + DMACtrl); diff --git a/drivers/net/ethernet/pasemi/pasemi_mac.c b/drivers/net/ethernet/pasemi/pasemi_mac.c index 5512e43bafc1..f0ace3a0e85c 100644 --- a/drivers/net/ethernet/pasemi/pasemi_mac.c +++ b/drivers/net/ethernet/pasemi/pasemi_mac.c @@ -1722,7 +1722,7 @@ pasemi_mac_probe(struct pci_dev *pdev, const struct pci_device_id *ent) err = -ENODEV; goto out; } - memcpy(dev->dev_addr, mac->mac_addr, sizeof(mac->mac_addr)); + eth_hw_addr_set(dev, mac->mac_addr); ret = mac_to_intf(mac); if (ret < 0) { diff --git a/drivers/net/ethernet/pensando/ionic/ionic.h b/drivers/net/ethernet/pensando/ionic/ionic.h index d570d03b23f6..5e25411ff02f 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic.h +++ b/drivers/net/ethernet/pensando/ionic/ionic.h @@ -70,8 +70,13 @@ struct ionic_admin_ctx { }; int ionic_adminq_post(struct ionic_lif *lif, struct ionic_admin_ctx *ctx); -int ionic_adminq_wait(struct ionic_lif *lif, struct ionic_admin_ctx *ctx, int err); +int ionic_adminq_wait(struct ionic_lif *lif, struct ionic_admin_ctx *ctx, + const int err, const bool do_msg); int ionic_adminq_post_wait(struct ionic_lif *lif, struct ionic_admin_ctx *ctx); +int ionic_adminq_post_wait_nomsg(struct ionic_lif *lif, struct ionic_admin_ctx *ctx); +void ionic_adminq_netdev_err_print(struct ionic_lif *lif, u8 opcode, + u8 status, int err); + int ionic_dev_cmd_wait(struct ionic *ionic, unsigned long max_wait); int ionic_set_dma_mask(struct ionic *ionic); int ionic_setup(struct ionic *ionic); diff --git a/drivers/net/ethernet/pensando/ionic/ionic_debugfs.c b/drivers/net/ethernet/pensando/ionic/ionic_debugfs.c index 86b79430c2ad..c58217027564 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_debugfs.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_debugfs.c @@ -226,6 +226,50 @@ static int netdev_show(struct seq_file *seq, void *v) } DEFINE_SHOW_ATTRIBUTE(netdev); +static int lif_filters_show(struct seq_file *seq, void *v) +{ + struct ionic_lif *lif = seq->private; + struct ionic_rx_filter *f; + struct hlist_head *head; + struct hlist_node *tmp; + unsigned int i; + + seq_puts(seq, "id flow state type filter\n"); + spin_lock_bh(&lif->rx_filters.lock); + for (i = 0; i < IONIC_RX_FILTER_HLISTS; i++) { + head = &lif->rx_filters.by_id[i]; + hlist_for_each_entry_safe(f, tmp, head, by_id) { + switch (le16_to_cpu(f->cmd.match)) { + case IONIC_RX_FILTER_MATCH_VLAN: + seq_printf(seq, "0x%04x 0x%08x 0x%02x vlan 0x%04x\n", + f->filter_id, f->flow_id, f->state, + le16_to_cpu(f->cmd.vlan.vlan)); + break; + case IONIC_RX_FILTER_MATCH_MAC: + seq_printf(seq, "0x%04x 0x%08x 0x%02x mac %pM\n", + f->filter_id, f->flow_id, f->state, + f->cmd.mac.addr); + break; + case IONIC_RX_FILTER_MATCH_MAC_VLAN: + seq_printf(seq, "0x%04x 0x%08x 0x%02x macvl 0x%04x %pM\n", + f->filter_id, f->flow_id, f->state, + le16_to_cpu(f->cmd.vlan.vlan), + f->cmd.mac.addr); + break; + case IONIC_RX_FILTER_STEER_PKTCLASS: + seq_printf(seq, "0x%04x 0x%08x 0x%02x rxstr 0x%llx\n", + f->filter_id, f->flow_id, f->state, + le64_to_cpu(f->cmd.pkt_class)); + break; + } + } + } + spin_unlock_bh(&lif->rx_filters.lock); + + return 0; +} +DEFINE_SHOW_ATTRIBUTE(lif_filters); + void ionic_debugfs_add_lif(struct ionic_lif *lif) { struct dentry *lif_dentry; @@ -237,6 +281,8 @@ void ionic_debugfs_add_lif(struct ionic_lif *lif) debugfs_create_file("netdev", 0400, lif->dentry, lif->netdev, &netdev_fops); + debugfs_create_file("filters", 0400, lif->dentry, + lif, &lif_filters_fops); } void ionic_debugfs_del_lif(struct ionic_lif *lif) diff --git a/drivers/net/ethernet/pensando/ionic/ionic_devlink.c b/drivers/net/ethernet/pensando/ionic/ionic_devlink.c index 2267da95640b..4297ed9024c0 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_devlink.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_devlink.c @@ -87,7 +87,6 @@ int ionic_devlink_register(struct ionic *ionic) err = devlink_port_register(dl, &ionic->dl_port, 0); if (err) { dev_err(ionic->dev, "devlink_port_register failed: %d\n", err); - devlink_unregister(dl); return err; } diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index a24e2e84611c..63f8a8163b5f 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -1242,137 +1242,6 @@ void ionic_get_stats64(struct net_device *netdev, ns->tx_errors = ns->tx_aborted_errors; } -int ionic_lif_addr_add(struct ionic_lif *lif, const u8 *addr) -{ - struct ionic_admin_ctx ctx = { - .work = COMPLETION_INITIALIZER_ONSTACK(ctx.work), - .cmd.rx_filter_add = { - .opcode = IONIC_CMD_RX_FILTER_ADD, - .lif_index = cpu_to_le16(lif->index), - .match = cpu_to_le16(IONIC_RX_FILTER_MATCH_MAC), - }, - }; - int nfilters = le32_to_cpu(lif->identity->eth.max_ucast_filters); - bool mc = is_multicast_ether_addr(addr); - struct ionic_rx_filter *f; - int err = 0; - - memcpy(ctx.cmd.rx_filter_add.mac.addr, addr, ETH_ALEN); - - spin_lock_bh(&lif->rx_filters.lock); - f = ionic_rx_filter_by_addr(lif, addr); - if (f) { - /* don't bother if we already have it and it is sync'd */ - if (f->state == IONIC_FILTER_STATE_SYNCED) { - spin_unlock_bh(&lif->rx_filters.lock); - return 0; - } - - /* mark preemptively as sync'd to block any parallel attempts */ - f->state = IONIC_FILTER_STATE_SYNCED; - } else { - /* save as SYNCED to catch any DEL requests while processing */ - err = ionic_rx_filter_save(lif, 0, IONIC_RXQ_INDEX_ANY, 0, &ctx, - IONIC_FILTER_STATE_SYNCED); - } - spin_unlock_bh(&lif->rx_filters.lock); - if (err) - return err; - - netdev_dbg(lif->netdev, "rx_filter add ADDR %pM\n", addr); - - /* Don't bother with the write to FW if we know there's no room, - * we can try again on the next sync attempt. - */ - if ((lif->nucast + lif->nmcast) >= nfilters) - err = -ENOSPC; - else - err = ionic_adminq_post_wait(lif, &ctx); - - spin_lock_bh(&lif->rx_filters.lock); - if (err && err != -EEXIST) { - /* set the state back to NEW so we can try again later */ - f = ionic_rx_filter_by_addr(lif, addr); - if (f && f->state == IONIC_FILTER_STATE_SYNCED) { - f->state = IONIC_FILTER_STATE_NEW; - set_bit(IONIC_LIF_F_FILTER_SYNC_NEEDED, lif->state); - } - - spin_unlock_bh(&lif->rx_filters.lock); - - if (err == -ENOSPC) - return 0; - else - return err; - } - - if (mc) - lif->nmcast++; - else - lif->nucast++; - - f = ionic_rx_filter_by_addr(lif, addr); - if (f && f->state == IONIC_FILTER_STATE_OLD) { - /* Someone requested a delete while we were adding - * so update the filter info with the results from the add - * and the data will be there for the delete on the next - * sync cycle. - */ - err = ionic_rx_filter_save(lif, 0, IONIC_RXQ_INDEX_ANY, 0, &ctx, - IONIC_FILTER_STATE_OLD); - } else { - err = ionic_rx_filter_save(lif, 0, IONIC_RXQ_INDEX_ANY, 0, &ctx, - IONIC_FILTER_STATE_SYNCED); - } - - spin_unlock_bh(&lif->rx_filters.lock); - - return err; -} - -int ionic_lif_addr_del(struct ionic_lif *lif, const u8 *addr) -{ - struct ionic_admin_ctx ctx = { - .work = COMPLETION_INITIALIZER_ONSTACK(ctx.work), - .cmd.rx_filter_del = { - .opcode = IONIC_CMD_RX_FILTER_DEL, - .lif_index = cpu_to_le16(lif->index), - }, - }; - struct ionic_rx_filter *f; - int state; - int err; - - spin_lock_bh(&lif->rx_filters.lock); - f = ionic_rx_filter_by_addr(lif, addr); - if (!f) { - spin_unlock_bh(&lif->rx_filters.lock); - return -ENOENT; - } - - netdev_dbg(lif->netdev, "rx_filter del ADDR %pM (id %d)\n", - addr, f->filter_id); - - state = f->state; - ctx.cmd.rx_filter_del.filter_id = cpu_to_le32(f->filter_id); - ionic_rx_filter_free(lif, f); - - if (is_multicast_ether_addr(addr) && lif->nmcast) - lif->nmcast--; - else if (!is_multicast_ether_addr(addr) && lif->nucast) - lif->nucast--; - - spin_unlock_bh(&lif->rx_filters.lock); - - if (state != IONIC_FILTER_STATE_NEW) { - err = ionic_adminq_post_wait(lif, &ctx); - if (err && err != -EEXIST) - return err; - } - - return 0; -} - static int ionic_addr_add(struct net_device *netdev, const u8 *addr) { return ionic_lif_list_addr(netdev_priv(netdev), addr, ADD_ADDR); @@ -1408,7 +1277,7 @@ void ionic_lif_rx_mode(struct ionic_lif *lif) rx_mode |= (nd_flags & IFF_PROMISC) ? IONIC_RX_MODE_F_PROMISC : 0; rx_mode |= (nd_flags & IFF_ALLMULTI) ? IONIC_RX_MODE_F_ALLMULTI : 0; - /* sync the mac filters */ + /* sync the filters */ ionic_rx_filter_sync(lif); /* check for overflow state @@ -1418,14 +1287,12 @@ void ionic_lif_rx_mode(struct ionic_lif *lif) * to see if we can disable NIC PROMISC */ nfilters = le32_to_cpu(lif->identity->eth.max_ucast_filters); - if ((lif->nucast + lif->nmcast) >= nfilters) { + + if (((lif->nucast + lif->nmcast) >= nfilters) || + (lif->max_vlans && lif->nvlans >= lif->max_vlans)) { rx_mode |= IONIC_RX_MODE_F_PROMISC; rx_mode |= IONIC_RX_MODE_F_ALLMULTI; - lif->uc_overflow = true; - lif->mc_overflow = true; - } else if (lif->uc_overflow) { - lif->uc_overflow = false; - lif->mc_overflow = false; + } else { if (!(nd_flags & IFF_PROMISC)) rx_mode &= ~IONIC_RX_MODE_F_PROMISC; if (!(nd_flags & IFF_ALLMULTI)) @@ -1810,59 +1677,30 @@ static int ionic_vlan_rx_add_vid(struct net_device *netdev, __be16 proto, u16 vid) { struct ionic_lif *lif = netdev_priv(netdev); - struct ionic_admin_ctx ctx = { - .work = COMPLETION_INITIALIZER_ONSTACK(ctx.work), - .cmd.rx_filter_add = { - .opcode = IONIC_CMD_RX_FILTER_ADD, - .lif_index = cpu_to_le16(lif->index), - .match = cpu_to_le16(IONIC_RX_FILTER_MATCH_VLAN), - .vlan.vlan = cpu_to_le16(vid), - }, - }; int err; - netdev_dbg(netdev, "rx_filter add VLAN %d\n", vid); - err = ionic_adminq_post_wait(lif, &ctx); + err = ionic_lif_vlan_add(lif, vid); if (err) return err; - spin_lock_bh(&lif->rx_filters.lock); - err = ionic_rx_filter_save(lif, 0, IONIC_RXQ_INDEX_ANY, 0, &ctx, - IONIC_FILTER_STATE_SYNCED); - spin_unlock_bh(&lif->rx_filters.lock); + ionic_lif_rx_mode(lif); - return err; + return 0; } static int ionic_vlan_rx_kill_vid(struct net_device *netdev, __be16 proto, u16 vid) { struct ionic_lif *lif = netdev_priv(netdev); - struct ionic_admin_ctx ctx = { - .work = COMPLETION_INITIALIZER_ONSTACK(ctx.work), - .cmd.rx_filter_del = { - .opcode = IONIC_CMD_RX_FILTER_DEL, - .lif_index = cpu_to_le16(lif->index), - }, - }; - struct ionic_rx_filter *f; + int err; - spin_lock_bh(&lif->rx_filters.lock); + err = ionic_lif_vlan_del(lif, vid); + if (err) + return err; - f = ionic_rx_filter_by_vlan(lif, vid); - if (!f) { - spin_unlock_bh(&lif->rx_filters.lock); - return -ENOENT; - } + ionic_lif_rx_mode(lif); - netdev_dbg(netdev, "rx_filter del VLAN %d (id %d)\n", - vid, f->filter_id); - - ctx.cmd.rx_filter_del.filter_id = cpu_to_le32(f->filter_id); - ionic_rx_filter_free(lif, f); - spin_unlock_bh(&lif->rx_filters.lock); - - return ionic_adminq_post_wait(lif, &ctx); + return 0; } int ionic_lif_rss_config(struct ionic_lif *lif, const u16 types, diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.h b/drivers/net/ethernet/pensando/ionic/ionic_lif.h index 41f28154745f..9f7ab2f17f93 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.h +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.h @@ -189,11 +189,11 @@ struct ionic_lif { u16 rx_mode; u64 hw_features; bool registered; - bool mc_overflow; - bool uc_overflow; u16 lif_type; unsigned int nmcast; unsigned int nucast; + unsigned int nvlans; + unsigned int max_vlans; char name[IONIC_LIF_NAME_MAX_SZ]; union ionic_lif_identity *identity; diff --git a/drivers/net/ethernet/pensando/ionic/ionic_main.c b/drivers/net/ethernet/pensando/ionic/ionic_main.c index bb49f1b8ef67..875f4ec42efe 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_main.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_main.c @@ -212,24 +212,28 @@ static void ionic_adminq_flush(struct ionic_lif *lif) spin_unlock_irqrestore(&lif->adminq_lock, irqflags); } +void ionic_adminq_netdev_err_print(struct ionic_lif *lif, u8 opcode, + u8 status, int err) +{ + netdev_err(lif->netdev, "%s (%d) failed: %s (%d)\n", + ionic_opcode_to_str(opcode), opcode, + ionic_error_to_str(status), err); +} + static int ionic_adminq_check_err(struct ionic_lif *lif, struct ionic_admin_ctx *ctx, - bool timeout) + const bool timeout, + const bool do_msg) { - struct net_device *netdev = lif->netdev; - const char *opcode_str; - const char *status_str; int err = 0; if (ctx->comp.comp.status || timeout) { - opcode_str = ionic_opcode_to_str(ctx->cmd.cmd.opcode); - status_str = ionic_error_to_str(ctx->comp.comp.status); err = timeout ? -ETIMEDOUT : ionic_error_to_errno(ctx->comp.comp.status); - netdev_err(netdev, "%s (%d) failed: %s (%d)\n", - opcode_str, ctx->cmd.cmd.opcode, - timeout ? "TIMEOUT" : status_str, err); + if (do_msg) + ionic_adminq_netdev_err_print(lif, ctx->cmd.cmd.opcode, + ctx->comp.comp.status, err); if (timeout) ionic_adminq_flush(lif); @@ -298,7 +302,8 @@ err_out: return err; } -int ionic_adminq_wait(struct ionic_lif *lif, struct ionic_admin_ctx *ctx, int err) +int ionic_adminq_wait(struct ionic_lif *lif, struct ionic_admin_ctx *ctx, + const int err, const bool do_msg) { struct net_device *netdev = lif->netdev; unsigned long time_limit; @@ -310,7 +315,7 @@ int ionic_adminq_wait(struct ionic_lif *lif, struct ionic_admin_ctx *ctx, int er name = ionic_opcode_to_str(ctx->cmd.cmd.opcode); if (err) { - if (!test_bit(IONIC_LIF_F_FW_RESET, lif->state)) + if (do_msg && !test_bit(IONIC_LIF_F_FW_RESET, lif->state)) netdev_err(netdev, "Posting of %s (%d) failed: %d\n", name, ctx->cmd.cmd.opcode, err); return err; @@ -328,8 +333,9 @@ int ionic_adminq_wait(struct ionic_lif *lif, struct ionic_admin_ctx *ctx, int er /* interrupt the wait if FW stopped */ if (test_bit(IONIC_LIF_F_FW_RESET, lif->state)) { - netdev_err(netdev, "%s (%d) interrupted, FW in reset\n", - name, ctx->cmd.cmd.opcode); + if (do_msg) + netdev_err(netdev, "%s (%d) interrupted, FW in reset\n", + name, ctx->cmd.cmd.opcode); return -ENXIO; } @@ -339,7 +345,9 @@ int ionic_adminq_wait(struct ionic_lif *lif, struct ionic_admin_ctx *ctx, int er dev_dbg(lif->ionic->dev, "%s: elapsed %d msecs\n", __func__, jiffies_to_msecs(time_done - time_start)); - return ionic_adminq_check_err(lif, ctx, time_after_eq(time_done, time_limit)); + return ionic_adminq_check_err(lif, ctx, + time_after_eq(time_done, time_limit), + do_msg); } int ionic_adminq_post_wait(struct ionic_lif *lif, struct ionic_admin_ctx *ctx) @@ -348,7 +356,16 @@ int ionic_adminq_post_wait(struct ionic_lif *lif, struct ionic_admin_ctx *ctx) err = ionic_adminq_post(lif, ctx); - return ionic_adminq_wait(lif, ctx, err); + return ionic_adminq_wait(lif, ctx, err, true); +} + +int ionic_adminq_post_wait_nomsg(struct ionic_lif *lif, struct ionic_admin_ctx *ctx) +{ + int err; + + err = ionic_adminq_post(lif, ctx); + + return ionic_adminq_wait(lif, ctx, err, false); } static void ionic_dev_cmd_clean(struct ionic *ionic) diff --git a/drivers/net/ethernet/pensando/ionic/ionic_phc.c b/drivers/net/ethernet/pensando/ionic/ionic_phc.c index eed2db69d708..887046838b3b 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_phc.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_phc.c @@ -348,7 +348,7 @@ static int ionic_phc_adjfine(struct ptp_clock_info *info, long scaled_ppm) spin_unlock_irqrestore(&phc->lock, irqflags); - return ionic_adminq_wait(phc->lif, &ctx, err); + return ionic_adminq_wait(phc->lif, &ctx, err, true); } static int ionic_phc_adjtime(struct ptp_clock_info *info, s64 delta) @@ -373,7 +373,7 @@ static int ionic_phc_adjtime(struct ptp_clock_info *info, s64 delta) spin_unlock_irqrestore(&phc->lock, irqflags); - return ionic_adminq_wait(phc->lif, &ctx, err); + return ionic_adminq_wait(phc->lif, &ctx, err, true); } static int ionic_phc_settime64(struct ptp_clock_info *info, @@ -402,7 +402,7 @@ static int ionic_phc_settime64(struct ptp_clock_info *info, spin_unlock_irqrestore(&phc->lock, irqflags); - return ionic_adminq_wait(phc->lif, &ctx, err); + return ionic_adminq_wait(phc->lif, &ctx, err, true); } static int ionic_phc_gettimex64(struct ptp_clock_info *info, @@ -459,7 +459,7 @@ static long ionic_phc_aux_work(struct ptp_clock_info *info) spin_unlock_irqrestore(&phc->lock, irqflags); - ionic_adminq_wait(phc->lif, &ctx, err); + ionic_adminq_wait(phc->lif, &ctx, err, true); return phc->aux_work_delay; } diff --git a/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.c b/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.c index 69728f9013cb..f6e785f949f9 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.c @@ -239,6 +239,21 @@ struct ionic_rx_filter *ionic_rx_filter_rxsteer(struct ionic_lif *lif) return NULL; } +static struct ionic_rx_filter *ionic_rx_filter_find(struct ionic_lif *lif, + struct ionic_rx_filter_add_cmd *ac) +{ + switch (le16_to_cpu(ac->match)) { + case IONIC_RX_FILTER_MATCH_VLAN: + return ionic_rx_filter_by_vlan(lif, le16_to_cpu(ac->vlan.vlan)); + case IONIC_RX_FILTER_MATCH_MAC: + return ionic_rx_filter_by_addr(lif, ac->mac.addr); + default: + netdev_err(lif->netdev, "unsupported filter match %d", + le16_to_cpu(ac->match)); + return NULL; + } +} + int ionic_lif_list_addr(struct ionic_lif *lif, const u8 *addr, bool mode) { struct ionic_rx_filter *f; @@ -286,6 +301,228 @@ int ionic_lif_list_addr(struct ionic_lif *lif, const u8 *addr, bool mode) return 0; } +static int ionic_lif_filter_add(struct ionic_lif *lif, + struct ionic_rx_filter_add_cmd *ac) +{ + struct ionic_admin_ctx ctx = { + .work = COMPLETION_INITIALIZER_ONSTACK(ctx.work), + }; + struct ionic_rx_filter *f; + int nfilters; + int err = 0; + + ctx.cmd.rx_filter_add = *ac; + ctx.cmd.rx_filter_add.opcode = IONIC_CMD_RX_FILTER_ADD, + ctx.cmd.rx_filter_add.lif_index = cpu_to_le16(lif->index), + + spin_lock_bh(&lif->rx_filters.lock); + f = ionic_rx_filter_find(lif, &ctx.cmd.rx_filter_add); + if (f) { + /* don't bother if we already have it and it is sync'd */ + if (f->state == IONIC_FILTER_STATE_SYNCED) { + spin_unlock_bh(&lif->rx_filters.lock); + return 0; + } + + /* mark preemptively as sync'd to block any parallel attempts */ + f->state = IONIC_FILTER_STATE_SYNCED; + } else { + /* save as SYNCED to catch any DEL requests while processing */ + err = ionic_rx_filter_save(lif, 0, IONIC_RXQ_INDEX_ANY, 0, &ctx, + IONIC_FILTER_STATE_SYNCED); + } + spin_unlock_bh(&lif->rx_filters.lock); + if (err) + return err; + + /* Don't bother with the write to FW if we know there's no room, + * we can try again on the next sync attempt. + * Since the FW doesn't have a way to tell us the vlan limit, + * we start max_vlans at 0 until we hit the ENOSPC error. + */ + switch (le16_to_cpu(ctx.cmd.rx_filter_add.match)) { + case IONIC_RX_FILTER_MATCH_VLAN: + netdev_dbg(lif->netdev, "%s: rx_filter add VLAN %d\n", + __func__, ctx.cmd.rx_filter_add.vlan.vlan); + if (lif->max_vlans && lif->nvlans >= lif->max_vlans) + err = -ENOSPC; + break; + case IONIC_RX_FILTER_MATCH_MAC: + netdev_dbg(lif->netdev, "%s: rx_filter add ADDR %pM\n", + __func__, ctx.cmd.rx_filter_add.mac.addr); + nfilters = le32_to_cpu(lif->identity->eth.max_ucast_filters); + if ((lif->nucast + lif->nmcast) >= nfilters) + err = -ENOSPC; + break; + } + + if (err != -ENOSPC) + err = ionic_adminq_post_wait_nomsg(lif, &ctx); + + spin_lock_bh(&lif->rx_filters.lock); + + if (err && err != -EEXIST) { + /* set the state back to NEW so we can try again later */ + f = ionic_rx_filter_find(lif, &ctx.cmd.rx_filter_add); + if (f && f->state == IONIC_FILTER_STATE_SYNCED) { + f->state = IONIC_FILTER_STATE_NEW; + + /* If -ENOSPC we won't waste time trying to sync again + * until there is a delete that might make room + */ + if (err != -ENOSPC) + set_bit(IONIC_LIF_F_FILTER_SYNC_NEEDED, lif->state); + } + + spin_unlock_bh(&lif->rx_filters.lock); + + if (err == -ENOSPC) { + if (le16_to_cpu(ctx.cmd.rx_filter_add.match) == IONIC_RX_FILTER_MATCH_VLAN) + lif->max_vlans = lif->nvlans; + return 0; + } + + ionic_adminq_netdev_err_print(lif, ctx.cmd.cmd.opcode, + ctx.comp.comp.status, err); + switch (le16_to_cpu(ctx.cmd.rx_filter_add.match)) { + case IONIC_RX_FILTER_MATCH_VLAN: + netdev_info(lif->netdev, "rx_filter add failed: VLAN %d\n", + ctx.cmd.rx_filter_add.vlan.vlan); + break; + case IONIC_RX_FILTER_MATCH_MAC: + netdev_info(lif->netdev, "rx_filter add failed: ADDR %pM\n", + ctx.cmd.rx_filter_add.mac.addr); + break; + } + + return err; + } + + switch (le16_to_cpu(ctx.cmd.rx_filter_add.match)) { + case IONIC_RX_FILTER_MATCH_VLAN: + lif->nvlans++; + break; + case IONIC_RX_FILTER_MATCH_MAC: + if (is_multicast_ether_addr(ctx.cmd.rx_filter_add.mac.addr)) + lif->nmcast++; + else + lif->nucast++; + break; + } + + f = ionic_rx_filter_find(lif, &ctx.cmd.rx_filter_add); + if (f && f->state == IONIC_FILTER_STATE_OLD) { + /* Someone requested a delete while we were adding + * so update the filter info with the results from the add + * and the data will be there for the delete on the next + * sync cycle. + */ + err = ionic_rx_filter_save(lif, 0, IONIC_RXQ_INDEX_ANY, 0, &ctx, + IONIC_FILTER_STATE_OLD); + } else { + err = ionic_rx_filter_save(lif, 0, IONIC_RXQ_INDEX_ANY, 0, &ctx, + IONIC_FILTER_STATE_SYNCED); + } + + spin_unlock_bh(&lif->rx_filters.lock); + + return err; +} + +int ionic_lif_addr_add(struct ionic_lif *lif, const u8 *addr) +{ + struct ionic_rx_filter_add_cmd ac = { + .match = cpu_to_le16(IONIC_RX_FILTER_MATCH_MAC), + }; + + memcpy(&ac.mac.addr, addr, ETH_ALEN); + + return ionic_lif_filter_add(lif, &ac); +} + +int ionic_lif_vlan_add(struct ionic_lif *lif, const u16 vid) +{ + struct ionic_rx_filter_add_cmd ac = { + .match = cpu_to_le16(IONIC_RX_FILTER_MATCH_VLAN), + .vlan.vlan = cpu_to_le16(vid), + }; + + return ionic_lif_filter_add(lif, &ac); +} + +static int ionic_lif_filter_del(struct ionic_lif *lif, + struct ionic_rx_filter_add_cmd *ac) +{ + struct ionic_admin_ctx ctx = { + .work = COMPLETION_INITIALIZER_ONSTACK(ctx.work), + .cmd.rx_filter_del = { + .opcode = IONIC_CMD_RX_FILTER_DEL, + .lif_index = cpu_to_le16(lif->index), + }, + }; + struct ionic_rx_filter *f; + int state; + int err; + + spin_lock_bh(&lif->rx_filters.lock); + f = ionic_rx_filter_find(lif, ac); + if (!f) { + spin_unlock_bh(&lif->rx_filters.lock); + return -ENOENT; + } + + switch (le16_to_cpu(ac->match)) { + case IONIC_RX_FILTER_MATCH_VLAN: + netdev_dbg(lif->netdev, "%s: rx_filter del VLAN %d id %d\n", + __func__, ac->vlan.vlan, f->filter_id); + lif->nvlans--; + break; + case IONIC_RX_FILTER_MATCH_MAC: + netdev_dbg(lif->netdev, "%s: rx_filter del ADDR %pM id %d\n", + __func__, ac->mac.addr, f->filter_id); + if (is_multicast_ether_addr(ac->mac.addr) && lif->nmcast) + lif->nmcast--; + else if (!is_multicast_ether_addr(ac->mac.addr) && lif->nucast) + lif->nucast--; + break; + } + + state = f->state; + ctx.cmd.rx_filter_del.filter_id = cpu_to_le32(f->filter_id); + ionic_rx_filter_free(lif, f); + + spin_unlock_bh(&lif->rx_filters.lock); + + if (state != IONIC_FILTER_STATE_NEW) { + err = ionic_adminq_post_wait(lif, &ctx); + if (err && err != -EEXIST) + return err; + } + + return 0; +} + +int ionic_lif_addr_del(struct ionic_lif *lif, const u8 *addr) +{ + struct ionic_rx_filter_add_cmd ac = { + .match = cpu_to_le16(IONIC_RX_FILTER_MATCH_MAC), + }; + + memcpy(&ac.mac.addr, addr, ETH_ALEN); + + return ionic_lif_filter_del(lif, &ac); +} + +int ionic_lif_vlan_del(struct ionic_lif *lif, const u16 vid) +{ + struct ionic_rx_filter_add_cmd ac = { + .match = cpu_to_le16(IONIC_RX_FILTER_MATCH_VLAN), + .vlan.vlan = cpu_to_le16(vid), + }; + + return ionic_lif_filter_del(lif, &ac); +} + struct sync_item { struct list_head list; struct ionic_rx_filter f; @@ -340,14 +577,14 @@ loop_out: * they can clear room for some new filters */ list_for_each_entry_safe(sync_item, spos, &sync_del_list, list) { - (void)ionic_lif_addr_del(lif, sync_item->f.cmd.mac.addr); + (void)ionic_lif_filter_del(lif, &sync_item->f.cmd); list_del(&sync_item->list); devm_kfree(dev, sync_item); } list_for_each_entry_safe(sync_item, spos, &sync_add_list, list) { - (void)ionic_lif_addr_add(lif, sync_item->f.cmd.mac.addr); + (void)ionic_lif_filter_add(lif, &sync_item->f.cmd); list_del(&sync_item->list); devm_kfree(dev, sync_item); diff --git a/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.h b/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.h index a66e35f0833b..87b2666f248b 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.h +++ b/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.h @@ -44,5 +44,7 @@ struct ionic_rx_filter *ionic_rx_filter_rxsteer(struct ionic_lif *lif); void ionic_rx_filter_sync(struct ionic_lif *lif); int ionic_lif_list_addr(struct ionic_lif *lif, const u8 *addr, bool mode); int ionic_rx_filters_need_sync(struct ionic_lif *lif); +int ionic_lif_vlan_add(struct ionic_lif *lif, const u16 vid); +int ionic_lif_vlan_del(struct ionic_lif *lif, const u16 vid); #endif /* _IONIC_RX_FILTER_H_ */ diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c index b4e094e6f58c..4cfab4434e80 100644 --- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c +++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c @@ -463,6 +463,7 @@ netxen_read_mac_addr(struct netxen_adapter *adapter) u64 mac_addr; struct net_device *netdev = adapter->netdev; struct pci_dev *pdev = adapter->pdev; + u8 addr[ETH_ALEN]; if (NX_IS_REVISION_P3(adapter->ahw.revision_id)) { if (netxen_p3_get_mac_addr(adapter, &mac_addr) != 0) @@ -474,7 +475,8 @@ netxen_read_mac_addr(struct netxen_adapter *adapter) p = (unsigned char *)&mac_addr; for (i = 0; i < 6; i++) - netdev->dev_addr[i] = *(p + 5 - i); + addr[i] = *(p + 5 - i); + eth_hw_addr_set(netdev, addr); memcpy(adapter->mac_addr, netdev->dev_addr, netdev->addr_len); diff --git a/drivers/net/ethernet/qlogic/qed/qed_debug.c b/drivers/net/ethernet/qlogic/qed/qed_debug.c index 6d693ee380f1..e3edca187ddf 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_debug.c +++ b/drivers/net/ethernet/qlogic/qed/qed_debug.c @@ -1315,7 +1315,6 @@ static u32 qed_dump_common_global_params(struct qed_hwfn *p_hwfn, u8 num_specific_global_params) { struct dbg_tools_data *dev_data = &p_hwfn->dbg_info; - char sw_platform_str[MAX_SW_PLTAFORM_STR_SIZE]; u32 offset = 0; u8 num_params; @@ -1341,8 +1340,6 @@ static u32 qed_dump_common_global_params(struct qed_hwfn *p_hwfn, dump, "platform", s_hw_type_defs[dev_data->hw_type].name); - offset += qed_dump_str_param(dump_buf + offset, - dump, "sw-platform", sw_platform_str); offset += qed_dump_num_param(dump_buf + offset, dump, "pci-func", p_hwfn->abs_pf_id); offset += qed_dump_num_param(dump_buf + offset, @@ -5259,7 +5256,7 @@ enum dbg_status qed_dbg_grc_config(struct qed_hwfn *p_hwfn, */ qed_dbg_grc_init_params(p_hwfn); - if (grc_param >= MAX_DBG_GRC_PARAMS || grc_param < 0) + if (grc_param >= MAX_DBG_GRC_PARAMS) return DBG_STATUS_INVALID_ARGS; if (val < s_grc_param_defs[grc_param].min || val > s_grc_param_defs[grc_param].max) diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c index 6823016ab5a3..18f3bf7c4dfe 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dev.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c @@ -952,7 +952,7 @@ qed_llh_remove_filter(struct qed_hwfn *p_hwfn, } int qed_llh_add_mac_filter(struct qed_dev *cdev, - u8 ppfid, u8 mac_addr[ETH_ALEN]) + u8 ppfid, const u8 mac_addr[ETH_ALEN]) { struct qed_hwfn *p_hwfn = QED_LEADING_HWFN(cdev); struct qed_ptt *p_ptt = qed_ptt_acquire(p_hwfn); diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev_api.h b/drivers/net/ethernet/qlogic/qed/qed_dev_api.h index 6582bfc1b4a9..f8682356d0cf 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dev_api.h +++ b/drivers/net/ethernet/qlogic/qed/qed_dev_api.h @@ -364,7 +364,7 @@ int qed_llh_set_roce_affinity(struct qed_dev *cdev, enum qed_eng eng); * Return: Int. */ int qed_llh_add_mac_filter(struct qed_dev *cdev, - u8 ppfid, u8 mac_addr[ETH_ALEN]); + u8 ppfid, const u8 mac_addr[ETH_ALEN]); /** * qed_llh_remove_mac_filter(): Remove a LLH MAC filter from the given diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c index a116fbc59725..2edd6bf64a3c 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c @@ -2848,7 +2848,7 @@ static int qed_fp_cqe_completion(struct qed_dev *dev, cqe); } -static int qed_req_bulletin_update_mac(struct qed_dev *cdev, u8 *mac) +static int qed_req_bulletin_update_mac(struct qed_dev *cdev, const u8 *mac) { int i, ret; diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.c b/drivers/net/ethernet/qlogic/qed/qed_ll2.c index 3fedcefc36d8..ed274f033626 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_ll2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.c @@ -378,7 +378,7 @@ static int qed_ll2_txq_completion(struct qed_hwfn *p_hwfn, void *p_cookie) num_bds_in_packet = p_pkt->bd_used; list_del(&p_pkt->list_entry); - if (num_bds < num_bds_in_packet) { + if (unlikely(num_bds < num_bds_in_packet)) { DP_NOTICE(p_hwfn, "Rest of BDs does not cover whole packet\n"); goto out; @@ -488,7 +488,7 @@ qed_ll2_rxq_handle_completion(struct qed_hwfn *p_hwfn, if (!list_empty(&p_rx->active_descq)) p_pkt = list_first_entry(&p_rx->active_descq, struct qed_ll2_rx_packet, list_entry); - if (!p_pkt) { + if (unlikely(!p_pkt)) { DP_NOTICE(p_hwfn, "[%d] LL2 Rx completion but active_descq is empty\n", p_ll2_conn->input.conn_type); @@ -501,7 +501,7 @@ qed_ll2_rxq_handle_completion(struct qed_hwfn *p_hwfn, qed_ll2_rxq_parse_reg(p_hwfn, p_cqe, &data); else qed_ll2_rxq_parse_gsi(p_hwfn, p_cqe, &data); - if (qed_chain_consume(&p_rx->rxq_chain) != p_pkt->rxq_bd) + if (unlikely(qed_chain_consume(&p_rx->rxq_chain) != p_pkt->rxq_bd)) DP_NOTICE(p_hwfn, "Mismatch between active_descq and the LL2 Rx chain\n"); @@ -623,18 +623,18 @@ static bool qed_ll2_lb_rxq_handler_slowpath(struct qed_hwfn *p_hwfn, struct core_rx_slow_path_cqe *p_cqe) { - struct ooo_opaque *iscsi_ooo; + struct ooo_opaque *ooo_opq; u32 cid; if (p_cqe->ramrod_cmd_id != CORE_RAMROD_RX_QUEUE_FLUSH) return false; - iscsi_ooo = (struct ooo_opaque *)&p_cqe->opaque_data; - if (iscsi_ooo->ooo_opcode != TCP_EVENT_DELETE_ISLES) + ooo_opq = (struct ooo_opaque *)&p_cqe->opaque_data; + if (ooo_opq->ooo_opcode != TCP_EVENT_DELETE_ISLES) return false; /* Need to make a flush */ - cid = le32_to_cpu(iscsi_ooo->cid); + cid = le32_to_cpu(ooo_opq->cid); qed_ooo_release_connection_isles(p_hwfn, p_hwfn->p_ooo_info, cid); return true; @@ -650,7 +650,7 @@ static int qed_ll2_lb_rxq_handler(struct qed_hwfn *p_hwfn, union core_rx_cqe_union *cqe = NULL; u16 cq_new_idx = 0, cq_old_idx = 0; struct qed_ooo_buffer *p_buffer; - struct ooo_opaque *iscsi_ooo; + struct ooo_opaque *ooo_opq; u8 placement_offset = 0; u8 cqe_type; @@ -671,7 +671,7 @@ static int qed_ll2_lb_rxq_handler(struct qed_hwfn *p_hwfn, &cqe->rx_cqe_sp)) continue; - if (cqe_type != CORE_RX_CQE_TYPE_REGULAR) { + if (unlikely(cqe_type != CORE_RX_CQE_TYPE_REGULAR)) { DP_NOTICE(p_hwfn, "Got a non-regular LB LL2 completion [type 0x%02x]\n", cqe_type); @@ -683,22 +683,21 @@ static int qed_ll2_lb_rxq_handler(struct qed_hwfn *p_hwfn, parse_flags = le16_to_cpu(p_cqe_fp->parse_flags.flags); packet_length = le16_to_cpu(p_cqe_fp->packet_length); vlan = le16_to_cpu(p_cqe_fp->vlan); - iscsi_ooo = (struct ooo_opaque *)&p_cqe_fp->opaque_data; - qed_ooo_save_history_entry(p_hwfn, p_hwfn->p_ooo_info, - iscsi_ooo); - cid = le32_to_cpu(iscsi_ooo->cid); + ooo_opq = (struct ooo_opaque *)&p_cqe_fp->opaque_data; + qed_ooo_save_history_entry(p_hwfn, p_hwfn->p_ooo_info, ooo_opq); + cid = le32_to_cpu(ooo_opq->cid); /* Process delete isle first */ - if (iscsi_ooo->drop_size) + if (ooo_opq->drop_size) qed_ooo_delete_isles(p_hwfn, p_hwfn->p_ooo_info, cid, - iscsi_ooo->drop_isle, - iscsi_ooo->drop_size); + ooo_opq->drop_isle, + ooo_opq->drop_size); - if (iscsi_ooo->ooo_opcode == TCP_EVENT_NOP) + if (ooo_opq->ooo_opcode == TCP_EVENT_NOP) continue; /* Now process create/add/join isles */ - if (list_empty(&p_rx->active_descq)) { + if (unlikely(list_empty(&p_rx->active_descq))) { DP_NOTICE(p_hwfn, "LL2 OOO RX chain has no submitted buffers\n" ); @@ -708,12 +707,12 @@ static int qed_ll2_lb_rxq_handler(struct qed_hwfn *p_hwfn, p_pkt = list_first_entry(&p_rx->active_descq, struct qed_ll2_rx_packet, list_entry); - if ((iscsi_ooo->ooo_opcode == TCP_EVENT_ADD_NEW_ISLE) || - (iscsi_ooo->ooo_opcode == TCP_EVENT_ADD_ISLE_RIGHT) || - (iscsi_ooo->ooo_opcode == TCP_EVENT_ADD_ISLE_LEFT) || - (iscsi_ooo->ooo_opcode == TCP_EVENT_ADD_PEN) || - (iscsi_ooo->ooo_opcode == TCP_EVENT_JOIN)) { - if (!p_pkt) { + if (likely(ooo_opq->ooo_opcode == TCP_EVENT_ADD_NEW_ISLE || + ooo_opq->ooo_opcode == TCP_EVENT_ADD_ISLE_RIGHT || + ooo_opq->ooo_opcode == TCP_EVENT_ADD_ISLE_LEFT || + ooo_opq->ooo_opcode == TCP_EVENT_ADD_PEN || + ooo_opq->ooo_opcode == TCP_EVENT_JOIN)) { + if (unlikely(!p_pkt)) { DP_NOTICE(p_hwfn, "LL2 OOO RX packet is not valid\n"); return -EIO; @@ -727,19 +726,19 @@ static int qed_ll2_lb_rxq_handler(struct qed_hwfn *p_hwfn, qed_chain_consume(&p_rx->rxq_chain); list_add_tail(&p_pkt->list_entry, &p_rx->free_descq); - switch (iscsi_ooo->ooo_opcode) { + switch (ooo_opq->ooo_opcode) { case TCP_EVENT_ADD_NEW_ISLE: qed_ooo_add_new_isle(p_hwfn, p_hwfn->p_ooo_info, cid, - iscsi_ooo->ooo_isle, + ooo_opq->ooo_isle, p_buffer); break; case TCP_EVENT_ADD_ISLE_RIGHT: qed_ooo_add_new_buffer(p_hwfn, p_hwfn->p_ooo_info, cid, - iscsi_ooo->ooo_isle, + ooo_opq->ooo_isle, p_buffer, QED_OOO_RIGHT_BUF); break; @@ -747,7 +746,7 @@ static int qed_ll2_lb_rxq_handler(struct qed_hwfn *p_hwfn, qed_ooo_add_new_buffer(p_hwfn, p_hwfn->p_ooo_info, cid, - iscsi_ooo->ooo_isle, + ooo_opq->ooo_isle, p_buffer, QED_OOO_LEFT_BUF); break; @@ -755,13 +754,12 @@ static int qed_ll2_lb_rxq_handler(struct qed_hwfn *p_hwfn, qed_ooo_add_new_buffer(p_hwfn, p_hwfn->p_ooo_info, cid, - iscsi_ooo->ooo_isle + - 1, + ooo_opq->ooo_isle + 1, p_buffer, QED_OOO_LEFT_BUF); qed_ooo_join_isles(p_hwfn, p_hwfn->p_ooo_info, - cid, iscsi_ooo->ooo_isle); + cid, ooo_opq->ooo_isle); break; case TCP_EVENT_ADD_PEN: num_ooo_add_to_peninsula++; @@ -773,7 +771,7 @@ static int qed_ll2_lb_rxq_handler(struct qed_hwfn *p_hwfn, } else { DP_NOTICE(p_hwfn, "Unexpected event (%d) TX OOO completion\n", - iscsi_ooo->ooo_opcode); + ooo_opq->ooo_opcode); } } @@ -885,16 +883,16 @@ static int qed_ll2_lb_txq_completion(struct qed_hwfn *p_hwfn, void *p_cookie) u16 new_idx = 0, num_bds = 0; int rc; - if (!p_ll2_conn) + if (unlikely(!p_ll2_conn)) return 0; - if (!QED_LL2_TX_REGISTERED(p_ll2_conn)) + if (unlikely(!QED_LL2_TX_REGISTERED(p_ll2_conn))) return 0; new_idx = le16_to_cpu(*p_tx->p_fw_cons); num_bds = ((s16)new_idx - (s16)p_tx->bds_idx); - if (!num_bds) + if (unlikely(!num_bds)) return 0; while (num_bds) { @@ -903,10 +901,10 @@ static int qed_ll2_lb_txq_completion(struct qed_hwfn *p_hwfn, void *p_cookie) p_pkt = list_first_entry(&p_tx->active_descq, struct qed_ll2_tx_packet, list_entry); - if (!p_pkt) + if (unlikely(!p_pkt)) return -EINVAL; - if (p_pkt->bd_used != 1) { + if (unlikely(p_pkt->bd_used != 1)) { DP_NOTICE(p_hwfn, "Unexpectedly many BDs(%d) in TX OOO completion\n", p_pkt->bd_used); @@ -1034,7 +1032,7 @@ static int qed_sp_ll2_tx_queue_start(struct qed_hwfn *p_hwfn, if (!QED_LL2_TX_REGISTERED(p_ll2_conn)) return 0; - if (p_ll2_conn->input.conn_type == QED_LL2_TYPE_OOO) + if (likely(p_ll2_conn->input.conn_type == QED_LL2_TYPE_OOO)) p_ll2_conn->tx_stats_en = 0; else p_ll2_conn->tx_stats_en = 1; @@ -1885,8 +1883,8 @@ qed_ll2_prepare_tx_packet_set_bd(struct qed_hwfn *p_hwfn, } start_bd = (struct core_tx_bd *)qed_chain_produce(p_tx_chain); - if (QED_IS_IWARP_PERSONALITY(p_hwfn) && - p_ll2->input.conn_type == QED_LL2_TYPE_OOO) { + if (likely(QED_IS_IWARP_PERSONALITY(p_hwfn) && + p_ll2->input.conn_type == QED_LL2_TYPE_OOO)) { start_bd->nw_vlan_or_lb_echo = cpu_to_le16(IWARP_LL2_IN_ORDER_TX_QUEUE); } else { @@ -2007,28 +2005,29 @@ int qed_ll2_prepare_tx_packet(void *cxt, int rc = 0; p_ll2_conn = qed_ll2_handle_sanity(p_hwfn, connection_handle); - if (!p_ll2_conn) + if (unlikely(!p_ll2_conn)) return -EINVAL; p_tx = &p_ll2_conn->tx_queue; p_tx_chain = &p_tx->txq_chain; - if (pkt->num_of_bds > p_ll2_conn->input.tx_max_bds_per_packet) + if (unlikely(pkt->num_of_bds > p_ll2_conn->input.tx_max_bds_per_packet)) return -EIO; spin_lock_irqsave(&p_tx->lock, flags); - if (p_tx->cur_send_packet) { + if (unlikely(p_tx->cur_send_packet)) { rc = -EEXIST; goto out; } /* Get entry, but only if we have tx elements for it */ - if (!list_empty(&p_tx->free_descq)) + if (unlikely(!list_empty(&p_tx->free_descq))) p_curp = list_first_entry(&p_tx->free_descq, struct qed_ll2_tx_packet, list_entry); - if (p_curp && qed_chain_get_elem_left(p_tx_chain) < pkt->num_of_bds) + if (unlikely(p_curp && + qed_chain_get_elem_left(p_tx_chain) < pkt->num_of_bds)) p_curp = NULL; - if (!p_curp) { + if (unlikely(!p_curp)) { rc = -EBUSY; goto out; } @@ -2057,16 +2056,16 @@ int qed_ll2_set_fragment_of_tx_packet(void *cxt, unsigned long flags; p_ll2_conn = qed_ll2_handle_sanity(p_hwfn, connection_handle); - if (!p_ll2_conn) + if (unlikely(!p_ll2_conn)) return -EINVAL; - if (!p_ll2_conn->tx_queue.cur_send_packet) + if (unlikely(!p_ll2_conn->tx_queue.cur_send_packet)) return -EINVAL; p_cur_send_packet = p_ll2_conn->tx_queue.cur_send_packet; cur_send_frag_num = p_ll2_conn->tx_queue.cur_send_frag_num; - if (cur_send_frag_num >= p_cur_send_packet->bd_used) + if (unlikely(cur_send_frag_num >= p_cur_send_packet->bd_used)) return -EINVAL; /* Fill the BD information, and possibly notify FW */ @@ -2693,7 +2692,7 @@ static int qed_ll2_start_xmit(struct qed_dev *cdev, struct sk_buff *skb, */ nr_frags = skb_shinfo(skb)->nr_frags; - if (1 + nr_frags > CORE_LL2_TX_MAX_BDS_PER_PACKET) { + if (unlikely(1 + nr_frags > CORE_LL2_TX_MAX_BDS_PER_PACKET)) { DP_ERR(cdev, "Cannot transmit a packet with %d fragments\n", 1 + nr_frags); return -EINVAL; @@ -2735,7 +2734,7 @@ static int qed_ll2_start_xmit(struct qed_dev *cdev, struct sk_buff *skb, */ rc = qed_ll2_prepare_tx_packet(p_hwfn, cdev->ll2->handle, &pkt, 1); - if (rc) + if (unlikely(rc)) goto err; for (i = 0; i < nr_frags; i++) { @@ -2759,7 +2758,7 @@ static int qed_ll2_start_xmit(struct qed_dev *cdev, struct sk_buff *skb, /* if failed not much to do here, partial packet has been posted * we can't free memory, will need to wait for completion */ - if (rc) + if (unlikely(rc)) goto err2; } diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c index 359ad859ae18..7673b3e07736 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_main.c +++ b/drivers/net/ethernet/qlogic/qed/qed_main.c @@ -2888,7 +2888,7 @@ static int qed_update_drv_state(struct qed_dev *cdev, bool active) return status; } -static int qed_update_mac(struct qed_dev *cdev, u8 *mac) +static int qed_update_mac(struct qed_dev *cdev, const u8 *mac) { struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev); struct qed_ptt *ptt; diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c index 11a52a4a673b..64678a256f3b 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c @@ -2851,7 +2851,7 @@ int qed_mcp_ov_update_mtu(struct qed_hwfn *p_hwfn, } int qed_mcp_ov_update_mac(struct qed_hwfn *p_hwfn, - struct qed_ptt *p_ptt, u8 *mac) + struct qed_ptt *p_ptt, const u8 *mac) { struct qed_mcp_mb_params mb_params; u32 mfw_mac[2]; diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.h b/drivers/net/ethernet/qlogic/qed/qed_mcp.h index 9e1de1191bd4..564723800d15 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.h +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.h @@ -536,7 +536,7 @@ int qed_mcp_ov_update_mtu(struct qed_hwfn *p_hwfn, * Return: Int - 0 - Operation was successul. */ int qed_mcp_ov_update_mac(struct qed_hwfn *p_hwfn, - struct qed_ptt *p_ptt, u8 *mac); + struct qed_ptt *p_ptt, const u8 *mac); /** * qed_mcp_ov_update_wol(): Send WOL mode to MFW. diff --git a/drivers/net/ethernet/qlogic/qed/qed_ooo.c b/drivers/net/ethernet/qlogic/qed/qed_ooo.c index b8c5641b29a8..5d725f59db24 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_ooo.c +++ b/drivers/net/ethernet/qlogic/qed/qed_ooo.c @@ -26,12 +26,12 @@ static struct qed_ooo_archipelago u32 idx = (cid & 0xffff) - p_ooo_info->cid_base; struct qed_ooo_archipelago *p_archipelago; - if (idx >= p_ooo_info->max_num_archipelagos) + if (unlikely(idx >= p_ooo_info->max_num_archipelagos)) return NULL; p_archipelago = &p_ooo_info->p_archipelagos_mem[idx]; - if (list_empty(&p_archipelago->isles_list)) + if (unlikely(list_empty(&p_archipelago->isles_list))) return NULL; return p_archipelago; @@ -46,7 +46,7 @@ static struct qed_ooo_isle *qed_ooo_seek_isle(struct qed_hwfn *p_hwfn, u8 the_num_of_isle = 1; p_archipelago = qed_ooo_seek_archipelago(p_hwfn, p_ooo_info, cid); - if (!p_archipelago) { + if (unlikely(!p_archipelago)) { DP_NOTICE(p_hwfn, "Connection %d is not found in OOO list\n", cid); return NULL; @@ -362,7 +362,7 @@ void qed_ooo_add_new_isle(struct qed_hwfn *p_hwfn, if (ooo_isle > 1) { p_prev_isle = qed_ooo_seek_isle(p_hwfn, p_ooo_info, cid, ooo_isle - 1); - if (!p_prev_isle) { + if (unlikely(!p_prev_isle)) { DP_NOTICE(p_hwfn, "Isle %d is not found(cid %d)\n", ooo_isle - 1, cid); @@ -370,7 +370,7 @@ void qed_ooo_add_new_isle(struct qed_hwfn *p_hwfn, } } p_archipelago = qed_ooo_seek_archipelago(p_hwfn, p_ooo_info, cid); - if (!p_archipelago && (ooo_isle != 1)) { + if (unlikely(!p_archipelago && ooo_isle != 1)) { DP_NOTICE(p_hwfn, "Connection %d is not found in OOO list\n", cid); return; @@ -381,7 +381,7 @@ void qed_ooo_add_new_isle(struct qed_hwfn *p_hwfn, struct qed_ooo_isle, list_entry); list_del(&p_isle->list_entry); - if (!list_empty(&p_isle->buffers_list)) { + if (unlikely(!list_empty(&p_isle->buffers_list))) { DP_NOTICE(p_hwfn, "Free isle is not empty\n"); INIT_LIST_HEAD(&p_isle->buffers_list); } @@ -418,13 +418,13 @@ void qed_ooo_add_new_buffer(struct qed_hwfn *p_hwfn, struct qed_ooo_isle *p_isle = NULL; p_isle = qed_ooo_seek_isle(p_hwfn, p_ooo_info, cid, ooo_isle); - if (!p_isle) { + if (unlikely(!p_isle)) { DP_NOTICE(p_hwfn, "Isle %d is not found(cid %d)\n", ooo_isle, cid); return; } - if (buffer_side == QED_OOO_LEFT_BUF) + if (unlikely(buffer_side == QED_OOO_LEFT_BUF)) list_add(&p_buffer->list_entry, &p_isle->buffers_list); else list_add_tail(&p_buffer->list_entry, &p_isle->buffers_list); @@ -438,7 +438,7 @@ void qed_ooo_join_isles(struct qed_hwfn *p_hwfn, p_right_isle = qed_ooo_seek_isle(p_hwfn, p_ooo_info, cid, left_isle + 1); - if (!p_right_isle) { + if (unlikely(!p_right_isle)) { DP_NOTICE(p_hwfn, "Right isle %d is not found(cid %d)\n", left_isle + 1, cid); @@ -450,7 +450,7 @@ void qed_ooo_join_isles(struct qed_hwfn *p_hwfn, if (left_isle) { p_left_isle = qed_ooo_seek_isle(p_hwfn, p_ooo_info, cid, left_isle); - if (!p_left_isle) { + if (unlikely(!p_left_isle)) { DP_NOTICE(p_hwfn, "Left isle %d is not found(cid %d)\n", left_isle, cid); diff --git a/drivers/net/ethernet/qlogic/qed/qed_rdma.c b/drivers/net/ethernet/qlogic/qed/qed_rdma.c index fe0bb11d0e43..7f3e84b8622d 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_rdma.c +++ b/drivers/net/ethernet/qlogic/qed/qed_rdma.c @@ -1965,7 +1965,7 @@ static void qed_rdma_remove_user(void *rdma_cxt, u16 dpi) static int qed_roce_ll2_set_mac_filter(struct qed_dev *cdev, u8 *old_mac_address, - u8 *new_mac_address) + const u8 *new_mac_address) { int rc = 0; diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.c b/drivers/net/ethernet/qlogic/qed/qed_sriov.c index f88f58ec2a20..8ac38828ba45 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sriov.c +++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.c @@ -5224,7 +5224,6 @@ void qed_iov_wq_stop(struct qed_dev *cdev, bool schedule_first) cancel_delayed_work_sync(&cdev->hwfns[i].iov_task); } - flush_workqueue(cdev->hwfns[i].iov_wq); destroy_workqueue(cdev->hwfns[i].iov_wq); } } diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.h b/drivers/net/ethernet/qlogic/qed/qed_sriov.h index 1edf9c44dc67..f448e3dd6c8b 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sriov.h +++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.h @@ -478,6 +478,18 @@ static inline int qed_sriov_disable(struct qed_dev *cdev, bool pci_enabled) static inline void qed_inform_vf_link_state(struct qed_hwfn *hwfn) { } + +static inline void qed_sriov_vfpf_malicious(struct qed_hwfn *p_hwfn, + struct fw_err_data *p_data) +{ +} + +static inline int qed_sriov_eqe_event(struct qed_hwfn *p_hwfn, u8 opcode, + __le16 echo, union event_ring_data *data, + u8 fw_return_code) +{ + return 0; +} #endif #define qed_for_each_vf(_p_hwfn, _i) \ diff --git a/drivers/net/ethernet/qlogic/qed/qed_vf.c b/drivers/net/ethernet/qlogic/qed/qed_vf.c index 220a95fa96e1..597cd9cd57b5 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_vf.c +++ b/drivers/net/ethernet/qlogic/qed/qed_vf.c @@ -1373,7 +1373,7 @@ exit: int qed_vf_pf_bulletin_update_mac(struct qed_hwfn *p_hwfn, - u8 *p_mac) + const u8 *p_mac) { struct qed_vf_iov *p_iov = p_hwfn->vf_iov_info; struct vfpf_bulletin_update_mac_tlv *p_req; diff --git a/drivers/net/ethernet/qlogic/qed/qed_vf.h b/drivers/net/ethernet/qlogic/qed/qed_vf.h index 8718760443be..306b5f4bc632 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_vf.h +++ b/drivers/net/ethernet/qlogic/qed/qed_vf.h @@ -1070,7 +1070,7 @@ u32 qed_vf_hw_bar_size(struct qed_hwfn *p_hwfn, enum BAR_ID bar_id); * * Return: Int. */ -int qed_vf_pf_bulletin_update_mac(struct qed_hwfn *p_hwfn, u8 *p_mac); +int qed_vf_pf_bulletin_update_mac(struct qed_hwfn *p_hwfn, const u8 *p_mac); #else static inline void qed_vf_get_link_params(struct qed_hwfn *p_hwfn, @@ -1259,7 +1259,7 @@ static inline int qed_vf_pf_tunnel_param_update(struct qed_hwfn *p_hwfn, } static inline int qed_vf_pf_bulletin_update_mac(struct qed_hwfn *p_hwfn, - u8 *p_mac) + const u8 *p_mac) { return -EINVAL; } diff --git a/drivers/net/ethernet/qlogic/qede/qede_filter.c b/drivers/net/ethernet/qlogic/qede/qede_filter.c index 03c51dd37e1f..3010833ddde3 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_filter.c +++ b/drivers/net/ethernet/qlogic/qede/qede_filter.c @@ -617,7 +617,7 @@ void qede_fill_rss_params(struct qede_dev *edev, static int qede_set_ucast_rx_mac(struct qede_dev *edev, enum qed_filter_xcast_params_type opcode, - unsigned char mac[ETH_ALEN]) + const unsigned char mac[ETH_ALEN]) { struct qed_filter_ucast_params ucast; diff --git a/drivers/net/ethernet/qlogic/qla3xxx.c b/drivers/net/ethernet/qlogic/qla3xxx.c index 395f054e9e0c..1e6d72adfe43 100644 --- a/drivers/net/ethernet/qlogic/qla3xxx.c +++ b/drivers/net/ethernet/qlogic/qla3xxx.c @@ -508,10 +508,12 @@ static void eeprom_readword(struct ql3_adapter *qdev, static void ql_set_mac_addr(struct net_device *ndev, u16 *addr) { - __le16 *p = (__le16 *)ndev->dev_addr; - p[0] = cpu_to_le16(addr[0]); - p[1] = cpu_to_le16(addr[1]); - p[2] = cpu_to_le16(addr[2]); + __le16 buf[ETH_ALEN / 2]; + + buf[0] = cpu_to_le16(addr[0]); + buf[1] = cpu_to_le16(addr[1]); + buf[2] = cpu_to_le16(addr[2]); + eth_hw_addr_set(ndev, (u8 *)buf); } static int ql_get_nvram_params(struct ql3_adapter *qdev) diff --git a/drivers/net/ethernet/qualcomm/emac/emac-mac.c b/drivers/net/ethernet/qualcomm/emac/emac-mac.c index 87b8c032195d..06104d2ff5b3 100644 --- a/drivers/net/ethernet/qualcomm/emac/emac-mac.c +++ b/drivers/net/ethernet/qualcomm/emac/emac-mac.c @@ -420,7 +420,7 @@ static void emac_mac_dma_config(struct emac_adapter *adpt) } /* set MAC address */ -static void emac_set_mac_address(struct emac_adapter *adpt, u8 *addr) +static void emac_set_mac_address(struct emac_adapter *adpt, const u8 *addr) { u32 sta; diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c index 13d8eb43a485..1b2119b1d48a 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c @@ -224,7 +224,7 @@ void rmnet_vnd_setup(struct net_device *rmnet_dev) rmnet_dev->netdev_ops = &rmnet_vnd_ops; rmnet_dev->mtu = RMNET_DFLT_PACKET_SIZE; rmnet_dev->needed_headroom = RMNET_NEEDED_HEADROOM; - eth_random_addr(rmnet_dev->dev_addr); + eth_hw_addr_random(rmnet_dev); rmnet_dev->tx_queue_len = RMNET_TX_QUEUE_LEN; /* Raw IP mode */ diff --git a/drivers/net/ethernet/rdc/r6040.c b/drivers/net/ethernet/rdc/r6040.c index 01ef5efd7bc2..a6bf7d505178 100644 --- a/drivers/net/ethernet/rdc/r6040.c +++ b/drivers/net/ethernet/rdc/r6040.c @@ -453,7 +453,7 @@ static void r6040_down(struct net_device *dev) { struct r6040_private *lp = netdev_priv(dev); void __iomem *ioaddr = lp->base; - u16 *adrp; + const u16 *adrp; /* Stop MAC */ iowrite16(MSK_INT, ioaddr + MIER); /* Mask Off Interrupt */ @@ -462,7 +462,7 @@ static void r6040_down(struct net_device *dev) r6040_reset_mac(lp); /* Restore MAC Address to MIDx */ - adrp = (u16 *) dev->dev_addr; + adrp = (const u16 *) dev->dev_addr; iowrite16(adrp[0], ioaddr + MID_0L); iowrite16(adrp[1], ioaddr + MID_0M); iowrite16(adrp[2], ioaddr + MID_0H); @@ -731,13 +731,13 @@ static void r6040_mac_address(struct net_device *dev) { struct r6040_private *lp = netdev_priv(dev); void __iomem *ioaddr = lp->base; - u16 *adrp; + const u16 *adrp; /* Reset MAC */ r6040_reset_mac(lp); /* Restore MAC Address */ - adrp = (u16 *) dev->dev_addr; + adrp = (const u16 *) dev->dev_addr; iowrite16(adrp[0], ioaddr + MID_0L); iowrite16(adrp[1], ioaddr + MID_0M); iowrite16(adrp[2], ioaddr + MID_0H); @@ -849,13 +849,13 @@ static void r6040_multicast_list(struct net_device *dev) unsigned long flags; struct netdev_hw_addr *ha; int i; - u16 *adrp; + const u16 *adrp; u16 hash_table[4] = { 0 }; spin_lock_irqsave(&lp->lock, flags); /* Keep our MAC Address */ - adrp = (u16 *)dev->dev_addr; + adrp = (const u16 *)dev->dev_addr; iowrite16(adrp[0], ioaddr + MID_0L); iowrite16(adrp[1], ioaddr + MID_0M); iowrite16(adrp[2], ioaddr + MID_0H); @@ -1031,8 +1031,8 @@ static int r6040_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) void __iomem *ioaddr; int err, io_size = R6040_IO_SIZE; static int card_idx = -1; + u16 addr[ETH_ALEN / 2]; int bar = 0; - u16 *adrp; pr_info("%s\n", version); @@ -1102,14 +1102,14 @@ static int r6040_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) /* Set MAC address */ card_idx++; - adrp = (u16 *)dev->dev_addr; - adrp[0] = ioread16(ioaddr + MID_0L); - adrp[1] = ioread16(ioaddr + MID_0M); - adrp[2] = ioread16(ioaddr + MID_0H); + addr[0] = ioread16(ioaddr + MID_0L); + addr[1] = ioread16(ioaddr + MID_0M); + addr[2] = ioread16(ioaddr + MID_0H); + eth_hw_addr_set(dev, (u8 *)addr); /* Some bootloader/BIOSes do not initialize * MAC address, warn about that */ - if (!(adrp[0] || adrp[1] || adrp[2])) { + if (!(addr[0] || addr[1] || addr[2])) { netdev_warn(dev, "MAC address not initialized, " "generating random\n"); eth_hw_addr_random(dev); diff --git a/drivers/net/ethernet/realtek/8139cp.c b/drivers/net/ethernet/realtek/8139cp.c index 614aac780b6b..4f39f843bb3a 100644 --- a/drivers/net/ethernet/realtek/8139cp.c +++ b/drivers/net/ethernet/realtek/8139cp.c @@ -1889,6 +1889,7 @@ static int cp_init_one (struct pci_dev *pdev, const struct pci_device_id *ent) void __iomem *regs; resource_size_t pciaddr; unsigned int addr_len, i, pci_using_dac; + __le16 addr[ETH_ALEN / 2]; pr_info_once("%s", version); @@ -1979,8 +1980,8 @@ static int cp_init_one (struct pci_dev *pdev, const struct pci_device_id *ent) /* read MAC address from EEPROM */ addr_len = read_eeprom (regs, 0, 8) == 0x8129 ? 8 : 6; for (i = 0; i < 3; i++) - ((__le16 *) (dev->dev_addr))[i] = - cpu_to_le16(read_eeprom (regs, i + 7, addr_len)); + addr[i] = cpu_to_le16(read_eeprom (regs, i + 7, addr_len)); + eth_hw_addr_set(dev, (u8 *)addr); dev->netdev_ops = &cp_netdev_ops; netif_napi_add(dev, &cp->napi, cp_rx_poll, 16); diff --git a/drivers/net/ethernet/realtek/8139too.c b/drivers/net/ethernet/realtek/8139too.c index 75b5ac91132b..15b40fd93cd2 100644 --- a/drivers/net/ethernet/realtek/8139too.c +++ b/drivers/net/ethernet/realtek/8139too.c @@ -945,6 +945,7 @@ static int rtl8139_init_one(struct pci_dev *pdev, { struct net_device *dev = NULL; struct rtl8139_private *tp; + __le16 addr[ETH_ALEN / 2]; int i, addr_len, option; void __iomem *ioaddr; static int board_idx = -1; @@ -994,8 +995,8 @@ static int rtl8139_init_one(struct pci_dev *pdev, addr_len = read_eeprom (ioaddr, 0, 8) == 0x8129 ? 8 : 6; for (i = 0; i < 3; i++) - ((__le16 *) (dev->dev_addr))[i] = - cpu_to_le16(read_eeprom (ioaddr, i + 7, addr_len)); + addr[i] = cpu_to_le16(read_eeprom (ioaddr, i + 7, addr_len)); + eth_hw_addr_set(dev, (u8 *)addr); /* The Rtl8139-specific entries in the device structure. */ dev->netdev_ops = &rtl8139_netdev_ops; diff --git a/drivers/net/ethernet/realtek/atp.c b/drivers/net/ethernet/realtek/atp.c index b6c849b258a0..6cbcb3164367 100644 --- a/drivers/net/ethernet/realtek/atp.c +++ b/drivers/net/ethernet/realtek/atp.c @@ -368,6 +368,7 @@ static int __init atp_probe1(long ioaddr) static void __init get_node_ID(struct net_device *dev) { long ioaddr = dev->base_addr; + __be16 addr[ETH_ALEN / 2]; int sa_offset = 0; int i; @@ -379,8 +380,9 @@ static void __init get_node_ID(struct net_device *dev) sa_offset = 15; for (i = 0; i < 3; i++) - ((__be16 *)dev->dev_addr)[i] = + addr[i] = cpu_to_be16(eeprom_op(ioaddr, EE_READ(sa_offset + i))); + eth_hw_addr_set(dev, (u8 *)addr); write_reg(ioaddr, CMR2, CMR2_NULL); } diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index 59e87d21577a..bbe21db20417 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -5218,7 +5218,7 @@ static int rtl_get_ether_clk(struct rtl8169_private *tp) static void rtl_init_mac_address(struct rtl8169_private *tp) { struct net_device *dev = tp->dev; - u8 *mac_addr = dev->dev_addr; + u8 mac_addr[ETH_ALEN]; int rc; rc = eth_platform_get_mac_address(tp_to_dev(tp), mac_addr); @@ -5236,6 +5236,7 @@ static void rtl_init_mac_address(struct rtl8169_private *tp) eth_hw_addr_random(dev); dev_warn(tp_to_dev(tp), "can't read MAC address, setting random one\n"); done: + eth_hw_addr_set(dev, mac_addr); rtl_rar_set(tp, mac_addr); } diff --git a/drivers/net/ethernet/renesas/ravb.h b/drivers/net/ethernet/renesas/ravb.h index 5dc1324786e0..08062d73df10 100644 --- a/drivers/net/ethernet/renesas/ravb.h +++ b/drivers/net/ethernet/renesas/ravb.h @@ -196,12 +196,15 @@ enum ravb_reg { MAHR = 0x05c0, MALR = 0x05c8, TROCR = 0x0700, /* R-Car Gen3 and RZ/G2L only */ + CXR41 = 0x0708, /* RZ/G2L only */ + CXR42 = 0x0710, /* RZ/G2L only */ CEFCR = 0x0740, FRECR = 0x0748, TSFRCR = 0x0750, TLFRCR = 0x0758, RFCR = 0x0760, MAFCR = 0x0778, + CSR0 = 0x0800, /* RZ/G2L only */ }; @@ -826,7 +829,7 @@ enum ECSR_BIT { ECSR_MPD = 0x00000002, ECSR_LCHNG = 0x00000004, ECSR_PHYI = 0x00000008, - ECSR_PFRI = 0x00000010, + ECSR_PFRI = 0x00000010, /* Documented for R-Car Gen3 and RZ/G2L */ }; /* ECSIPR */ @@ -962,6 +965,11 @@ enum CXR31_BIT { CXR31_SEL_LINK1 = 0x00000008, }; +enum CSR0_BIT { + CSR0_TPE = 0x00000010, + CSR0_RPE = 0x00000020, +}; + #define DBAT_ENTRY_NUM 22 #define RX_QUEUE_OFFSET 4 #define NUM_RX_QUEUE 2 @@ -970,6 +978,7 @@ enum CXR31_BIT { #define RX_BUF_SZ (2048 - ETH_FCS_LEN + sizeof(__sum16)) #define GBETH_RX_BUFF_MAX 8192 +#define GBETH_RX_DESC_DATA_SIZE 4080 struct ravb_tstamp_skb { struct list_head list; @@ -1009,16 +1018,18 @@ struct ravb_hw_info { netdev_features_t net_features; int stats_len; size_t max_rx_len; - u32 tsrq; + u32 tccr_mask; + u32 rx_max_buf_size; unsigned aligned_tx: 1; /* hardware features */ unsigned internal_delay:1; /* AVB-DMAC has internal delays */ unsigned tx_counters:1; /* E-MAC has TX counters */ + unsigned carrier_counters:1; /* E-MAC has carrier counters */ unsigned multi_irqs:1; /* AVB-DMAC and E-MAC has multiple irqs */ unsigned gptp:1; /* AVB-DMAC has gPTP support */ unsigned ccc_gac:1; /* AVB-DMAC has gPTP support active in config mode */ - unsigned nc_queue:1; /* AVB-DMAC has NC queue */ + unsigned nc_queues:1; /* AVB-DMAC has RX and TX NC queues */ unsigned magic_pkt:1; /* E-MAC supports magic packet detection */ unsigned half_duplex:1; /* E-MAC supports half duplex mode */ }; @@ -1037,9 +1048,11 @@ struct ravb_private { struct ravb_desc *desc_bat; dma_addr_t rx_desc_dma[NUM_RX_QUEUE]; dma_addr_t tx_desc_dma[NUM_TX_QUEUE]; + struct ravb_rx_desc *gbeth_rx_ring; struct ravb_ex_rx_desc *rx_ring[NUM_RX_QUEUE]; struct ravb_tx_desc *tx_ring[NUM_TX_QUEUE]; void *tx_align[NUM_TX_QUEUE]; + struct sk_buff *rx_1st_skb; struct sk_buff **rx_skb[NUM_RX_QUEUE]; struct sk_buff **tx_skb[NUM_TX_QUEUE]; u32 rx_over_errors; diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index 50038e76c72f..b4c597f4040c 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -136,13 +136,15 @@ static void ravb_read_mac_address(struct device_node *np, if (ret) { u32 mahr = ravb_read(ndev, MAHR); u32 malr = ravb_read(ndev, MALR); + u8 addr[ETH_ALEN]; - ndev->dev_addr[0] = (mahr >> 24) & 0xFF; - ndev->dev_addr[1] = (mahr >> 16) & 0xFF; - ndev->dev_addr[2] = (mahr >> 8) & 0xFF; - ndev->dev_addr[3] = (mahr >> 0) & 0xFF; - ndev->dev_addr[4] = (malr >> 8) & 0xFF; - ndev->dev_addr[5] = (malr >> 0) & 0xFF; + addr[0] = (mahr >> 24) & 0xFF; + addr[1] = (mahr >> 16) & 0xFF; + addr[2] = (mahr >> 8) & 0xFF; + addr[3] = (mahr >> 0) & 0xFF; + addr[4] = (malr >> 8) & 0xFF; + addr[5] = (malr >> 0) & 0xFF; + eth_hw_addr_set(ndev, addr); } } @@ -236,10 +238,30 @@ static int ravb_tx_free(struct net_device *ndev, int q, bool free_txed_only) static void ravb_rx_ring_free_gbeth(struct net_device *ndev, int q) { - /* Place holder */ + struct ravb_private *priv = netdev_priv(ndev); + unsigned int ring_size; + unsigned int i; + + if (!priv->gbeth_rx_ring) + return; + + for (i = 0; i < priv->num_rx_ring[q]; i++) { + struct ravb_rx_desc *desc = &priv->gbeth_rx_ring[i]; + + if (!dma_mapping_error(ndev->dev.parent, + le32_to_cpu(desc->dptr))) + dma_unmap_single(ndev->dev.parent, + le32_to_cpu(desc->dptr), + GBETH_RX_BUFF_MAX, + DMA_FROM_DEVICE); + } + ring_size = sizeof(struct ravb_rx_desc) * (priv->num_rx_ring[q] + 1); + dma_free_coherent(ndev->dev.parent, ring_size, priv->gbeth_rx_ring, + priv->rx_desc_dma[q]); + priv->gbeth_rx_ring = NULL; } -static void ravb_rx_ring_free(struct net_device *ndev, int q) +static void ravb_rx_ring_free_rcar(struct net_device *ndev, int q) { struct ravb_private *priv = netdev_priv(ndev); unsigned int ring_size; @@ -307,10 +329,36 @@ static void ravb_ring_free(struct net_device *ndev, int q) static void ravb_rx_ring_format_gbeth(struct net_device *ndev, int q) { - /* Place holder */ + struct ravb_private *priv = netdev_priv(ndev); + struct ravb_rx_desc *rx_desc; + unsigned int rx_ring_size; + dma_addr_t dma_addr; + unsigned int i; + + rx_ring_size = sizeof(*rx_desc) * priv->num_rx_ring[q]; + memset(priv->gbeth_rx_ring, 0, rx_ring_size); + /* Build RX ring buffer */ + for (i = 0; i < priv->num_rx_ring[q]; i++) { + /* RX descriptor */ + rx_desc = &priv->gbeth_rx_ring[i]; + rx_desc->ds_cc = cpu_to_le16(GBETH_RX_DESC_DATA_SIZE); + dma_addr = dma_map_single(ndev->dev.parent, priv->rx_skb[q][i]->data, + GBETH_RX_BUFF_MAX, + DMA_FROM_DEVICE); + /* We just set the data size to 0 for a failed mapping which + * should prevent DMA from happening... + */ + if (dma_mapping_error(ndev->dev.parent, dma_addr)) + rx_desc->ds_cc = cpu_to_le16(0); + rx_desc->dptr = cpu_to_le32(dma_addr); + rx_desc->die_dt = DT_FEMPTY; + } + rx_desc = &priv->gbeth_rx_ring[i]; + rx_desc->dptr = cpu_to_le32((u32)priv->rx_desc_dma[q]); + rx_desc->die_dt = DT_LINKFIX; /* type */ } -static void ravb_rx_ring_format(struct net_device *ndev, int q) +static void ravb_rx_ring_format_rcar(struct net_device *ndev, int q) { struct ravb_private *priv = netdev_priv(ndev); struct ravb_ex_rx_desc *rx_desc; @@ -385,11 +433,18 @@ static void ravb_ring_format(struct net_device *ndev, int q) static void *ravb_alloc_rx_desc_gbeth(struct net_device *ndev, int q) { - /* Place holder */ - return NULL; + struct ravb_private *priv = netdev_priv(ndev); + unsigned int ring_size; + + ring_size = sizeof(struct ravb_rx_desc) * (priv->num_rx_ring[q] + 1); + + priv->gbeth_rx_ring = dma_alloc_coherent(ndev->dev.parent, ring_size, + &priv->rx_desc_dma[q], + GFP_KERNEL); + return priv->gbeth_rx_ring; } -static void *ravb_alloc_rx_desc(struct net_device *ndev, int q) +static void *ravb_alloc_rx_desc_rcar(struct net_device *ndev, int q) { struct ravb_private *priv = netdev_priv(ndev); unsigned int ring_size; @@ -466,10 +521,10 @@ static void ravb_emac_init_gbeth(struct net_device *ndev) /* Receive frame limit set register */ ravb_write(ndev, GBETH_RX_BUFF_MAX + ETH_FCS_LEN, RFLR); - /* PAUSE prohibition */ + /* EMAC Mode: PAUSE prohibition; Duplex; TX; RX; CRC Pass Through */ ravb_write(ndev, ECMR_ZPF | ((priv->duplex > 0) ? ECMR_DM : 0) | ECMR_TE | ECMR_RE | ECMR_RCPT | - ECMR_TXF | ECMR_RXF | ECMR_PRM, ECMR); + ECMR_TXF | ECMR_RXF, ECMR); ravb_set_rate_gbeth(ndev); @@ -481,12 +536,12 @@ static void ravb_emac_init_gbeth(struct net_device *ndev) /* E-MAC status register clear */ ravb_write(ndev, ECSR_ICD | ECSR_LCHNG | ECSR_PFRI, ECSR); + ravb_write(ndev, CSR0_TPE | CSR0_RPE, CSR0); /* E-MAC interrupt enable register */ ravb_write(ndev, ECSIPR_ICDIP, ECSIPR); - ravb_modify(ndev, CXR31, CXR31_SEL_LINK1, 0); - ravb_modify(ndev, CXR31, CXR31_SEL_LINK0, CXR31_SEL_LINK0); + ravb_modify(ndev, CXR31, CXR31_SEL_LINK0 | CXR31_SEL_LINK1, CXR31_SEL_LINK0); } static void ravb_emac_init_rcar(struct net_device *ndev) @@ -535,7 +590,7 @@ static int ravb_dmac_init_gbeth(struct net_device *ndev) /* Descriptor format */ ravb_ring_format(ndev, RAVB_BE); - /* Set AVB RX */ + /* Set DMAC RX */ ravb_write(ndev, 0x60000000, RCR); /* Set Max Frame Length (RTC) */ @@ -681,15 +736,151 @@ static void ravb_rx_csum(struct sk_buff *skb) skb_trim(skb, skb->len - sizeof(__sum16)); } +static struct sk_buff *ravb_get_skb_gbeth(struct net_device *ndev, int entry, + struct ravb_rx_desc *desc) +{ + struct ravb_private *priv = netdev_priv(ndev); + struct sk_buff *skb; + + skb = priv->rx_skb[RAVB_BE][entry]; + priv->rx_skb[RAVB_BE][entry] = NULL; + dma_unmap_single(ndev->dev.parent, le32_to_cpu(desc->dptr), + ALIGN(GBETH_RX_BUFF_MAX, 16), DMA_FROM_DEVICE); + + return skb; +} + /* Packet receive function for Gigabit Ethernet */ static bool ravb_rx_gbeth(struct net_device *ndev, int *quota, int q) { - /* Place holder */ - return true; + struct ravb_private *priv = netdev_priv(ndev); + const struct ravb_hw_info *info = priv->info; + struct net_device_stats *stats; + struct ravb_rx_desc *desc; + struct sk_buff *skb; + dma_addr_t dma_addr; + u8 desc_status; + int boguscnt; + u16 pkt_len; + u8 die_dt; + int entry; + int limit; + + entry = priv->cur_rx[q] % priv->num_rx_ring[q]; + boguscnt = priv->dirty_rx[q] + priv->num_rx_ring[q] - priv->cur_rx[q]; + stats = &priv->stats[q]; + + boguscnt = min(boguscnt, *quota); + limit = boguscnt; + desc = &priv->gbeth_rx_ring[entry]; + while (desc->die_dt != DT_FEMPTY) { + /* Descriptor type must be checked before all other reads */ + dma_rmb(); + desc_status = desc->msc; + pkt_len = le16_to_cpu(desc->ds_cc) & RX_DS; + + if (--boguscnt < 0) + break; + + /* We use 0-byte descriptors to mark the DMA mapping errors */ + if (!pkt_len) + continue; + + if (desc_status & MSC_MC) + stats->multicast++; + + if (desc_status & (MSC_CRC | MSC_RFE | MSC_RTSF | MSC_RTLF | MSC_CEEF)) { + stats->rx_errors++; + if (desc_status & MSC_CRC) + stats->rx_crc_errors++; + if (desc_status & MSC_RFE) + stats->rx_frame_errors++; + if (desc_status & (MSC_RTLF | MSC_RTSF)) + stats->rx_length_errors++; + if (desc_status & MSC_CEEF) + stats->rx_missed_errors++; + } else { + die_dt = desc->die_dt & 0xF0; + switch (die_dt) { + case DT_FSINGLE: + skb = ravb_get_skb_gbeth(ndev, entry, desc); + skb_put(skb, pkt_len); + skb->protocol = eth_type_trans(skb, ndev); + napi_gro_receive(&priv->napi[q], skb); + stats->rx_packets++; + stats->rx_bytes += pkt_len; + break; + case DT_FSTART: + priv->rx_1st_skb = ravb_get_skb_gbeth(ndev, entry, desc); + skb_put(priv->rx_1st_skb, pkt_len); + break; + case DT_FMID: + skb = ravb_get_skb_gbeth(ndev, entry, desc); + skb_copy_to_linear_data_offset(priv->rx_1st_skb, + priv->rx_1st_skb->len, + skb->data, + pkt_len); + skb_put(priv->rx_1st_skb, pkt_len); + dev_kfree_skb(skb); + break; + case DT_FEND: + skb = ravb_get_skb_gbeth(ndev, entry, desc); + skb_copy_to_linear_data_offset(priv->rx_1st_skb, + priv->rx_1st_skb->len, + skb->data, + pkt_len); + skb_put(priv->rx_1st_skb, pkt_len); + dev_kfree_skb(skb); + priv->rx_1st_skb->protocol = + eth_type_trans(priv->rx_1st_skb, ndev); + napi_gro_receive(&priv->napi[q], + priv->rx_1st_skb); + stats->rx_packets++; + stats->rx_bytes += priv->rx_1st_skb->len; + break; + } + } + + entry = (++priv->cur_rx[q]) % priv->num_rx_ring[q]; + desc = &priv->gbeth_rx_ring[entry]; + } + + /* Refill the RX ring buffers. */ + for (; priv->cur_rx[q] - priv->dirty_rx[q] > 0; priv->dirty_rx[q]++) { + entry = priv->dirty_rx[q] % priv->num_rx_ring[q]; + desc = &priv->gbeth_rx_ring[entry]; + desc->ds_cc = cpu_to_le16(GBETH_RX_DESC_DATA_SIZE); + + if (!priv->rx_skb[q][entry]) { + skb = netdev_alloc_skb(ndev, info->max_rx_len); + if (!skb) + break; + ravb_set_buffer_align(skb); + dma_addr = dma_map_single(ndev->dev.parent, + skb->data, + GBETH_RX_BUFF_MAX, + DMA_FROM_DEVICE); + skb_checksum_none_assert(skb); + /* We just set the data size to 0 for a failed mapping + * which should prevent DMA from happening... + */ + if (dma_mapping_error(ndev->dev.parent, dma_addr)) + desc->ds_cc = cpu_to_le16(0); + desc->dptr = cpu_to_le32(dma_addr); + priv->rx_skb[q][entry] = skb; + } + /* Descriptor type must be set after all the above writes */ + dma_wmb(); + desc->die_dt = DT_FEMPTY; + } + + *quota -= limit - (++boguscnt); + + return boguscnt <= 0; } /* Packet receive function for Ethernet AVB */ -static bool ravb_rcar_rx(struct net_device *ndev, int *quota, int q) +static bool ravb_rx_rcar(struct net_device *ndev, int *quota, int q) { struct ravb_private *priv = netdev_priv(ndev); const struct ravb_hw_info *info = priv->info; @@ -832,7 +1023,7 @@ static int ravb_stop_dma(struct net_device *ndev) int error; /* Wait for stopping the hardware TX process */ - error = ravb_wait(ndev, TCCR, info->tsrq, 0); + error = ravb_wait(ndev, TCCR, info->tccr_mask, 0); if (error) return error; @@ -988,7 +1179,7 @@ static irqreturn_t ravb_interrupt(int irq, void *dev_id) result = IRQ_HANDLED; /* Network control and best effort queue RX/TX */ - if (info->nc_queue) { + if (info->nc_queues) { for (q = RAVB_NC; q >= RAVB_BE; q--) { if (ravb_queue_interrupt(ndev, q)) result = IRQ_HANDLED; @@ -1084,16 +1275,25 @@ static int ravb_poll(struct napi_struct *napi, int budget) struct net_device *ndev = napi->dev; struct ravb_private *priv = netdev_priv(ndev); const struct ravb_hw_info *info = priv->info; + bool gptp = info->gptp || info->ccc_gac; + struct ravb_rx_desc *desc; unsigned long flags; int q = napi - priv->napi; int mask = BIT(q); int quota = budget; + unsigned int entry; + if (!gptp) { + entry = priv->cur_rx[q] % priv->num_rx_ring[q]; + desc = &priv->gbeth_rx_ring[entry]; + } /* Processing RX Descriptor Ring */ /* Clear RX interrupt */ ravb_write(ndev, ~(mask | RIS0_RESERVED), RIS0); - if (ravb_rx(ndev, "a, q)) - goto out; + if (gptp || desc->die_dt != DT_FEMPTY) { + if (ravb_rx(ndev, "a, q)) + goto out; + } /* Processing TX Descriptor Ring */ spin_lock_irqsave(&priv->lock, flags); @@ -1118,7 +1318,7 @@ static int ravb_poll(struct napi_struct *napi, int budget) /* Receive error message handling */ priv->rx_over_errors = priv->stats[RAVB_BE].rx_over_errors; - if (info->nc_queue) + if (info->nc_queues) priv->rx_over_errors += priv->stats[RAVB_NC].rx_over_errors; if (priv->rx_over_errors != ndev->stats.rx_over_errors) ndev->stats.rx_over_errors = priv->rx_over_errors; @@ -1295,6 +1495,24 @@ static void ravb_set_msglevel(struct net_device *ndev, u32 value) priv->msg_enable = value; } +static const char ravb_gstrings_stats_gbeth[][ETH_GSTRING_LEN] = { + "rx_queue_0_current", + "tx_queue_0_current", + "rx_queue_0_dirty", + "tx_queue_0_dirty", + "rx_queue_0_packets", + "tx_queue_0_packets", + "rx_queue_0_bytes", + "tx_queue_0_bytes", + "rx_queue_0_mcast_packets", + "rx_queue_0_errors", + "rx_queue_0_crc_errors", + "rx_queue_0_frame_errors", + "rx_queue_0_length_errors", + "rx_queue_0_csum_offload_errors", + "rx_queue_0_over_errors", +}; + static const char ravb_gstrings_stats[][ETH_GSTRING_LEN] = { "rx_queue_0_current", "tx_queue_0_current", @@ -1351,7 +1569,7 @@ static void ravb_get_ethtool_stats(struct net_device *ndev, int i = 0; int q; - num_rx_q = info->nc_queue ? NUM_RX_QUEUE : 1; + num_rx_q = info->nc_queues ? NUM_RX_QUEUE : 1; /* Device-specific stats */ for (q = RAVB_BE; q < num_rx_q; q++) { struct net_device_stats *stats = &priv->stats[q]; @@ -1428,7 +1646,7 @@ static int ravb_set_ringparam(struct net_device *ndev, /* Free all the skb's in the RX queue and the DMA buffers. */ ravb_ring_free(ndev, RAVB_BE); - if (info->nc_queue) + if (info->nc_queues) ravb_ring_free(ndev, RAVB_NC); } @@ -1548,7 +1766,7 @@ static int ravb_open(struct net_device *ndev) int error; napi_enable(&priv->napi[RAVB_BE]); - if (info->nc_queue) + if (info->nc_queues) napi_enable(&priv->napi[RAVB_NC]); if (!info->multi_irqs) { @@ -1623,7 +1841,7 @@ out_free_irq_emac: out_free_irq: free_irq(ndev->irq, ndev); out_napi_off: - if (info->nc_queue) + if (info->nc_queues) napi_disable(&priv->napi[RAVB_NC]); napi_disable(&priv->napi[RAVB_BE]); return error; @@ -1673,7 +1891,7 @@ static void ravb_tx_timeout_work(struct work_struct *work) } ravb_ring_free(ndev, RAVB_BE); - if (info->nc_queue) + if (info->nc_queues) ravb_ring_free(ndev, RAVB_NC); /* Device init */ @@ -1855,6 +2073,13 @@ static struct net_device_stats *ravb_get_stats(struct net_device *ndev) ravb_write(ndev, 0, TROCR); /* (write clear) */ } + if (info->carrier_counters) { + nstats->collisions += ravb_read(ndev, CXR41); + ravb_write(ndev, 0, CXR41); /* (write clear) */ + nstats->tx_carrier_errors += ravb_read(ndev, CXR42); + ravb_write(ndev, 0, CXR42); /* (write clear) */ + } + nstats->rx_packets = stats0->rx_packets; nstats->tx_packets = stats0->tx_packets; nstats->rx_bytes = stats0->rx_bytes; @@ -1866,7 +2091,7 @@ static struct net_device_stats *ravb_get_stats(struct net_device *ndev) nstats->rx_length_errors = stats0->rx_length_errors; nstats->rx_missed_errors = stats0->rx_missed_errors; nstats->rx_over_errors = stats0->rx_over_errors; - if (info->nc_queue) { + if (info->nc_queues) { stats1 = &priv->stats[RAVB_NC]; nstats->rx_packets += stats1->rx_packets; @@ -1947,13 +2172,13 @@ static int ravb_close(struct net_device *ndev) } free_irq(ndev->irq, ndev); - if (info->nc_queue) + if (info->nc_queues) napi_disable(&priv->napi[RAVB_NC]); napi_disable(&priv->napi[RAVB_BE]); /* Free all the skb's in the RX queue and the DMA buffers. */ ravb_ring_free(ndev, RAVB_BE); - if (info->nc_queue) + if (info->nc_queues) ravb_ring_free(ndev, RAVB_NC); return 0; @@ -2173,10 +2398,10 @@ static int ravb_mdio_release(struct ravb_private *priv) } static const struct ravb_hw_info ravb_gen3_hw_info = { - .rx_ring_free = ravb_rx_ring_free, - .rx_ring_format = ravb_rx_ring_format, - .alloc_rx_desc = ravb_alloc_rx_desc, - .receive = ravb_rcar_rx, + .rx_ring_free = ravb_rx_ring_free_rcar, + .rx_ring_format = ravb_rx_ring_format_rcar, + .alloc_rx_desc = ravb_alloc_rx_desc_rcar, + .receive = ravb_rx_rcar, .set_rate = ravb_set_rate_rcar, .set_feature = ravb_set_features_rcar, .dmac_init = ravb_dmac_init_rcar, @@ -2187,20 +2412,21 @@ static const struct ravb_hw_info ravb_gen3_hw_info = { .net_features = NETIF_F_RXCSUM, .stats_len = ARRAY_SIZE(ravb_gstrings_stats), .max_rx_len = RX_BUF_SZ + RAVB_ALIGN - 1, - .tsrq = TCCR_TSRQ0 | TCCR_TSRQ1 | TCCR_TSRQ2 | TCCR_TSRQ3, + .tccr_mask = TCCR_TSRQ0 | TCCR_TSRQ1 | TCCR_TSRQ2 | TCCR_TSRQ3, + .rx_max_buf_size = SZ_2K, .internal_delay = 1, .tx_counters = 1, .multi_irqs = 1, .ccc_gac = 1, - .nc_queue = 1, + .nc_queues = 1, .magic_pkt = 1, }; static const struct ravb_hw_info ravb_gen2_hw_info = { - .rx_ring_free = ravb_rx_ring_free, - .rx_ring_format = ravb_rx_ring_format, - .alloc_rx_desc = ravb_alloc_rx_desc, - .receive = ravb_rcar_rx, + .rx_ring_free = ravb_rx_ring_free_rcar, + .rx_ring_format = ravb_rx_ring_format_rcar, + .alloc_rx_desc = ravb_alloc_rx_desc_rcar, + .receive = ravb_rx_rcar, .set_rate = ravb_set_rate_rcar, .set_feature = ravb_set_features_rcar, .dmac_init = ravb_dmac_init_rcar, @@ -2211,10 +2437,11 @@ static const struct ravb_hw_info ravb_gen2_hw_info = { .net_features = NETIF_F_RXCSUM, .stats_len = ARRAY_SIZE(ravb_gstrings_stats), .max_rx_len = RX_BUF_SZ + RAVB_ALIGN - 1, - .tsrq = TCCR_TSRQ0 | TCCR_TSRQ1 | TCCR_TSRQ2 | TCCR_TSRQ3, + .tccr_mask = TCCR_TSRQ0 | TCCR_TSRQ1 | TCCR_TSRQ2 | TCCR_TSRQ3, + .rx_max_buf_size = SZ_2K, .aligned_tx = 1, .gptp = 1, - .nc_queue = 1, + .nc_queues = 1, .magic_pkt = 1, }; @@ -2227,10 +2454,15 @@ static const struct ravb_hw_info gbeth_hw_info = { .set_feature = ravb_set_features_gbeth, .dmac_init = ravb_dmac_init_gbeth, .emac_init = ravb_emac_init_gbeth, - .max_rx_len = GBETH_RX_BUFF_MAX + RAVB_ALIGN - 1, - .tsrq = TCCR_TSRQ0, + .gstrings_stats = ravb_gstrings_stats_gbeth, + .gstrings_size = sizeof(ravb_gstrings_stats_gbeth), + .stats_len = ARRAY_SIZE(ravb_gstrings_stats_gbeth), + .max_rx_len = ALIGN(GBETH_RX_BUFF_MAX, RAVB_ALIGN), + .tccr_mask = TCCR_TSRQ0, + .rx_max_buf_size = SZ_8K, .aligned_tx = 1, .tx_counters = 1, + .carrier_counters = 1, .half_duplex = 1, }; @@ -2389,7 +2621,7 @@ static int ravb_probe(struct platform_device *pdev) priv->pdev = pdev; priv->num_tx_ring[RAVB_BE] = BE_TX_RING_SIZE; priv->num_rx_ring[RAVB_BE] = BE_RX_RING_SIZE; - if (info->nc_queue) { + if (info->nc_queues) { priv->num_tx_ring[RAVB_NC] = NC_TX_RING_SIZE; priv->num_rx_ring[RAVB_NC] = NC_RX_RING_SIZE; } @@ -2452,7 +2684,7 @@ static int ravb_probe(struct platform_device *pdev) } clk_prepare_enable(priv->refclk); - ndev->max_mtu = 2048 - (ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN); + ndev->max_mtu = info->rx_max_buf_size - (ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN); ndev->min_mtu = ETH_MIN_MTU; /* FIXME: R-Car Gen2 has 4byte alignment restriction for tx buffer @@ -2525,7 +2757,7 @@ static int ravb_probe(struct platform_device *pdev) } netif_napi_add(ndev, &priv->napi[RAVB_BE], ravb_poll, 64); - if (info->nc_queue) + if (info->nc_queues) netif_napi_add(ndev, &priv->napi[RAVB_NC], ravb_poll, 64); /* Network device register */ @@ -2544,7 +2776,7 @@ static int ravb_probe(struct platform_device *pdev) return 0; out_napi_del: - if (info->nc_queue) + if (info->nc_queues) netif_napi_del(&priv->napi[RAVB_NC]); netif_napi_del(&priv->napi[RAVB_BE]); @@ -2585,7 +2817,7 @@ static int ravb_remove(struct platform_device *pdev) ravb_write(ndev, CCC_OPC_RESET, CCC); pm_runtime_put_sync(&pdev->dev); unregister_netdev(ndev); - if (info->nc_queue) + if (info->nc_queues) netif_napi_del(&priv->napi[RAVB_NC]); netif_napi_del(&priv->napi[RAVB_BE]); ravb_mdio_release(priv); @@ -2609,7 +2841,7 @@ static int ravb_wol_setup(struct net_device *ndev) /* Only allow ECI interrupts */ synchronize_irq(priv->emac_irq); - if (info->nc_queue) + if (info->nc_queues) napi_disable(&priv->napi[RAVB_NC]); napi_disable(&priv->napi[RAVB_BE]); ravb_write(ndev, ECSIPR_MPDIP, ECSIPR); @@ -2626,7 +2858,7 @@ static int ravb_wol_restore(struct net_device *ndev) const struct ravb_hw_info *info = priv->info; int ret; - if (info->nc_queue) + if (info->nc_queues) napi_enable(&priv->napi[RAVB_NC]); napi_enable(&priv->napi[RAVB_BE]); diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index 0a7d23df45f2..a3fbb2221c9a 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -1157,13 +1157,15 @@ static void read_mac_address(struct net_device *ndev, unsigned char *mac) } else { u32 mahr = sh_eth_read(ndev, MAHR); u32 malr = sh_eth_read(ndev, MALR); + u8 addr[ETH_ALEN]; - ndev->dev_addr[0] = (mahr >> 24) & 0xFF; - ndev->dev_addr[1] = (mahr >> 16) & 0xFF; - ndev->dev_addr[2] = (mahr >> 8) & 0xFF; - ndev->dev_addr[3] = (mahr >> 0) & 0xFF; - ndev->dev_addr[4] = (malr >> 8) & 0xFF; - ndev->dev_addr[5] = (malr >> 0) & 0xFF; + addr[0] = (mahr >> 24) & 0xFF; + addr[1] = (mahr >> 16) & 0xFF; + addr[2] = (mahr >> 8) & 0xFF; + addr[3] = (mahr >> 0) & 0xFF; + addr[4] = (malr >> 8) & 0xFF; + addr[5] = (malr >> 0) & 0xFF; + eth_hw_addr_set(ndev, addr); } } diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c index f28c0c36b606..ba4062881eed 100644 --- a/drivers/net/ethernet/rocker/rocker_main.c +++ b/drivers/net/ethernet/rocker/rocker_main.c @@ -2545,11 +2545,13 @@ static void rocker_port_dev_addr_init(struct rocker_port *rocker_port) { const struct rocker *rocker = rocker_port->rocker; const struct pci_dev *pdev = rocker->pdev; + u8 addr[ETH_ALEN]; int err; - err = rocker_cmd_get_port_settings_macaddr(rocker_port, - rocker_port->dev->dev_addr); - if (err) { + err = rocker_cmd_get_port_settings_macaddr(rocker_port, addr); + if (!err) { + eth_hw_addr_set(rocker_port->dev, addr); + } else { dev_warn(&pdev->dev, "failed to get mac address, using random\n"); eth_hw_addr_random(rocker_port->dev); } diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_common.h b/drivers/net/ethernet/samsung/sxgbe/sxgbe_common.h index 049dc6cf4611..0f45107db8dd 100644 --- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_common.h +++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_common.h @@ -329,7 +329,7 @@ struct sxgbe_core_ops { /* Set power management mode (e.g. magic frame) */ void (*pmt)(void __iomem *ioaddr, unsigned long mode); /* Set/Get Unicast MAC addresses */ - void (*set_umac_addr)(void __iomem *ioaddr, unsigned char *addr, + void (*set_umac_addr)(void __iomem *ioaddr, const unsigned char *addr, unsigned int reg_n); void (*get_umac_addr)(void __iomem *ioaddr, unsigned char *addr, unsigned int reg_n); diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_core.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_core.c index e96e2bd295ef..7d9f257de92a 100644 --- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_core.c +++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_core.c @@ -85,7 +85,8 @@ static void sxgbe_core_pmt(void __iomem *ioaddr, unsigned long mode) } /* Set/Get Unicast MAC addresses */ -static void sxgbe_core_set_umac_addr(void __iomem *ioaddr, unsigned char *addr, +static void sxgbe_core_set_umac_addr(void __iomem *ioaddr, + const unsigned char *addr, unsigned int reg_n) { u32 high_word, low_word; diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c index 6781aa636d58..32161a56726c 100644 --- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c +++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c @@ -931,10 +931,13 @@ static int sxgbe_get_hw_features(struct sxgbe_priv_data * const priv) static void sxgbe_check_ether_addr(struct sxgbe_priv_data *priv) { if (!is_valid_ether_addr(priv->dev->dev_addr)) { + u8 addr[ETH_ALEN]; + priv->hw->mac->get_umac_addr((void __iomem *) - priv->ioaddr, - priv->dev->dev_addr, 0); - if (!is_valid_ether_addr(priv->dev->dev_addr)) + priv->ioaddr, addr, 0); + if (is_valid_ether_addr(addr)) + eth_hw_addr_set(priv->dev, addr); + else eth_hw_addr_random(priv->dev); } dev_info(priv->device, "device MAC address %pM\n", diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c index e7e2223aebbf..cf366ed2557c 100644 --- a/drivers/net/ethernet/sfc/ef10.c +++ b/drivers/net/ethernet/sfc/ef10.c @@ -1038,7 +1038,7 @@ int efx_ef10_vadaptor_free(struct efx_nic *efx, unsigned int port_id) } int efx_ef10_vport_add_mac(struct efx_nic *efx, - unsigned int port_id, u8 *mac) + unsigned int port_id, const u8 *mac) { MCDI_DECLARE_BUF(inbuf, MC_CMD_VPORT_ADD_MAC_ADDRESS_IN_LEN); @@ -1050,7 +1050,7 @@ int efx_ef10_vport_add_mac(struct efx_nic *efx, } int efx_ef10_vport_del_mac(struct efx_nic *efx, - unsigned int port_id, u8 *mac) + unsigned int port_id, const u8 *mac) { MCDI_DECLARE_BUF(inbuf, MC_CMD_VPORT_DEL_MAC_ADDRESS_IN_LEN); diff --git a/drivers/net/ethernet/sfc/ef10_sriov.c b/drivers/net/ethernet/sfc/ef10_sriov.c index 06d23c708a5f..7f5aa4a8c451 100644 --- a/drivers/net/ethernet/sfc/ef10_sriov.c +++ b/drivers/net/ethernet/sfc/ef10_sriov.c @@ -480,7 +480,7 @@ static int efx_ef10_vport_del_vf_mac(struct efx_nic *efx, unsigned int port_id, return rc; } -int efx_ef10_sriov_set_vf_mac(struct efx_nic *efx, int vf_i, u8 *mac) +int efx_ef10_sriov_set_vf_mac(struct efx_nic *efx, int vf_i, const u8 *mac) { struct efx_ef10_nic_data *nic_data = efx->nic_data; struct ef10_vf *vf; diff --git a/drivers/net/ethernet/sfc/ef10_sriov.h b/drivers/net/ethernet/sfc/ef10_sriov.h index cfe556d17313..3c703ca878b0 100644 --- a/drivers/net/ethernet/sfc/ef10_sriov.h +++ b/drivers/net/ethernet/sfc/ef10_sriov.h @@ -39,7 +39,7 @@ static inline void efx_ef10_sriov_reset(struct efx_nic *efx) {} void efx_ef10_sriov_fini(struct efx_nic *efx); static inline void efx_ef10_sriov_flr(struct efx_nic *efx, unsigned vf_i) {} -int efx_ef10_sriov_set_vf_mac(struct efx_nic *efx, int vf, u8 *mac); +int efx_ef10_sriov_set_vf_mac(struct efx_nic *efx, int vf, const u8 *mac); int efx_ef10_sriov_set_vf_vlan(struct efx_nic *efx, int vf_i, u16 vlan, u8 qos); @@ -60,9 +60,9 @@ int efx_ef10_vswitching_restore_vf(struct efx_nic *efx); void efx_ef10_vswitching_remove_pf(struct efx_nic *efx); void efx_ef10_vswitching_remove_vf(struct efx_nic *efx); int efx_ef10_vport_add_mac(struct efx_nic *efx, - unsigned int port_id, u8 *mac); + unsigned int port_id, const u8 *mac); int efx_ef10_vport_del_mac(struct efx_nic *efx, - unsigned int port_id, u8 *mac); + unsigned int port_id, const u8 *mac); int efx_ef10_vadaptor_alloc(struct efx_nic *efx, unsigned int port_id); int efx_ef10_vadaptor_query(struct efx_nic *efx, unsigned int port_id, u32 *port_flags, u32 *vadaptor_flags, diff --git a/drivers/net/ethernet/sfc/ethtool_common.c b/drivers/net/ethernet/sfc/ethtool_common.c index bf1443539a1a..bd552c7dffcb 100644 --- a/drivers/net/ethernet/sfc/ethtool_common.c +++ b/drivers/net/ethernet/sfc/ethtool_common.c @@ -563,20 +563,14 @@ int efx_ethtool_get_link_ksettings(struct net_device *net_dev, { struct efx_nic *efx = netdev_priv(net_dev); struct efx_link_state *link_state = &efx->link_state; - u32 supported; mutex_lock(&efx->mac_lock); efx_mcdi_phy_get_link_ksettings(efx, cmd); mutex_unlock(&efx->mac_lock); /* Both MACs support pause frames (bidirectional and respond-only) */ - ethtool_convert_link_mode_to_legacy_u32(&supported, - cmd->link_modes.supported); - - supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause; - - ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported, - supported); + ethtool_link_ksettings_add_link_mode(cmd, supported, Pause); + ethtool_link_ksettings_add_link_mode(cmd, supported, Asym_Pause); if (LOOPBACK_INTERNAL(efx)) { cmd->base.speed = link_state->speed; diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h index f6981810039d..cc15ee8812d9 100644 --- a/drivers/net/ethernet/sfc/net_driver.h +++ b/drivers/net/ethernet/sfc/net_driver.h @@ -1440,7 +1440,7 @@ struct efx_nic_type { bool (*sriov_wanted)(struct efx_nic *efx); void (*sriov_reset)(struct efx_nic *efx); void (*sriov_flr)(struct efx_nic *efx, unsigned vf_i); - int (*sriov_set_vf_mac)(struct efx_nic *efx, int vf_i, u8 *mac); + int (*sriov_set_vf_mac)(struct efx_nic *efx, int vf_i, const u8 *mac); int (*sriov_set_vf_vlan)(struct efx_nic *efx, int vf_i, u16 vlan, u8 qos); int (*sriov_set_vf_spoofchk)(struct efx_nic *efx, int vf_i, diff --git a/drivers/net/ethernet/sfc/siena_sriov.c b/drivers/net/ethernet/sfc/siena_sriov.c index 441e7f3e5375..f12851a527d9 100644 --- a/drivers/net/ethernet/sfc/siena_sriov.c +++ b/drivers/net/ethernet/sfc/siena_sriov.c @@ -1591,7 +1591,7 @@ void efx_fini_sriov(void) destroy_workqueue(vfdi_workqueue); } -int efx_siena_sriov_set_vf_mac(struct efx_nic *efx, int vf_i, u8 *mac) +int efx_siena_sriov_set_vf_mac(struct efx_nic *efx, int vf_i, const u8 *mac) { struct siena_nic_data *nic_data = efx->nic_data; struct siena_vf *vf; diff --git a/drivers/net/ethernet/sfc/siena_sriov.h b/drivers/net/ethernet/sfc/siena_sriov.h index e441c89c25ce..e548c4daf189 100644 --- a/drivers/net/ethernet/sfc/siena_sriov.h +++ b/drivers/net/ethernet/sfc/siena_sriov.h @@ -46,7 +46,7 @@ bool efx_siena_sriov_wanted(struct efx_nic *efx); void efx_siena_sriov_reset(struct efx_nic *efx); void efx_siena_sriov_flr(struct efx_nic *efx, unsigned flr); -int efx_siena_sriov_set_vf_mac(struct efx_nic *efx, int vf, u8 *mac); +int efx_siena_sriov_set_vf_mac(struct efx_nic *efx, int vf, const u8 *mac); int efx_siena_sriov_set_vf_vlan(struct efx_nic *efx, int vf, u16 vlan, u8 qos); int efx_siena_sriov_set_vf_spoofchk(struct efx_nic *efx, int vf, diff --git a/drivers/net/ethernet/silan/sc92031.c b/drivers/net/ethernet/silan/sc92031.c index 1fd08a04bd4e..ff4197f5e46d 100644 --- a/drivers/net/ethernet/silan/sc92031.c +++ b/drivers/net/ethernet/silan/sc92031.c @@ -1400,6 +1400,7 @@ static int sc92031_probe(struct pci_dev *pdev, const struct pci_device_id *id) void __iomem* port_base; struct net_device *dev; struct sc92031_priv *priv; + u8 addr[ETH_ALEN]; u32 mac0, mac1; err = pci_enable_device(pdev); @@ -1458,12 +1459,13 @@ static int sc92031_probe(struct pci_dev *pdev, const struct pci_device_id *id) mac0 = ioread32(port_base + MAC0); mac1 = ioread32(port_base + MAC0 + 4); - dev->dev_addr[0] = mac0 >> 24; - dev->dev_addr[1] = mac0 >> 16; - dev->dev_addr[2] = mac0 >> 8; - dev->dev_addr[3] = mac0; - dev->dev_addr[4] = mac1 >> 8; - dev->dev_addr[5] = mac1; + addr[0] = mac0 >> 24; + addr[1] = mac0 >> 16; + addr[2] = mac0 >> 8; + addr[3] = mac0; + addr[4] = mac1 >> 8; + addr[5] = mac1; + eth_hw_addr_set(dev, addr); err = register_netdev(dev); if (err < 0) diff --git a/drivers/net/ethernet/sis/sis190.c b/drivers/net/ethernet/sis/sis190.c index be4d772e68cf..216bb2d34d7c 100644 --- a/drivers/net/ethernet/sis/sis190.c +++ b/drivers/net/ethernet/sis/sis190.c @@ -1586,6 +1586,7 @@ static int sis190_get_mac_addr_from_eeprom(struct pci_dev *pdev, { struct sis190_private *tp = netdev_priv(dev); void __iomem *ioaddr = tp->mmio_addr; + __le16 addr[ETH_ALEN / 2]; u16 sig; int i; @@ -1606,8 +1607,9 @@ static int sis190_get_mac_addr_from_eeprom(struct pci_dev *pdev, for (i = 0; i < ETH_ALEN / 2; i++) { u16 w = sis190_read_eeprom(ioaddr, EEPROMMACAddr + i); - ((__le16 *)dev->dev_addr)[i] = cpu_to_le16(w); + addr[i] = cpu_to_le16(w); } + eth_hw_addr_set(dev, (u8 *)addr); sis190_set_rgmii(tp, sis190_read_eeprom(ioaddr, EEPROMInfo)); @@ -1629,6 +1631,7 @@ static int sis190_get_mac_addr_from_apc(struct pci_dev *pdev, static const u16 ids[] = { 0x0965, 0x0966, 0x0968 }; struct sis190_private *tp = netdev_priv(dev); struct pci_dev *isa_bridge; + u8 addr[ETH_ALEN]; u8 reg, tmp8; unsigned int i; @@ -1657,8 +1660,9 @@ static int sis190_get_mac_addr_from_apc(struct pci_dev *pdev, for (i = 0; i < ETH_ALEN; i++) { outb(0x9 + i, 0x78); - dev->dev_addr[i] = inb(0x79); + addr[i] = inb(0x79); } + eth_hw_addr_set(dev, addr); outb(0x12, 0x78); reg = inb(0x79); diff --git a/drivers/net/ethernet/sis/sis900.c b/drivers/net/ethernet/sis/sis900.c index 60a0c0e9ded2..cc2d907c4c4b 100644 --- a/drivers/net/ethernet/sis/sis900.c +++ b/drivers/net/ethernet/sis/sis900.c @@ -258,6 +258,7 @@ static int sis900_get_mac_addr(struct pci_dev *pci_dev, { struct sis900_private *sis_priv = netdev_priv(net_dev); void __iomem *ioaddr = sis_priv->ioaddr; + u16 addr[ETH_ALEN / 2]; u16 signature; int i; @@ -271,7 +272,8 @@ static int sis900_get_mac_addr(struct pci_dev *pci_dev, /* get MAC address from EEPROM */ for (i = 0; i < 3; i++) - ((u16 *)(net_dev->dev_addr))[i] = read_eeprom(ioaddr, i+EEPROMMACAddr); + addr[i] = read_eeprom(ioaddr, i+EEPROMMACAddr); + eth_hw_addr_set(net_dev, (u8 *)addr); return 1; } @@ -290,6 +292,7 @@ static int sis630e_get_mac_addr(struct pci_dev *pci_dev, struct net_device *net_dev) { struct pci_dev *isa_bridge = NULL; + u8 addr[ETH_ALEN]; u8 reg; int i; @@ -306,8 +309,9 @@ static int sis630e_get_mac_addr(struct pci_dev *pci_dev, for (i = 0; i < 6; i++) { outb(0x09 + i, 0x70); - ((u8 *)(net_dev->dev_addr))[i] = inb(0x71); + addr[i] = inb(0x71); } + eth_hw_addr_set(net_dev, addr); pci_write_config_byte(isa_bridge, 0x48, reg & ~0x40); pci_dev_put(isa_bridge); @@ -331,6 +335,7 @@ static int sis635_get_mac_addr(struct pci_dev *pci_dev, { struct sis900_private *sis_priv = netdev_priv(net_dev); void __iomem *ioaddr = sis_priv->ioaddr; + u16 addr[ETH_ALEN / 2]; u32 rfcrSave; u32 i; @@ -345,8 +350,9 @@ static int sis635_get_mac_addr(struct pci_dev *pci_dev, /* load MAC addr to filter data register */ for (i = 0 ; i < 3 ; i++) { sw32(rfcr, (i << RFADDR_shift)); - *( ((u16 *)net_dev->dev_addr) + i) = sr16(rfdr); + addr[i] = sr16(rfdr); } + eth_hw_addr_set(net_dev, (u8 *)addr); /* enable packet filtering */ sw32(rfcr, rfcrSave | RFEN); @@ -375,17 +381,18 @@ static int sis96x_get_mac_addr(struct pci_dev *pci_dev, { struct sis900_private *sis_priv = netdev_priv(net_dev); void __iomem *ioaddr = sis_priv->ioaddr; + u16 addr[ETH_ALEN / 2]; int wait, rc = 0; sw32(mear, EEREQ); for (wait = 0; wait < 2000; wait++) { if (sr32(mear) & EEGNT) { - u16 *mac = (u16 *)net_dev->dev_addr; int i; /* get MAC address from EEPROM */ for (i = 0; i < 3; i++) - mac[i] = read_eeprom(ioaddr, i + EEPROMMACAddr); + addr[i] = read_eeprom(ioaddr, i + EEPROMMACAddr); + eth_hw_addr_set(net_dev, (u8 *)addr); rc = 1; break; @@ -1098,7 +1105,7 @@ sis900_init_rxfilter (struct net_device * net_dev) /* load MAC addr to filter data register */ for (i = 0 ; i < 3 ; i++) { - u32 w = (u32) *((u16 *)(net_dev->dev_addr)+i); + u32 w = (u32) *((const u16 *)(net_dev->dev_addr)+i); sw32(rfcr, i << RFADDR_shift); sw32(rfdr, w); diff --git a/drivers/net/ethernet/smsc/epic100.c b/drivers/net/ethernet/smsc/epic100.c index 44daf79a8f97..a0654e88444c 100644 --- a/drivers/net/ethernet/smsc/epic100.c +++ b/drivers/net/ethernet/smsc/epic100.c @@ -325,6 +325,7 @@ static int epic_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) struct net_device *dev; struct epic_private *ep; int i, ret, option = 0, duplex = 0; + __le16 addr[ETH_ALEN / 2]; void *ring_space; dma_addr_t ring_dma; @@ -416,7 +417,8 @@ static int epic_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) /* Note: the '175 does not have a serial EEPROM. */ for (i = 0; i < 3; i++) - ((__le16 *)dev->dev_addr)[i] = cpu_to_le16(er16(LAN0 + i*4)); + addr[i] = cpu_to_le16(er16(LAN0 + i*4)); + eth_hw_addr_set(dev, (u8 *)addr); if (debug > 2) { dev_dbg(&pdev->dev, "EEPROM contents:\n"); diff --git a/drivers/net/ethernet/smsc/smc911x.c b/drivers/net/ethernet/smsc/smc911x.c index b008b4e8a2a5..89381f796985 100644 --- a/drivers/net/ethernet/smsc/smc911x.c +++ b/drivers/net/ethernet/smsc/smc911x.c @@ -1788,6 +1788,7 @@ static int smc911x_probe(struct net_device *dev) struct dma_slave_config config; dma_cap_mask_t mask; #endif + u8 addr[ETH_ALEN]; DBG(SMC_DEBUG_FUNC, dev, "--> %s\n", __func__); @@ -1892,7 +1893,8 @@ static int smc911x_probe(struct net_device *dev) spin_lock_init(&lp->lock); /* Get the MAC address */ - SMC_GET_MAC_ADDR(lp, dev->dev_addr); + SMC_GET_MAC_ADDR(lp, addr); + eth_hw_addr_set(dev, addr); /* now, reset the chip, and put it into a known state */ smc911x_reset(dev); diff --git a/drivers/net/ethernet/smsc/smc91c92_cs.c b/drivers/net/ethernet/smsc/smc91c92_cs.c index 42fc37c7887a..37c822e27207 100644 --- a/drivers/net/ethernet/smsc/smc91c92_cs.c +++ b/drivers/net/ethernet/smsc/smc91c92_cs.c @@ -347,6 +347,7 @@ static void smc91c92_detach(struct pcmcia_device *link) static int cvt_ascii_address(struct net_device *dev, char *s) { + u8 mac[ETH_ALEN]; int i, j, da, c; if (strlen(s) != 12) @@ -359,8 +360,9 @@ static int cvt_ascii_address(struct net_device *dev, char *s) da += ((c >= '0') && (c <= '9')) ? (c - '0') : ((c & 0x0f) + 9); } - dev->dev_addr[i] = da; + mac[i] = da; } + eth_hw_addr_set(dev, mac); return 0; } @@ -539,6 +541,7 @@ static int mot_setup(struct pcmcia_device *link) struct net_device *dev = link->priv; unsigned int ioaddr = dev->base_addr; int i, wait, loop; + u8 mac[ETH_ALEN]; u_int addr; /* Read Ethernet address from Serial EEPROM */ @@ -559,9 +562,10 @@ static int mot_setup(struct pcmcia_device *link) return -1; addr = inw(ioaddr + GENERAL); - dev->dev_addr[2*i] = addr & 0xff; - dev->dev_addr[2*i+1] = (addr >> 8) & 0xff; + mac[2*i] = addr & 0xff; + mac[2*i+1] = (addr >> 8) & 0xff; } + eth_hw_addr_set(dev, mac); return 0; } @@ -666,14 +670,13 @@ static int pcmcia_osi_mac(struct pcmcia_device *p_dev, void *priv) { struct net_device *dev = priv; - int i; if (tuple->TupleDataLen < 8) return -EINVAL; if (tuple->TupleData[0] != 0x04) return -EINVAL; - for (i = 0; i < 6; i++) - dev->dev_addr[i] = tuple->TupleData[i+2]; + + eth_hw_addr_set(dev, &tuple->TupleData[2]); return 0; }; diff --git a/drivers/net/ethernet/smsc/smc91x.c b/drivers/net/ethernet/smsc/smc91x.c index 813ea941b91a..a31c159e96ea 100644 --- a/drivers/net/ethernet/smsc/smc91x.c +++ b/drivers/net/ethernet/smsc/smc91x.c @@ -1851,6 +1851,7 @@ static int smc_probe(struct net_device *dev, void __iomem *ioaddr, int retval; unsigned int val, revision_register; const char *version_string; + u8 addr[ETH_ALEN]; DBG(2, dev, "%s: %s\n", CARDNAME, __func__); @@ -1922,7 +1923,8 @@ static int smc_probe(struct net_device *dev, void __iomem *ioaddr, /* Get the MAC address */ SMC_SELECT_BANK(lp, 1); - SMC_GET_MAC_ADDR(lp, dev->dev_addr); + SMC_GET_MAC_ADDR(lp, addr); + eth_hw_addr_set(dev, addr); /* now, reset the chip, and put it into a known state */ smc_reset(dev); diff --git a/drivers/net/ethernet/smsc/smsc911x.c b/drivers/net/ethernet/smsc/smsc911x.c index fa387510c189..7a50ba00f8ae 100644 --- a/drivers/net/ethernet/smsc/smsc911x.c +++ b/drivers/net/ethernet/smsc/smsc911x.c @@ -1503,7 +1503,7 @@ static int smsc911x_soft_reset(struct smsc911x_data *pdata) /* Sets the device MAC address to dev_addr, called with mac_lock held */ static void -smsc911x_set_hw_mac_address(struct smsc911x_data *pdata, u8 dev_addr[6]) +smsc911x_set_hw_mac_address(struct smsc911x_data *pdata, const u8 dev_addr[6]) { u32 mac_high16 = (dev_addr[5] << 8) | dev_addr[4]; u32 mac_low32 = (dev_addr[3] << 24) | (dev_addr[2] << 16) | @@ -2162,13 +2162,15 @@ static void smsc911x_read_mac_address(struct net_device *dev) struct smsc911x_data *pdata = netdev_priv(dev); u32 mac_high16 = smsc911x_mac_read(pdata, ADDRH); u32 mac_low32 = smsc911x_mac_read(pdata, ADDRL); + u8 addr[ETH_ALEN]; - dev->dev_addr[0] = (u8)(mac_low32); - dev->dev_addr[1] = (u8)(mac_low32 >> 8); - dev->dev_addr[2] = (u8)(mac_low32 >> 16); - dev->dev_addr[3] = (u8)(mac_low32 >> 24); - dev->dev_addr[4] = (u8)(mac_high16); - dev->dev_addr[5] = (u8)(mac_high16 >> 8); + addr[0] = (u8)(mac_low32); + addr[1] = (u8)(mac_low32 >> 8); + addr[2] = (u8)(mac_low32 >> 16); + addr[3] = (u8)(mac_low32 >> 24); + addr[4] = (u8)(mac_high16); + addr[5] = (u8)(mac_high16 >> 8); + eth_hw_addr_set(dev, addr); } /* Initializing private device structures, only called from probe */ diff --git a/drivers/net/ethernet/smsc/smsc9420.c b/drivers/net/ethernet/smsc/smsc9420.c index 3d1176588f7d..d937af18973e 100644 --- a/drivers/net/ethernet/smsc/smsc9420.c +++ b/drivers/net/ethernet/smsc/smsc9420.c @@ -404,7 +404,7 @@ static const struct ethtool_ops smsc9420_ethtool_ops = { static void smsc9420_set_mac_address(struct net_device *dev) { struct smsc9420_pdata *pd = netdev_priv(dev); - u8 *dev_addr = dev->dev_addr; + const u8 *dev_addr = dev->dev_addr; u32 mac_high16 = (dev_addr[5] << 8) | dev_addr[4]; u32 mac_low32 = (dev_addr[3] << 24) | (dev_addr[2] << 16) | (dev_addr[1] << 8) | dev_addr[0]; @@ -416,6 +416,7 @@ static void smsc9420_set_mac_address(struct net_device *dev) static void smsc9420_check_mac_address(struct net_device *dev) { struct smsc9420_pdata *pd = netdev_priv(dev); + u8 addr[ETH_ALEN]; /* Check if mac address has been specified when bringing interface up */ if (is_valid_ether_addr(dev->dev_addr)) { @@ -427,15 +428,16 @@ static void smsc9420_check_mac_address(struct net_device *dev) * it will already have been set */ u32 mac_high16 = smsc9420_reg_read(pd, ADDRH); u32 mac_low32 = smsc9420_reg_read(pd, ADDRL); - dev->dev_addr[0] = (u8)(mac_low32); - dev->dev_addr[1] = (u8)(mac_low32 >> 8); - dev->dev_addr[2] = (u8)(mac_low32 >> 16); - dev->dev_addr[3] = (u8)(mac_low32 >> 24); - dev->dev_addr[4] = (u8)(mac_high16); - dev->dev_addr[5] = (u8)(mac_high16 >> 8); + addr[0] = (u8)(mac_low32); + addr[1] = (u8)(mac_low32 >> 8); + addr[2] = (u8)(mac_low32 >> 16); + addr[3] = (u8)(mac_low32 >> 24); + addr[4] = (u8)(mac_high16); + addr[5] = (u8)(mac_high16 >> 8); - if (is_valid_ether_addr(dev->dev_addr)) { + if (is_valid_ether_addr(addr)) { /* eeprom values are valid so use them */ + eth_hw_addr_set(dev, addr); netif_dbg(pd, probe, pd->dev, "Mac Address is read from EEPROM\n"); } else { diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c index baa9f5d1c549..de7d8bf2c226 100644 --- a/drivers/net/ethernet/socionext/netsec.c +++ b/drivers/net/ethernet/socionext/netsec.c @@ -2037,13 +2037,15 @@ static int netsec_probe(struct platform_device *pdev) if (ret && priv->eeprom_base) { void __iomem *macp = priv->eeprom_base + NETSEC_EEPROM_MAC_ADDRESS; + u8 addr[ETH_ALEN]; - ndev->dev_addr[0] = readb(macp + 3); - ndev->dev_addr[1] = readb(macp + 2); - ndev->dev_addr[2] = readb(macp + 1); - ndev->dev_addr[3] = readb(macp + 0); - ndev->dev_addr[4] = readb(macp + 7); - ndev->dev_addr[5] = readb(macp + 6); + addr[0] = readb(macp + 3); + addr[1] = readb(macp + 2); + addr[2] = readb(macp + 1); + addr[3] = readb(macp + 0); + addr[4] = readb(macp + 7); + addr[5] = readb(macp + 6); + eth_hw_addr_set(ndev, addr); } if (!is_valid_ether_addr(ndev->dev_addr)) { diff --git a/drivers/net/ethernet/socionext/sni_ave.c b/drivers/net/ethernet/socionext/sni_ave.c index 4b0fe0f58bbf..2c48f8b8ab71 100644 --- a/drivers/net/ethernet/socionext/sni_ave.c +++ b/drivers/net/ethernet/socionext/sni_ave.c @@ -1935,6 +1935,17 @@ static const struct ave_soc_data ave_pxs3_data = { .get_pinmode = ave_pxs3_get_pinmode, }; +static const struct ave_soc_data ave_nx1_data = { + .is_desc_64bit = true, + .clock_names = { + "ether", + }, + .reset_names = { + "ether", + }, + .get_pinmode = ave_pxs3_get_pinmode, +}; + static const struct of_device_id of_ave_match[] = { { .compatible = "socionext,uniphier-pro4-ave4", @@ -1956,6 +1967,10 @@ static const struct of_device_id of_ave_match[] = { .compatible = "socionext,uniphier-pxs3-ave4", .data = &ave_pxs3_data, }, + { + .compatible = "socionext,uniphier-nx1-ave4", + .data = &ave_nx1_data, + }, { /* Sentinel */ } }; MODULE_DEVICE_TABLE(of, of_ave_match); diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index b6d945ea903d..9160f9ed363a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -546,13 +546,13 @@ int dwmac4_setup(struct stmmac_priv *priv); int dwxgmac2_setup(struct stmmac_priv *priv); int dwxlgmac2_setup(struct stmmac_priv *priv); -void stmmac_set_mac_addr(void __iomem *ioaddr, u8 addr[6], +void stmmac_set_mac_addr(void __iomem *ioaddr, const u8 addr[6], unsigned int high, unsigned int low); void stmmac_get_mac_addr(void __iomem *ioaddr, unsigned char *addr, unsigned int high, unsigned int low); void stmmac_set_mac(void __iomem *ioaddr, bool enable); -void stmmac_dwmac4_set_mac_addr(void __iomem *ioaddr, u8 addr[6], +void stmmac_dwmac4_set_mac_addr(void __iomem *ioaddr, const u8 addr[6], unsigned int high, unsigned int low); void stmmac_dwmac4_get_mac_addr(void __iomem *ioaddr, unsigned char *addr, unsigned int high, unsigned int low); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c index 4422baeed3d8..617d0e4c6495 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c @@ -634,7 +634,7 @@ static void sun8i_dwmac_set_mac(void __iomem *ioaddr, bool enable) * If addr is NULL, clear the slot */ static void sun8i_dwmac_set_umac_addr(struct mac_device_info *hw, - unsigned char *addr, + const unsigned char *addr, unsigned int reg_n) { void __iomem *ioaddr = hw->pcsr; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c index fc8759f146c7..76edb9b72675 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c @@ -104,7 +104,7 @@ static void dwmac1000_dump_regs(struct mac_device_info *hw, u32 *reg_space) } static void dwmac1000_set_umac_addr(struct mac_device_info *hw, - unsigned char *addr, + const unsigned char *addr, unsigned int reg_n) { void __iomem *ioaddr = hw->pcsr; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c index ebcad8dd99db..75071a7d551a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c @@ -68,7 +68,7 @@ static int dwmac100_irq_status(struct mac_device_info *hw, } static void dwmac100_set_umac_addr(struct mac_device_info *hw, - unsigned char *addr, + const unsigned char *addr, unsigned int reg_n) { void __iomem *ioaddr = hw->pcsr; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index b21745368983..fd41db65fe1d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -322,7 +322,7 @@ static void dwmac4_pmt(struct mac_device_info *hw, unsigned long mode) } static void dwmac4_set_umac_addr(struct mac_device_info *hw, - unsigned char *addr, unsigned int reg_n) + const unsigned char *addr, unsigned int reg_n) { void __iomem *ioaddr = hw->pcsr; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c index 9292a1fab7d3..d1c605777985 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c @@ -187,7 +187,7 @@ int dwmac4_dma_interrupt(void __iomem *ioaddr, return ret; } -void stmmac_dwmac4_set_mac_addr(void __iomem *ioaddr, u8 addr[6], +void stmmac_dwmac4_set_mac_addr(void __iomem *ioaddr, const u8 addr[6], unsigned int high, unsigned int low) { unsigned long data; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c index d1c31200bb91..caa4bfc4c1d6 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c @@ -239,7 +239,7 @@ void dwmac_dma_flush_tx_fifo(void __iomem *ioaddr) do {} while ((readl(ioaddr + DMA_CONTROL) & DMA_CONTROL_FTF)); } -void stmmac_set_mac_addr(void __iomem *ioaddr, u8 addr[6], +void stmmac_set_mac_addr(void __iomem *ioaddr, const u8 addr[6], unsigned int high, unsigned int low) { unsigned long data; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c index c4d78fa93663..c6c4d7948fe5 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c @@ -335,7 +335,8 @@ static void dwxgmac2_pmt(struct mac_device_info *hw, unsigned long mode) } static void dwxgmac2_set_umac_addr(struct mac_device_info *hw, - unsigned char *addr, unsigned int reg_n) + const unsigned char *addr, + unsigned int reg_n) { void __iomem *ioaddr = hw->pcsr; u32 value; diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h index fe2660d5694d..f7dc447f05a0 100644 --- a/drivers/net/ethernet/stmicro/stmmac/hwif.h +++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h @@ -330,7 +330,8 @@ struct stmmac_ops { /* Set power management mode (e.g. magic frame) */ void (*pmt)(struct mac_device_info *hw, unsigned long mode); /* Set/Get Unicast MAC addresses */ - void (*set_umac_addr)(struct mac_device_info *hw, unsigned char *addr, + void (*set_umac_addr)(struct mac_device_info *hw, + const unsigned char *addr, unsigned int reg_n); void (*get_umac_addr)(struct mac_device_info *hw, unsigned char *addr, unsigned int reg_n); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index f28a6915d327..d3f350c25b9b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -2818,9 +2818,13 @@ static int stmmac_get_hw_features(struct stmmac_priv *priv) */ static void stmmac_check_ether_addr(struct stmmac_priv *priv) { + u8 addr[ETH_ALEN]; + if (!is_valid_ether_addr(priv->dev->dev_addr)) { - stmmac_get_umac_addr(priv, priv->hw, priv->dev->dev_addr, 0); - if (!is_valid_ether_addr(priv->dev->dev_addr)) + stmmac_get_umac_addr(priv, priv->hw, addr, 0); + if (is_valid_ether_addr(addr)) + eth_hw_addr_set(priv->dev, addr); + else eth_hw_addr_random(priv->dev); dev_info(priv->device, "device MAC address %pM\n", priv->dev->dev_addr); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c index e649a3e6a529..be3cb63675a5 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c @@ -36,7 +36,7 @@ struct stmmac_packet_attrs { int vlan_id_in; int vlan_id_out; unsigned char *src; - unsigned char *dst; + const unsigned char *dst; u32 ip_src; u32 ip_dst; int tcp; @@ -249,8 +249,8 @@ static int stmmac_test_loopback_validate(struct sk_buff *skb, struct net_device *orig_ndev) { struct stmmac_test_priv *tpriv = pt->af_packet_priv; + const unsigned char *dst = tpriv->packet->dst; unsigned char *src = tpriv->packet->src; - unsigned char *dst = tpriv->packet->dst; struct stmmachdr *shdr; struct ethhdr *ehdr; struct udphdr *uhdr; diff --git a/drivers/net/ethernet/sun/cassini.c b/drivers/net/ethernet/sun/cassini.c index 287ae4c538aa..d2d4f47c7e28 100644 --- a/drivers/net/ethernet/sun/cassini.c +++ b/drivers/net/ethernet/sun/cassini.c @@ -3027,7 +3027,7 @@ static void cas_mac_reset(struct cas *cp) /* Must be invoked under cp->lock. */ static void cas_init_mac(struct cas *cp) { - unsigned char *e = &cp->dev->dev_addr[0]; + const unsigned char *e = &cp->dev->dev_addr[0]; int i; cas_mac_reset(cp); @@ -3379,6 +3379,7 @@ static void cas_check_pci_invariants(struct cas *cp) static int cas_check_invariants(struct cas *cp) { struct pci_dev *pdev = cp->pdev; + u8 addr[ETH_ALEN]; u32 cfg; int i; @@ -3407,8 +3408,8 @@ static int cas_check_invariants(struct cas *cp) /* finish phy determination. MDIO1 takes precedence over MDIO0 if * they're both connected. */ - cp->phy_type = cas_get_vpd_info(cp, cp->dev->dev_addr, - PCI_SLOT(pdev->devfn)); + cp->phy_type = cas_get_vpd_info(cp, addr, PCI_SLOT(pdev->devfn)); + eth_hw_addr_set(cp->dev, addr); if (cp->phy_type & CAS_PHY_SERDES) { cp->cas_flags |= CAS_FLAG_1000MB_CAP; return 0; /* no more checking needed */ diff --git a/drivers/net/ethernet/sun/ldmvsw.c b/drivers/net/ethernet/sun/ldmvsw.c index 50bd4e3b0af9..6b59b14e74b1 100644 --- a/drivers/net/ethernet/sun/ldmvsw.c +++ b/drivers/net/ethernet/sun/ldmvsw.c @@ -230,7 +230,6 @@ static struct net_device *vsw_alloc_netdev(u8 hwaddr[], { struct net_device *dev; struct vnet_port *port; - int i; dev = alloc_etherdev_mqs(sizeof(*port), VNET_MAX_TXQS, 1); if (!dev) @@ -238,10 +237,8 @@ static struct net_device *vsw_alloc_netdev(u8 hwaddr[], dev->needed_headroom = VNET_PACKET_SKIP + 8; dev->needed_tailroom = 8; - for (i = 0; i < ETH_ALEN; i++) { - dev->dev_addr[i] = hwaddr[i]; - dev->perm_addr[i] = dev->dev_addr[i]; - } + eth_hw_addr_set(dev, hwaddr); + ether_addr_copy(dev->perm_addr, dev->dev_addr); sprintf(dev->name, "vif%d.%d", (int)handle, (int)port_id); diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c index 1a73a9401347..ba8ad76313a9 100644 --- a/drivers/net/ethernet/sun/niu.c +++ b/drivers/net/ethernet/sun/niu.c @@ -2603,7 +2603,7 @@ static int niu_init_link(struct niu *np) return 0; } -static void niu_set_primary_mac(struct niu *np, unsigned char *addr) +static void niu_set_primary_mac(struct niu *np, const unsigned char *addr) { u16 reg0 = addr[4] << 8 | addr[5]; u16 reg1 = addr[2] << 8 | addr[3]; @@ -8312,6 +8312,7 @@ static void niu_pci_vpd_validate(struct niu *np) { struct net_device *dev = np->dev; struct niu_vpd *vpd = &np->vpd; + u8 addr[ETH_ALEN]; u8 val8; if (!is_valid_ether_addr(&vpd->local_mac[0])) { @@ -8344,17 +8345,20 @@ static void niu_pci_vpd_validate(struct niu *np) return; } - eth_hw_addr_set(dev, vpd->local_mac); + ether_addr_copy(addr, vpd->local_mac); - val8 = dev->dev_addr[5]; - dev->dev_addr[5] += np->port; - if (dev->dev_addr[5] < val8) - dev->dev_addr[4]++; + val8 = addr[5]; + addr[5] += np->port; + if (addr[5] < val8) + addr[4]++; + + eth_hw_addr_set(dev, addr); } static int niu_pci_probe_sprom(struct niu *np) { struct net_device *dev = np->dev; + u8 addr[ETH_ALEN]; int len, i; u64 val, sum; u8 val8; @@ -8446,27 +8450,29 @@ static int niu_pci_probe_sprom(struct niu *np) val = nr64(ESPC_MAC_ADDR0); netif_printk(np, probe, KERN_DEBUG, np->dev, "SPROM: MAC_ADDR0[%08llx]\n", (unsigned long long)val); - dev->dev_addr[0] = (val >> 0) & 0xff; - dev->dev_addr[1] = (val >> 8) & 0xff; - dev->dev_addr[2] = (val >> 16) & 0xff; - dev->dev_addr[3] = (val >> 24) & 0xff; + addr[0] = (val >> 0) & 0xff; + addr[1] = (val >> 8) & 0xff; + addr[2] = (val >> 16) & 0xff; + addr[3] = (val >> 24) & 0xff; val = nr64(ESPC_MAC_ADDR1); netif_printk(np, probe, KERN_DEBUG, np->dev, "SPROM: MAC_ADDR1[%08llx]\n", (unsigned long long)val); - dev->dev_addr[4] = (val >> 0) & 0xff; - dev->dev_addr[5] = (val >> 8) & 0xff; + addr[4] = (val >> 0) & 0xff; + addr[5] = (val >> 8) & 0xff; - if (!is_valid_ether_addr(&dev->dev_addr[0])) { + if (!is_valid_ether_addr(addr)) { dev_err(np->device, "SPROM MAC address invalid [ %pM ]\n", - dev->dev_addr); + addr); return -EINVAL; } - val8 = dev->dev_addr[5]; - dev->dev_addr[5] += np->port; - if (dev->dev_addr[5] < val8) - dev->dev_addr[4]++; + val8 = addr[5]; + addr[5] += np->port; + if (addr[5] < val8) + addr[4]++; + + eth_hw_addr_set(dev, addr); val = nr64(ESPC_MOD_STR_LEN); netif_printk(np, probe, KERN_DEBUG, np->dev, diff --git a/drivers/net/ethernet/sun/sunbmac.c b/drivers/net/ethernet/sun/sunbmac.c index c646575e79d5..531a6f449afa 100644 --- a/drivers/net/ethernet/sun/sunbmac.c +++ b/drivers/net/ethernet/sun/sunbmac.c @@ -623,7 +623,7 @@ static int bigmac_init_hw(struct bigmac *bp, bool non_blocking) void __iomem *cregs = bp->creg; void __iomem *bregs = bp->bregs; __u32 bblk_dvma = (__u32)bp->bblock_dvma; - unsigned char *e = &bp->dev->dev_addr[0]; + const unsigned char *e = &bp->dev->dev_addr[0]; /* Latch current counters into statistics. */ bigmac_get_counters(bp, bregs); @@ -1076,7 +1076,6 @@ static int bigmac_ether_init(struct platform_device *op, struct net_device *dev; u8 bsizes, bsizes_more; struct bigmac *bp; - int i; /* Get a new device struct for this interface. */ dev = alloc_etherdev(sizeof(struct bigmac)); @@ -1086,8 +1085,7 @@ static int bigmac_ether_init(struct platform_device *op, if (version_printed++ == 0) printk(KERN_INFO "%s", version); - for (i = 0; i < 6; i++) - dev->dev_addr[i] = idprom->id_ethaddr[i]; + eth_hw_addr_set(dev, idprom->id_ethaddr); /* Setup softc, with backpointers to QEC and BigMAC SBUS device structs. */ bp = netdev_priv(dev); diff --git a/drivers/net/ethernet/sun/sungem.c b/drivers/net/ethernet/sun/sungem.c index 5f786d6fa150..036856102c50 100644 --- a/drivers/net/ethernet/sun/sungem.c +++ b/drivers/net/ethernet/sun/sungem.c @@ -1810,7 +1810,7 @@ static u32 gem_setup_multicast(struct gem *gp) static void gem_init_mac(struct gem *gp) { - unsigned char *e = &gp->dev->dev_addr[0]; + const unsigned char *e = &gp->dev->dev_addr[0]; writel(0x1bf0, gp->regs + MAC_SNDPAUSE); @@ -2087,7 +2087,7 @@ static void gem_stop_phy(struct gem *gp, int wol) writel(mifcfg, gp->regs + MIF_CFG); if (wol && gp->has_wol) { - unsigned char *e = &gp->dev->dev_addr[0]; + const unsigned char *e = &gp->dev->dev_addr[0]; u32 csr; /* Setup wake-on-lan for MAGIC packet */ @@ -2431,8 +2431,8 @@ static struct net_device_stats *gem_get_stats(struct net_device *dev) static int gem_set_mac_address(struct net_device *dev, void *addr) { struct sockaddr *macaddr = (struct sockaddr *) addr; + const unsigned char *e = &dev->dev_addr[0]; struct gem *gp = netdev_priv(dev); - unsigned char *e = &dev->dev_addr[0]; if (!is_valid_ether_addr(macaddr->sa_data)) return -EADDRNOTAVAIL; @@ -2799,7 +2799,10 @@ static int gem_get_device_address(struct gem *gp) } eth_hw_addr_set(dev, addr); #else - get_gem_mac_nonobp(gp->pdev, gp->dev->dev_addr); + u8 addr[ETH_ALEN]; + + get_gem_mac_nonobp(gp->pdev, addr); + eth_hw_addr_set(gp->dev, addr); #endif return 0; } diff --git a/drivers/net/ethernet/sun/sunhme.c b/drivers/net/ethernet/sun/sunhme.c index fe5482b1872f..ad9029ae6848 100644 --- a/drivers/net/ethernet/sun/sunhme.c +++ b/drivers/net/ethernet/sun/sunhme.c @@ -1395,13 +1395,13 @@ force_link: /* hp->happy_lock must be held */ static int happy_meal_init(struct happy_meal *hp) { + const unsigned char *e = &hp->dev->dev_addr[0]; void __iomem *gregs = hp->gregs; void __iomem *etxregs = hp->etxregs; void __iomem *erxregs = hp->erxregs; void __iomem *bregs = hp->bigmacregs; void __iomem *tregs = hp->tcvregs; u32 regtmp, rxcfg; - unsigned char *e = &hp->dev->dev_addr[0]; /* If auto-negotiation timer is running, kill it. */ del_timer(&hp->happy_timer); @@ -2661,6 +2661,7 @@ static int happy_meal_sbus_probe_one(struct platform_device *op, int is_qfe) struct happy_meal *hp; struct net_device *dev; int i, qfe_slot = -1; + u8 addr[ETH_ALEN]; int err = -ENODEV; sbus_dp = op->dev.parent->of_node; @@ -2698,7 +2699,8 @@ static int happy_meal_sbus_probe_one(struct platform_device *op, int is_qfe) } if (i < 6) { /* a mac address was given */ for (i = 0; i < 6; i++) - dev->dev_addr[i] = macaddr[i]; + addr[i] = macaddr[i]; + eth_hw_addr_set(dev, addr); macaddr[5]++; } else { const unsigned char *addr; @@ -2969,6 +2971,7 @@ static int happy_meal_pci_probe(struct pci_dev *pdev, unsigned long hpreg_res; int i, qfe_slot = -1; char prom_name[64]; + u8 addr[ETH_ALEN]; int err; /* Now make sure pci_dev cookie is there. */ @@ -3044,7 +3047,8 @@ static int happy_meal_pci_probe(struct pci_dev *pdev, } if (i < 6) { /* a mac address was given */ for (i = 0; i < 6; i++) - dev->dev_addr[i] = macaddr[i]; + addr[i] = macaddr[i]; + eth_hw_addr_set(dev, addr); macaddr[5]++; } else { #ifdef CONFIG_SPARC @@ -3060,7 +3064,10 @@ static int happy_meal_pci_probe(struct pci_dev *pdev, eth_hw_addr_set(dev, idprom->id_ethaddr); } #else - get_hme_mac_nonsparc(pdev, &dev->dev_addr[0]); + u8 addr[ETH_ALEN]; + + get_hme_mac_nonsparc(pdev, addr); + eth_hw_addr_set(dev, addr); #endif } diff --git a/drivers/net/ethernet/sun/sunqe.c b/drivers/net/ethernet/sun/sunqe.c index 52b1053a0a77..efe0d33f6024 100644 --- a/drivers/net/ethernet/sun/sunqe.c +++ b/drivers/net/ethernet/sun/sunqe.c @@ -144,7 +144,7 @@ static int qe_init(struct sunqe *qep, int from_irq) void __iomem *cregs = qep->qcregs; void __iomem *mregs = qep->mregs; void __iomem *gregs = qecp->gregs; - unsigned char *e = &qep->dev->dev_addr[0]; + const unsigned char *e = &qep->dev->dev_addr[0]; __u32 qblk_dvma = (__u32)qep->qblock_dvma; u32 tmp; int i; diff --git a/drivers/net/ethernet/sun/sunvnet.c b/drivers/net/ethernet/sun/sunvnet.c index 58ee89223951..da8119625cf3 100644 --- a/drivers/net/ethernet/sun/sunvnet.c +++ b/drivers/net/ethernet/sun/sunvnet.c @@ -285,6 +285,7 @@ static struct vnet *vnet_new(const u64 *local_mac, struct vio_dev *vdev) { struct net_device *dev; + u8 addr[ETH_ALEN]; struct vnet *vp; int err, i; @@ -295,7 +296,8 @@ static struct vnet *vnet_new(const u64 *local_mac, dev->needed_tailroom = 8; for (i = 0; i < ETH_ALEN; i++) - dev->dev_addr[i] = (*local_mac >> (5 - i) * 8) & 0xff; + addr[i] = (*local_mac >> (5 - i) * 8) & 0xff; + eth_hw_addr_set(dev, addr); vp = netdev_priv(dev); diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac-hw.c b/drivers/net/ethernet/synopsys/dwc-xlgmac-hw.c index bf6c1c6779ff..76eb7db80f13 100644 --- a/drivers/net/ethernet/synopsys/dwc-xlgmac-hw.c +++ b/drivers/net/ethernet/synopsys/dwc-xlgmac-hw.c @@ -57,7 +57,7 @@ static int xlgmac_enable_rx_csum(struct xlgmac_pdata *pdata) return 0; } -static int xlgmac_set_mac_address(struct xlgmac_pdata *pdata, u8 *addr) +static int xlgmac_set_mac_address(struct xlgmac_pdata *pdata, const u8 *addr) { unsigned int mac_addr_hi, mac_addr_lo; diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac.h b/drivers/net/ethernet/synopsys/dwc-xlgmac.h index 8598aaf3ec99..98e3a271e017 100644 --- a/drivers/net/ethernet/synopsys/dwc-xlgmac.h +++ b/drivers/net/ethernet/synopsys/dwc-xlgmac.h @@ -410,7 +410,7 @@ struct xlgmac_hw_ops { void (*dev_xmit)(struct xlgmac_channel *channel); int (*dev_read)(struct xlgmac_channel *channel); - int (*set_mac_address)(struct xlgmac_pdata *pdata, u8 *addr); + int (*set_mac_address)(struct xlgmac_pdata *pdata, const u8 *addr); int (*config_rx_mode)(struct xlgmac_pdata *pdata); int (*enable_rx_csum)(struct xlgmac_pdata *pdata); int (*disable_rx_csum)(struct xlgmac_pdata *pdata); diff --git a/drivers/net/ethernet/tehuti/tehuti.c b/drivers/net/ethernet/tehuti/tehuti.c index 3e8a3fde8302..0775a5542f2f 100644 --- a/drivers/net/ethernet/tehuti/tehuti.c +++ b/drivers/net/ethernet/tehuti/tehuti.c @@ -840,6 +840,7 @@ static int bdx_set_mac(struct net_device *ndev, void *p) static int bdx_read_mac(struct bdx_priv *priv) { u16 macAddress[3], i; + u8 addr[ETH_ALEN]; ENTER; macAddress[2] = READ_REG(priv, regUNC_MAC0_A); @@ -849,9 +850,10 @@ static int bdx_read_mac(struct bdx_priv *priv) macAddress[0] = READ_REG(priv, regUNC_MAC2_A); macAddress[0] = READ_REG(priv, regUNC_MAC2_A); for (i = 0; i < 3; i++) { - priv->ndev->dev_addr[i * 2 + 1] = macAddress[i]; - priv->ndev->dev_addr[i * 2] = macAddress[i] >> 8; + addr[i * 2 + 1] = macAddress[i]; + addr[i * 2] = macAddress[i] >> 8; } + eth_hw_addr_set(priv->ndev, addr); RET(0); } diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index 6904bfaa5777..c092cb61416a 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -1918,7 +1918,7 @@ static int am65_cpsw_nuss_init_slave_ports(struct am65_cpsw_common *common) port->port_id, port->slave.mac_addr); if (!is_valid_ether_addr(port->slave.mac_addr)) { - random_ether_addr(port->slave.mac_addr); + eth_random_addr(port->slave.mac_addr); dev_err(dev, "Use random MAC address\n"); } } diff --git a/drivers/net/ethernet/ti/cpmac.c b/drivers/net/ethernet/ti/cpmac.c index 02d4e51f7306..7449436fc87c 100644 --- a/drivers/net/ethernet/ti/cpmac.c +++ b/drivers/net/ethernet/ti/cpmac.c @@ -1112,7 +1112,7 @@ static int cpmac_probe(struct platform_device *pdev) priv->dev = dev; priv->ring_size = 64; priv->msg_enable = netif_msg_init(debug_level, 0xff); - memcpy(dev->dev_addr, pdata->dev_addr, sizeof(pdata->dev_addr)); + eth_hw_addr_set(dev, pdata->dev_addr); snprintf(priv->phy_name, MII_BUS_ID_SIZE, PHY_ID_FMT, mdio_bus_id, phy_id); diff --git a/drivers/net/ethernet/ti/davinci_emac.c b/drivers/net/ethernet/ti/davinci_emac.c index 4538e597eefe..2d2dcf70563f 100644 --- a/drivers/net/ethernet/ti/davinci_emac.c +++ b/drivers/net/ethernet/ti/davinci_emac.c @@ -1402,7 +1402,6 @@ static int match_first_device(struct device *dev, const void *data) static int emac_dev_open(struct net_device *ndev) { struct device *emac_dev = &ndev->dev; - u32 cnt; struct resource *res; int q, m, ret; int res_num = 0, irq_num = 0; @@ -1420,8 +1419,7 @@ static int emac_dev_open(struct net_device *ndev) } netif_carrier_off(ndev); - for (cnt = 0; cnt < ETH_ALEN; cnt++) - ndev->dev_addr[cnt] = priv->mac_addr[cnt]; + eth_hw_addr_set(ndev, priv->mac_addr); /* Configuration items */ priv->rx_buf_size = EMAC_DEF_MAX_FRAME_SIZE + NET_IP_ALIGN; diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c index b666e1b53c5f..b818e4579f6f 100644 --- a/drivers/net/ethernet/ti/netcp_core.c +++ b/drivers/net/ethernet/ti/netcp_core.c @@ -2030,14 +2030,14 @@ static int netcp_create_interface(struct netcp_device *netcp_device, if (is_valid_ether_addr(efuse_mac_addr)) eth_hw_addr_set(ndev, efuse_mac_addr); else - eth_random_addr(ndev->dev_addr); + eth_hw_addr_random(ndev); devm_iounmap(dev, efuse); devm_release_mem_region(dev, res.start, size); } else { ret = of_get_ethdev_address(node_interface, ndev); if (ret) - eth_random_addr(ndev->dev_addr); + eth_hw_addr_random(ndev); } ret = of_property_read_string(node_interface, "rx-channel", diff --git a/drivers/net/ethernet/ti/tlan.c b/drivers/net/ethernet/ti/tlan.c index 77c448ad67ce..741c42c6a417 100644 --- a/drivers/net/ethernet/ti/tlan.c +++ b/drivers/net/ethernet/ti/tlan.c @@ -184,7 +184,7 @@ static void tlan_print_list(struct tlan_list *, char *, int); static void tlan_read_and_clear_stats(struct net_device *, int); static void tlan_reset_adapter(struct net_device *); static void tlan_finish_reset(struct net_device *); -static void tlan_set_mac(struct net_device *, int areg, char *mac); +static void tlan_set_mac(struct net_device *, int areg, const char *mac); static void __tlan_phy_print(struct net_device *); static void tlan_phy_print(struct net_device *); @@ -817,6 +817,7 @@ static int tlan_init(struct net_device *dev) int err; int i; struct tlan_priv *priv; + u8 addr[ETH_ALEN]; priv = netdev_priv(dev); @@ -842,7 +843,7 @@ static int tlan_init(struct net_device *dev) for (i = 0; i < ETH_ALEN; i++) err |= tlan_ee_read_byte(dev, (u8) priv->adapter->addr_ofs + i, - (u8 *) &dev->dev_addr[i]); + addr + i); if (err) { pr_err("%s: Error reading MAC from eeprom: %d\n", dev->name, err); @@ -850,11 +851,12 @@ static int tlan_init(struct net_device *dev) /* Olicom OC-2325/OC-2326 have the address byte-swapped */ if (priv->adapter->addr_ofs == 0xf8) { for (i = 0; i < ETH_ALEN; i += 2) { - char tmp = dev->dev_addr[i]; - dev->dev_addr[i] = dev->dev_addr[i + 1]; - dev->dev_addr[i + 1] = tmp; + char tmp = addr[i]; + addr[i] = addr[i + 1]; + addr[i + 1] = tmp; } } + eth_hw_addr_set(dev, addr); netif_carrier_off(dev); @@ -2346,7 +2348,7 @@ tlan_finish_reset(struct net_device *dev) * **************************************************************/ -static void tlan_set_mac(struct net_device *dev, int areg, char *mac) +static void tlan_set_mac(struct net_device *dev, int areg, const char *mac) { int i; diff --git a/drivers/net/ethernet/toshiba/tc35815.c b/drivers/net/ethernet/toshiba/tc35815.c index 93453e5713b2..ce38f7515225 100644 --- a/drivers/net/ethernet/toshiba/tc35815.c +++ b/drivers/net/ethernet/toshiba/tc35815.c @@ -725,6 +725,7 @@ static int tc35815_init_dev_addr(struct net_device *dev) { struct tc35815_regs __iomem *tr = (struct tc35815_regs __iomem *)dev->base_addr; + u8 addr[ETH_ALEN]; int i; while (tc_readl(&tr->PROM_Ctl) & PROM_Busy) @@ -735,9 +736,10 @@ static int tc35815_init_dev_addr(struct net_device *dev) while (tc_readl(&tr->PROM_Ctl) & PROM_Busy) ; data = tc_readl(&tr->PROM_Data); - dev->dev_addr[i] = data & 0xff; - dev->dev_addr[i+1] = data >> 8; + addr[i] = data & 0xff; + addr[i+1] = data >> 8; } + eth_hw_addr_set(dev, addr); if (!is_valid_ether_addr(dev->dev_addr)) return tc35815_read_plat_dev_addr(dev); return 0; @@ -1859,7 +1861,8 @@ static struct net_device_stats *tc35815_get_stats(struct net_device *dev) return &dev->stats; } -static void tc35815_set_cam_entry(struct net_device *dev, int index, unsigned char *addr) +static void tc35815_set_cam_entry(struct net_device *dev, int index, + const unsigned char *addr) { struct tc35815_local *lp = netdev_priv(dev); struct tc35815_regs __iomem *tr = diff --git a/drivers/net/ethernet/via/via-rhine.c b/drivers/net/ethernet/via/via-rhine.c index 3b73a9c55a5a..509c5e9b29df 100644 --- a/drivers/net/ethernet/via/via-rhine.c +++ b/drivers/net/ethernet/via/via-rhine.c @@ -899,6 +899,7 @@ static int rhine_init_one_common(struct device *hwdev, u32 quirks, struct net_device *dev; struct rhine_private *rp; int i, rc, phy_id; + u8 addr[ETH_ALEN]; const char *name; /* this should always be supported */ @@ -933,7 +934,8 @@ static int rhine_init_one_common(struct device *hwdev, u32 quirks, rhine_hw_init(dev, pioaddr); for (i = 0; i < 6; i++) - dev->dev_addr[i] = ioread8(ioaddr + StationAddr + i); + addr[i] = ioread8(ioaddr + StationAddr + i); + eth_hw_addr_set(dev, addr); if (!is_valid_ether_addr(dev->dev_addr)) { /* Report it and use a random ethernet address instead */ diff --git a/drivers/net/ethernet/via/via-velocity.c b/drivers/net/ethernet/via/via-velocity.c index 4b9c30f735b5..be2b992f24d9 100644 --- a/drivers/net/ethernet/via/via-velocity.c +++ b/drivers/net/ethernet/via/via-velocity.c @@ -2767,6 +2767,7 @@ static int velocity_probe(struct device *dev, int irq, struct velocity_info *vptr; struct mac_regs __iomem *regs; int ret = -ENOMEM; + u8 addr[ETH_ALEN]; /* FIXME: this driver, like almost all other ethernet drivers, * can support more than MAX_UNITS. @@ -2820,7 +2821,8 @@ static int velocity_probe(struct device *dev, int irq, mac_wol_reset(regs); for (i = 0; i < 6; i++) - netdev->dev_addr[i] = readb(®s->PAR[i]); + addr[i] = readb(®s->PAR[i]); + eth_hw_addr_set(netdev, addr); velocity_get_options(&vptr->options, velocity_nics); diff --git a/drivers/net/ethernet/wiznet/w5100-spi.c b/drivers/net/ethernet/wiznet/w5100-spi.c index 2b84848dc26a..7779a36da3c8 100644 --- a/drivers/net/ethernet/wiznet/w5100-spi.c +++ b/drivers/net/ethernet/wiznet/w5100-spi.c @@ -463,7 +463,9 @@ static int w5100_spi_probe(struct spi_device *spi) static int w5100_spi_remove(struct spi_device *spi) { - return w5100_remove(&spi->dev); + w5100_remove(&spi->dev); + + return 0; } static const struct spi_device_id w5100_spi_ids[] = { diff --git a/drivers/net/ethernet/wiznet/w5100.c b/drivers/net/ethernet/wiznet/w5100.c index 88fc65ed0017..ae24d6b86803 100644 --- a/drivers/net/ethernet/wiznet/w5100.c +++ b/drivers/net/ethernet/wiznet/w5100.c @@ -1064,7 +1064,9 @@ static int w5100_mmio_probe(struct platform_device *pdev) static int w5100_mmio_remove(struct platform_device *pdev) { - return w5100_remove(&pdev->dev); + w5100_remove(&pdev->dev); + + return 0; } void *w5100_ops_priv(const struct net_device *ndev) @@ -1210,7 +1212,7 @@ err_register: } EXPORT_SYMBOL_GPL(w5100_probe); -int w5100_remove(struct device *dev) +void w5100_remove(struct device *dev) { struct net_device *ndev = dev_get_drvdata(dev); struct w5100_priv *priv = netdev_priv(ndev); @@ -1226,7 +1228,6 @@ int w5100_remove(struct device *dev) unregister_netdev(ndev); free_netdev(ndev); - return 0; } EXPORT_SYMBOL_GPL(w5100_remove); diff --git a/drivers/net/ethernet/wiznet/w5100.h b/drivers/net/ethernet/wiznet/w5100.h index 5d3d4b541fec..481af3b6d9e8 100644 --- a/drivers/net/ethernet/wiznet/w5100.h +++ b/drivers/net/ethernet/wiznet/w5100.h @@ -31,6 +31,6 @@ void *w5100_ops_priv(const struct net_device *ndev); int w5100_probe(struct device *dev, const struct w5100_ops *ops, int sizeof_ops_priv, const void *mac_addr, int irq, int link_gpio); -int w5100_remove(struct device *dev); +void w5100_remove(struct device *dev); extern const struct dev_pm_ops w5100_pm_ops; diff --git a/drivers/net/ethernet/xilinx/xilinx_emaclite.c b/drivers/net/ethernet/xilinx/xilinx_emaclite.c index b95aee8607a4..0815de581c7f 100644 --- a/drivers/net/ethernet/xilinx/xilinx_emaclite.c +++ b/drivers/net/ethernet/xilinx/xilinx_emaclite.c @@ -206,12 +206,13 @@ static void xemaclite_disable_interrupts(struct net_local *drvdata) * This function writes data from a 16-bit aligned buffer to a 32-bit aligned * address in the EmacLite device. */ -static void xemaclite_aligned_write(void *src_ptr, u32 *dest_ptr, +static void xemaclite_aligned_write(const void *src_ptr, u32 *dest_ptr, unsigned length) { + const u16 *from_u16_ptr; u32 align_buffer; u32 *to_u32_ptr; - u16 *from_u16_ptr, *to_u16_ptr; + u16 *to_u16_ptr; to_u32_ptr = dest_ptr; from_u16_ptr = src_ptr; @@ -470,7 +471,7 @@ static u16 xemaclite_recv_data(struct net_local *drvdata, u8 *data, int maxlen) * buffers (if configured). */ static void xemaclite_update_address(struct net_local *drvdata, - u8 *address_ptr) + const u8 *address_ptr) { void __iomem *addr; u32 reg_data; diff --git a/drivers/net/ethernet/xircom/xirc2ps_cs.c b/drivers/net/ethernet/xircom/xirc2ps_cs.c index ae611e46da6a..f9587e55b842 100644 --- a/drivers/net/ethernet/xircom/xirc2ps_cs.c +++ b/drivers/net/ethernet/xircom/xirc2ps_cs.c @@ -671,7 +671,6 @@ static int pcmcia_get_mac_ce(struct pcmcia_device *p_dev, void *priv) { struct net_device *dev = priv; - int i; if (tuple->TupleDataLen != 13) return -EINVAL; @@ -679,8 +678,7 @@ static int pcmcia_get_mac_ce(struct pcmcia_device *p_dev, (tuple->TupleData[2] != 6)) return -EINVAL; /* another try (James Lehmer's CE2 version 4.1)*/ - for (i = 2; i < 6; i++) - dev->dev_addr[i] = tuple->TupleData[i+2]; + dev_addr_mod(dev, 2, &tuple->TupleData[2], 4); return 0; }; @@ -742,11 +740,9 @@ xirc2ps_config(struct pcmcia_device * link) len = pcmcia_get_tuple(link, 0x89, &buf); /* data layout looks like tuple 0x22 */ if (buf && len == 8) { - if (*buf == CISTPL_FUNCE_LAN_NODE_ID) { - int i; - for (i = 2; i < 6; i++) - dev->dev_addr[i] = buf[i+2]; - } else + if (*buf == CISTPL_FUNCE_LAN_NODE_ID) + dev_addr_mod(dev, 2, &buf[2], 4); + else err = -1; } kfree(buf); @@ -1271,7 +1267,7 @@ struct set_address_info { unsigned int ioaddr; }; -static void set_address(struct set_address_info *sa_info, char *addr) +static void set_address(struct set_address_info *sa_info, const char *addr) { unsigned int ioaddr = sa_info->ioaddr; int i; diff --git a/drivers/net/ethernet/xscale/ixp4xx_eth.c b/drivers/net/ethernet/xscale/ixp4xx_eth.c index 3e5fd952aeaa..65fdad1107fc 100644 --- a/drivers/net/ethernet/xscale/ixp4xx_eth.c +++ b/drivers/net/ethernet/xscale/ixp4xx_eth.c @@ -1103,10 +1103,9 @@ static int init_queues(struct port *port) return -ENOMEM; } - if (!(port->desc_tab = dma_pool_alloc(dma_pool, GFP_KERNEL, - &port->desc_tab_phys))) + port->desc_tab = dma_pool_zalloc(dma_pool, GFP_KERNEL, &port->desc_tab_phys); + if (!port->desc_tab) return -ENOMEM; - memset(port->desc_tab, 0, POOL_ALLOC_SIZE); memset(port->rx_buff_tab, 0, sizeof(port->rx_buff_tab)); /* tables */ memset(port->tx_buff_tab, 0, sizeof(port->tx_buff_tab)); diff --git a/drivers/net/fddi/defxx.c b/drivers/net/fddi/defxx.c index 5810e8473789..b584ffe38ad6 100644 --- a/drivers/net/fddi/defxx.c +++ b/drivers/net/fddi/defxx.c @@ -1117,7 +1117,7 @@ static int dfx_driver_init(struct net_device *dev, const char *print_name, * dfx_ctl_set_mac_address. */ - memcpy(dev->dev_addr, bp->factory_mac_addr, FDDI_K_ALEN); + dev_addr_set(dev, bp->factory_mac_addr); if (dfx_bus_tc) board_name = "DEFTA"; if (dfx_bus_eisa) @@ -1474,7 +1474,7 @@ static int dfx_open(struct net_device *dev) * address. */ - memcpy(dev->dev_addr, bp->factory_mac_addr, FDDI_K_ALEN); + dev_addr_set(dev, bp->factory_mac_addr); /* Clear local unicast/multicast address tables and counts */ @@ -2379,7 +2379,7 @@ static int dfx_ctl_set_mac_address(struct net_device *dev, void *addr) /* Copy unicast address to driver-maintained structs and update count */ - memcpy(dev->dev_addr, p_sockaddr->sa_data, FDDI_K_ALEN); /* update device struct */ + dev_addr_set(dev, p_sockaddr->sa_data); /* update device struct */ memcpy(&bp->uc_table[0], p_sockaddr->sa_data, FDDI_K_ALEN); /* update driver struct */ bp->uc_count = 1; diff --git a/drivers/net/fddi/defza.c b/drivers/net/fddi/defza.c index 0de2c4552f5e..3a6b08eb5e1b 100644 --- a/drivers/net/fddi/defza.c +++ b/drivers/net/fddi/defza.c @@ -1380,7 +1380,7 @@ static int fza_probe(struct device *bdev) goto err_out_irq; fza_reads(&init->hw_addr, &hw_addr, sizeof(hw_addr)); - memcpy(dev->dev_addr, &hw_addr, FDDI_K_ALEN); + dev_addr_set(dev, &hw_addr); fza_reads(&init->rom_rev, &rom_rev, sizeof(rom_rev)); fza_reads(&init->fw_rev, &fw_rev, sizeof(fw_rev)); diff --git a/drivers/net/fddi/skfp/h/smc.h b/drivers/net/fddi/skfp/h/smc.h index 3814a2ff64ae..b0e6ce0d893e 100644 --- a/drivers/net/fddi/skfp/h/smc.h +++ b/drivers/net/fddi/skfp/h/smc.h @@ -470,7 +470,7 @@ void card_stop(struct s_smc *smc); void init_board(struct s_smc *smc, u_char *mac_addr); int init_fplus(struct s_smc *smc); void init_plc(struct s_smc *smc); -int init_smt(struct s_smc *smc, u_char *mac_addr); +int init_smt(struct s_smc *smc, const u_char *mac_addr); void mac1_irq(struct s_smc *smc, u_short stu, u_short stl); void mac2_irq(struct s_smc *smc, u_short code_s2u, u_short code_s2l); void mac3_irq(struct s_smc *smc, u_short code_s3u, u_short code_s3l); diff --git a/drivers/net/fddi/skfp/skfddi.c b/drivers/net/fddi/skfp/skfddi.c index 652cb174302e..2b6a607ac0b7 100644 --- a/drivers/net/fddi/skfp/skfddi.c +++ b/drivers/net/fddi/skfp/skfddi.c @@ -925,7 +925,7 @@ static int skfp_ctl_set_mac_address(struct net_device *dev, void *addr) unsigned long Flags; - memcpy(dev->dev_addr, p_sockaddr->sa_data, FDDI_K_ALEN); + dev_addr_set(dev, p_sockaddr->sa_data); spin_lock_irqsave(&bp->DriverLock, Flags); ResetAdapter(smc); spin_unlock_irqrestore(&bp->DriverLock, Flags); diff --git a/drivers/net/fddi/skfp/smtinit.c b/drivers/net/fddi/skfp/smtinit.c index c9898c83fe30..8b172c195685 100644 --- a/drivers/net/fddi/skfp/smtinit.c +++ b/drivers/net/fddi/skfp/smtinit.c @@ -19,7 +19,7 @@ #include "h/fddi.h" #include "h/smc.h" -void init_fddi_driver(struct s_smc *smc, u_char *mac_addr); +void init_fddi_driver(struct s_smc *smc, const u_char *mac_addr); /* define global debug variable */ #if defined(DEBUG) && !defined(DEBUG_BRD) @@ -57,7 +57,7 @@ static void set_oem_spec_val(struct s_smc *smc) /* * Init SMT */ -int init_smt(struct s_smc *smc, u_char *mac_addr) +int init_smt(struct s_smc *smc, const u_char *mac_addr) /* u_char *mac_addr; canonical address or NULL */ { int p ; diff --git a/drivers/net/fjes/fjes_hw.c b/drivers/net/fjes/fjes_hw.c index 065bb0a40b1d..704e949484d0 100644 --- a/drivers/net/fjes/fjes_hw.c +++ b/drivers/net/fjes/fjes_hw.c @@ -137,7 +137,8 @@ static void fjes_hw_free_epbuf(struct epbuf_handler *epbh) epbh->ring = NULL; } -void fjes_hw_setup_epbuf(struct epbuf_handler *epbh, u8 *mac_addr, u32 mtu) +void fjes_hw_setup_epbuf(struct epbuf_handler *epbh, const u8 *mac_addr, + u32 mtu) { union ep_buffer_info *info = epbh->info; u16 vlan_id[EP_BUFFER_SUPPORT_VLAN_MAX]; diff --git a/drivers/net/fjes/fjes_hw.h b/drivers/net/fjes/fjes_hw.h index b4608ea2a2d5..997c7b37a402 100644 --- a/drivers/net/fjes/fjes_hw.h +++ b/drivers/net/fjes/fjes_hw.h @@ -330,7 +330,7 @@ int fjes_hw_register_buff_addr(struct fjes_hw *, int, int fjes_hw_unregister_buff_addr(struct fjes_hw *, int); void fjes_hw_init_command_registers(struct fjes_hw *, struct fjes_device_command_param *); -void fjes_hw_setup_epbuf(struct epbuf_handler *, u8 *, u32); +void fjes_hw_setup_epbuf(struct epbuf_handler *, const u8 *, u32); int fjes_hw_raise_interrupt(struct fjes_hw *, int, enum REG_ICTL_MASK); void fjes_hw_set_irqmask(struct fjes_hw *, enum REG_ICTL_MASK, bool); u32 fjes_hw_capture_interrupt_status(struct fjes_hw *); diff --git a/drivers/net/fjes/fjes_main.c b/drivers/net/fjes/fjes_main.c index 185c8a398681..b06c17ac8d4e 100644 --- a/drivers/net/fjes/fjes_main.c +++ b/drivers/net/fjes/fjes_main.c @@ -1203,6 +1203,7 @@ static int fjes_probe(struct platform_device *plat_dev) struct net_device *netdev; struct resource *res; struct fjes_hw *hw; + u8 addr[ETH_ALEN]; int err; err = -ENOMEM; @@ -1266,12 +1267,13 @@ static int fjes_probe(struct platform_device *plat_dev) goto err_free_control_wq; /* setup MAC address (02:00:00:00:00:[epid])*/ - netdev->dev_addr[0] = 2; - netdev->dev_addr[1] = 0; - netdev->dev_addr[2] = 0; - netdev->dev_addr[3] = 0; - netdev->dev_addr[4] = 0; - netdev->dev_addr[5] = hw->my_epid; /* EPID */ + addr[0] = 2; + addr[1] = 0; + addr[2] = 0; + addr[3] = 0; + addr[4] = 0; + addr[5] = hw->my_epid; /* EPID */ + eth_hw_addr_set(netdev, addr); err = register_netdev(netdev); if (err) diff --git a/drivers/net/hamradio/6pack.c b/drivers/net/hamradio/6pack.c index 6192244b304a..f4e8793e995d 100644 --- a/drivers/net/hamradio/6pack.c +++ b/drivers/net/hamradio/6pack.c @@ -288,7 +288,7 @@ static int sp_set_mac_address(struct net_device *dev, void *addr) netif_tx_lock_bh(dev); netif_addr_lock(dev); - memcpy(dev->dev_addr, &sa->sax25_call, AX25_ADDR_LEN); + __dev_addr_set(dev, &sa->sax25_call, AX25_ADDR_LEN); netif_addr_unlock(dev); netif_tx_unlock_bh(dev); @@ -317,7 +317,7 @@ static void sp_setup(struct net_device *dev) /* Only activated in AX.25 mode */ memcpy(dev->broadcast, &ax25_bcast, AX25_ADDR_LEN); - memcpy(dev->dev_addr, &ax25_defaddr, AX25_ADDR_LEN); + dev_addr_set(dev, (u8 *)&ax25_defaddr); dev->flags = 0; } @@ -726,7 +726,7 @@ static int sixpack_ioctl(struct tty_struct *tty, struct file *file, } netif_tx_lock_bh(dev); - memcpy(dev->dev_addr, &addr, AX25_ADDR_LEN); + __dev_addr_set(dev, &addr, AX25_ADDR_LEN); netif_tx_unlock_bh(dev); err = 0; break; diff --git a/drivers/net/hamradio/baycom_epp.c b/drivers/net/hamradio/baycom_epp.c index 6b6f28d5b8d5..a03d0b474641 100644 --- a/drivers/net/hamradio/baycom_epp.c +++ b/drivers/net/hamradio/baycom_epp.c @@ -791,7 +791,7 @@ static int baycom_set_mac_address(struct net_device *dev, void *addr) struct sockaddr *sa = (struct sockaddr *)addr; /* addr is an AX.25 shifted ASCII mac address */ - memcpy(dev->dev_addr, sa->sa_data, dev->addr_len); + dev_addr_set(dev, sa->sa_data); return 0; } @@ -1159,7 +1159,7 @@ static void baycom_probe(struct net_device *dev) dev->mtu = AX25_DEF_PACLEN; /* eth_mtu is the default */ dev->addr_len = AX25_ADDR_LEN; /* sizeof an ax.25 address */ memcpy(dev->broadcast, &ax25_bcast, AX25_ADDR_LEN); - memcpy(dev->dev_addr, &null_ax25_address, AX25_ADDR_LEN); + dev_addr_set(dev, (u8 *)&null_ax25_address); dev->tx_queue_len = 16; /* New style flags */ diff --git a/drivers/net/hamradio/bpqether.c b/drivers/net/hamradio/bpqether.c index d967b0748773..30af0081e2be 100644 --- a/drivers/net/hamradio/bpqether.c +++ b/drivers/net/hamradio/bpqether.c @@ -302,7 +302,7 @@ static int bpq_set_mac_address(struct net_device *dev, void *addr) { struct sockaddr *sa = (struct sockaddr *)addr; - memcpy(dev->dev_addr, sa->sa_data, dev->addr_len); + dev_addr_set(dev, sa->sa_data); return 0; } @@ -457,9 +457,6 @@ static void bpq_setup(struct net_device *dev) dev->netdev_ops = &bpq_netdev_ops; dev->needs_free_netdev = true; - memcpy(dev->broadcast, &ax25_bcast, AX25_ADDR_LEN); - memcpy(dev->dev_addr, &ax25_defaddr, AX25_ADDR_LEN); - dev->flags = 0; dev->features = NETIF_F_LLTX; /* Allow recursion */ @@ -472,6 +469,8 @@ static void bpq_setup(struct net_device *dev) dev->mtu = AX25_DEF_PACLEN; dev->addr_len = AX25_ADDR_LEN; + memcpy(dev->broadcast, &ax25_bcast, AX25_ADDR_LEN); + dev_addr_set(dev, (u8 *)&ax25_defaddr); } /* diff --git a/drivers/net/hamradio/dmascc.c b/drivers/net/hamradio/dmascc.c index f4c3efc3e074..7e527499d3ad 100644 --- a/drivers/net/hamradio/dmascc.c +++ b/drivers/net/hamradio/dmascc.c @@ -426,7 +426,7 @@ static void __init dev_setup(struct net_device *dev) dev->addr_len = AX25_ADDR_LEN; dev->tx_queue_len = 64; memcpy(dev->broadcast, &ax25_bcast, AX25_ADDR_LEN); - memcpy(dev->dev_addr, &ax25_defaddr, AX25_ADDR_LEN); + dev_addr_set(dev, (u8 *)&ax25_defaddr); } static const struct net_device_ops scc_netdev_ops = { @@ -956,8 +956,7 @@ static int scc_send_packet(struct sk_buff *skb, struct net_device *dev) static int scc_set_mac_address(struct net_device *dev, void *sa) { - memcpy(dev->dev_addr, ((struct sockaddr *) sa)->sa_data, - dev->addr_len); + dev_addr_set(dev, ((struct sockaddr *)sa)->sa_data); return 0; } diff --git a/drivers/net/hamradio/hdlcdrv.c b/drivers/net/hamradio/hdlcdrv.c index 5805cfc83854..b0edb91bb10a 100644 --- a/drivers/net/hamradio/hdlcdrv.c +++ b/drivers/net/hamradio/hdlcdrv.c @@ -415,7 +415,7 @@ static int hdlcdrv_set_mac_address(struct net_device *dev, void *addr) struct sockaddr *sa = (struct sockaddr *)addr; /* addr is an AX.25 shifted ASCII mac address */ - memcpy(dev->dev_addr, sa->sa_data, dev->addr_len); + dev_addr_set(dev, sa->sa_data); return 0; } @@ -675,7 +675,7 @@ static void hdlcdrv_setup(struct net_device *dev) dev->mtu = AX25_DEF_PACLEN; /* eth_mtu is the default */ dev->addr_len = AX25_ADDR_LEN; /* sizeof an ax.25 address */ memcpy(dev->broadcast, &ax25_bcast, AX25_ADDR_LEN); - memcpy(dev->dev_addr, &ax25_defaddr, AX25_ADDR_LEN); + dev_addr_set(dev, (u8 *)&ax25_defaddr); dev->tx_queue_len = 16; } diff --git a/drivers/net/hamradio/mkiss.c b/drivers/net/hamradio/mkiss.c index 8666110bec55..867252a0247b 100644 --- a/drivers/net/hamradio/mkiss.c +++ b/drivers/net/hamradio/mkiss.c @@ -344,7 +344,7 @@ static int ax_set_mac_address(struct net_device *dev, void *addr) netif_tx_lock_bh(dev); netif_addr_lock(dev); - memcpy(dev->dev_addr, &sa->sax25_call, AX25_ADDR_LEN); + __dev_addr_set(dev, &sa->sax25_call, AX25_ADDR_LEN); netif_addr_unlock(dev); netif_tx_unlock_bh(dev); @@ -647,7 +647,7 @@ static void ax_setup(struct net_device *dev) memcpy(dev->broadcast, &ax25_bcast, AX25_ADDR_LEN); - memcpy(dev->dev_addr, &ax25_defaddr, AX25_ADDR_LEN); + dev_addr_set(dev, (u8 *)&ax25_defaddr); dev->flags = IFF_BROADCAST | IFF_MULTICAST; } @@ -850,7 +850,7 @@ static int mkiss_ioctl(struct tty_struct *tty, struct file *file, } netif_tx_lock_bh(dev); - memcpy(dev->dev_addr, addr, AX25_ADDR_LEN); + __dev_addr_set(dev, addr, AX25_ADDR_LEN); netif_tx_unlock_bh(dev); err = 0; diff --git a/drivers/net/hamradio/scc.c b/drivers/net/hamradio/scc.c index e0bb131a33d7..3d59dac063ac 100644 --- a/drivers/net/hamradio/scc.c +++ b/drivers/net/hamradio/scc.c @@ -1563,9 +1563,6 @@ static void scc_net_setup(struct net_device *dev) dev->netdev_ops = &scc_netdev_ops; dev->header_ops = &ax25_header_ops; - memcpy(dev->broadcast, &ax25_bcast, AX25_ADDR_LEN); - memcpy(dev->dev_addr, &ax25_defaddr, AX25_ADDR_LEN); - dev->flags = 0; dev->type = ARPHRD_AX25; @@ -1573,6 +1570,8 @@ static void scc_net_setup(struct net_device *dev) dev->mtu = AX25_DEF_PACLEN; dev->addr_len = AX25_ADDR_LEN; + memcpy(dev->broadcast, &ax25_bcast, AX25_ADDR_LEN); + dev_addr_set(dev, (u8 *)&ax25_defaddr); } /* ----> open network device <---- */ @@ -1951,7 +1950,7 @@ static int scc_net_siocdevprivate(struct net_device *dev, static int scc_net_set_mac_address(struct net_device *dev, void *addr) { struct sockaddr *sa = (struct sockaddr *) addr; - memcpy(dev->dev_addr, sa->sa_data, dev->addr_len); + dev_addr_set(dev, sa->sa_data); return 0; } diff --git a/drivers/net/hamradio/yam.c b/drivers/net/hamradio/yam.c index 6ddacbdb224b..6376b8485976 100644 --- a/drivers/net/hamradio/yam.c +++ b/drivers/net/hamradio/yam.c @@ -1063,7 +1063,7 @@ static int yam_set_mac_address(struct net_device *dev, void *addr) struct sockaddr *sa = (struct sockaddr *) addr; /* addr is an AX.25 shifted ASCII mac address */ - memcpy(dev->dev_addr, sa->sa_data, dev->addr_len); + dev_addr_set(dev, sa->sa_data); return 0; } @@ -1107,7 +1107,7 @@ static void yam_setup(struct net_device *dev) dev->mtu = AX25_MTU; dev->addr_len = AX25_ADDR_LEN; memcpy(dev->broadcast, &ax25_bcast, AX25_ADDR_LEN); - memcpy(dev->dev_addr, &ax25_defaddr, AX25_ADDR_LEN); + dev_addr_set(dev, (u8 *)&ax25_defaddr); } static int __init yam_init_driver(void) diff --git a/drivers/net/hippi/rrunner.c b/drivers/net/hippi/rrunner.c index 7661dbb31162..16105292b140 100644 --- a/drivers/net/hippi/rrunner.c +++ b/drivers/net/hippi/rrunner.c @@ -502,6 +502,7 @@ static unsigned int write_eeprom(struct rr_private *rrpriv, static int rr_init(struct net_device *dev) { + u8 addr[HIPPI_ALEN] __aligned(4); struct rr_private *rrpriv; struct rr_regs __iomem *regs; u32 sram_size, rev; @@ -537,10 +538,11 @@ static int rr_init(struct net_device *dev) * other method I've seen. -VAL */ - *(__be16 *)(dev->dev_addr) = + *(__be16 *)(addr) = htons(rr_read_eeprom_word(rrpriv, offsetof(struct eeprom, manf.BoardULA))); - *(__be32 *)(dev->dev_addr+2) = + *(__be32 *)(addr+2) = htonl(rr_read_eeprom_word(rrpriv, offsetof(struct eeprom, manf.BoardULA[4]))); + dev_addr_set(dev, addr); printk(" MAC: %pM\n", dev->dev_addr); diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 479d2835a220..7e66ae1d2a59 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -803,6 +803,7 @@ void netvsc_linkstatus_callback(struct net_device *net, schedule_delayed_work(&ndev_ctx->dwork, 0); } +/* This function should only be called after skb_record_rx_queue() */ static void netvsc_xdp_xmit(struct sk_buff *skb, struct net_device *ndev) { int rc; @@ -2742,8 +2743,7 @@ static int netvsc_netdev_event(struct notifier_block *this, return NOTIFY_DONE; /* Avoid Bonding master dev with same MAC registering as VF */ - if ((event_dev->priv_flags & IFF_BONDING) && - (event_dev->flags & IFF_MASTER)) + if (netif_is_bond_master(event_dev)) return NOTIFY_DONE; switch (event) { diff --git a/drivers/net/ieee802154/ca8210.c b/drivers/net/ieee802154/ca8210.c index 3a2824f24caa..ece6ff6049f6 100644 --- a/drivers/net/ieee802154/ca8210.c +++ b/drivers/net/ieee802154/ca8210.c @@ -2938,9 +2938,7 @@ static int ca8210_dev_com_init(struct ca8210_priv *priv) */ static void ca8210_dev_com_clear(struct ca8210_priv *priv) { - flush_workqueue(priv->mlme_workqueue); destroy_workqueue(priv->mlme_workqueue); - flush_workqueue(priv->irq_workqueue); destroy_workqueue(priv->irq_workqueue); } diff --git a/drivers/net/ifb.c b/drivers/net/ifb.c index e9258a9f3702..2c319dd27f29 100644 --- a/drivers/net/ifb.c +++ b/drivers/net/ifb.c @@ -31,6 +31,7 @@ #include #include #include +#include #include #include @@ -75,8 +76,10 @@ static void ifb_ri_tasklet(struct tasklet_struct *t) } while ((skb = __skb_dequeue(&txp->tq)) != NULL) { + /* Skip tc and netfilter to prevent redirection loop. */ skb->redirected = 0; skb->tc_skip_classify = 1; + nf_skip_egress(skb, true); u64_stats_update_begin(&txp->tsync); txp->tx_packets++; diff --git a/drivers/net/ipvlan/ipvtap.c b/drivers/net/ipvlan/ipvtap.c index 1cedb634f4f7..ef02f2cf5ce1 100644 --- a/drivers/net/ipvlan/ipvtap.c +++ b/drivers/net/ipvlan/ipvtap.c @@ -162,7 +162,7 @@ static int ipvtap_device_event(struct notifier_block *unused, devt = MKDEV(MAJOR(ipvtap_major), vlantap->tap.minor); classdev = device_create(&ipvtap_class, &dev->dev, devt, - dev, tap_name); + dev, "%s", tap_name); if (IS_ERR(classdev)) { tap_free_minor(ipvtap_major, &vlantap->tap); return notifier_from_errno(PTR_ERR(classdev)); diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index 694e2f5dbbe5..6b12902a803f 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -169,7 +169,7 @@ static int macvtap_device_event(struct notifier_block *unused, devt = MKDEV(MAJOR(macvtap_major), vlantap->tap.minor); classdev = device_create(&macvtap_class, &dev->dev, devt, - dev, tap_name); + dev, "%s", tap_name); if (IS_ERR(classdev)) { tap_free_minor(macvtap_major, &vlantap->tap); return notifier_from_errno(PTR_ERR(classdev)); diff --git a/drivers/net/net_failover.c b/drivers/net/net_failover.c index 2a4892402ed8..86ec5aae4289 100644 --- a/drivers/net/net_failover.c +++ b/drivers/net/net_failover.c @@ -748,8 +748,7 @@ struct failover *net_failover_create(struct net_device *standby_dev) failover_dev->hw_features |= NETIF_F_GSO_ENCAP_ALL; failover_dev->features |= failover_dev->hw_features; - memcpy(failover_dev->dev_addr, standby_dev->dev_addr, - failover_dev->addr_len); + dev_addr_set(failover_dev, standby_dev->dev_addr); failover_dev->min_mtu = standby_dev->min_mtu; failover_dev->max_mtu = standby_dev->max_mtu; diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c index cb6645012a30..9661aca35703 100644 --- a/drivers/net/netdevsim/dev.c +++ b/drivers/net/netdevsim/dev.c @@ -1511,8 +1511,8 @@ int nsim_dev_probe(struct nsim_bus_dev *nsim_bus_dev) goto err_psample_exit; nsim_dev->esw_mode = DEVLINK_ESWITCH_MODE_LEGACY; + devlink_set_features(devlink, DEVLINK_F_RELOAD); devlink_register(devlink); - devlink_reload_enable(devlink); return 0; err_psample_exit: @@ -1566,9 +1566,7 @@ void nsim_dev_remove(struct nsim_bus_dev *nsim_bus_dev) struct nsim_dev *nsim_dev = dev_get_drvdata(&nsim_bus_dev->dev); struct devlink *devlink = priv_to_devlink(nsim_dev); - devlink_reload_disable(devlink); devlink_unregister(devlink); - nsim_dev_reload_destroy(nsim_dev); nsim_bpf_dev_exit(nsim_dev); diff --git a/drivers/net/ntb_netdev.c b/drivers/net/ntb_netdev.c index a5bab614ff84..98ca6b18415e 100644 --- a/drivers/net/ntb_netdev.c +++ b/drivers/net/ntb_netdev.c @@ -428,7 +428,7 @@ static int ntb_netdev_probe(struct device *client_dev) ndev->watchdog_timeo = msecs_to_jiffies(NTB_TX_TIMEOUT_MS); eth_random_addr(ndev->perm_addr); - memcpy(ndev->dev_addr, ndev->perm_addr, ndev->addr_len); + dev_addr_set(ndev, ndev->perm_addr); ndev->netdev_ops = &ntb_netdev_ops; ndev->ethtool_ops = &ntb_ethtool_ops; diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c index ae7e1f1c59f0..69da011e82c8 100644 --- a/drivers/net/phy/at803x.c +++ b/drivers/net/phy/at803x.c @@ -86,15 +86,22 @@ #define AT803X_PSSR 0x11 /*PHY-Specific Status Register*/ #define AT803X_PSSR_MR_AN_COMPLETE 0x0200 -#define AT803X_DEBUG_REG_0 0x00 +#define AT803X_DEBUG_ANALOG_TEST_CTRL 0x00 +#define QCA8327_DEBUG_MANU_CTRL_EN BIT(2) +#define QCA8337_DEBUG_MANU_CTRL_EN GENMASK(3, 2) #define AT803X_DEBUG_RX_CLK_DLY_EN BIT(15) -#define AT803X_DEBUG_REG_5 0x05 +#define AT803X_DEBUG_SYSTEM_CTRL_MODE 0x05 #define AT803X_DEBUG_TX_CLK_DLY_EN BIT(8) +#define AT803X_DEBUG_REG_HIB_CTRL 0x0b +#define AT803X_DEBUG_HIB_CTRL_SEL_RST_80U BIT(10) +#define AT803X_DEBUG_HIB_CTRL_EN_ANY_CHANGE BIT(13) + #define AT803X_DEBUG_REG_3C 0x3C -#define AT803X_DEBUG_REG_3D 0x3D +#define AT803X_DEBUG_REG_GREEN 0x3D +#define AT803X_DEBUG_GATE_CLK_IN1000 BIT(6) #define AT803X_DEBUG_REG_1F 0x1F #define AT803X_DEBUG_PLL_ON BIT(2) @@ -278,25 +285,25 @@ static int at803x_read_page(struct phy_device *phydev) static int at803x_enable_rx_delay(struct phy_device *phydev) { - return at803x_debug_reg_mask(phydev, AT803X_DEBUG_REG_0, 0, + return at803x_debug_reg_mask(phydev, AT803X_DEBUG_ANALOG_TEST_CTRL, 0, AT803X_DEBUG_RX_CLK_DLY_EN); } static int at803x_enable_tx_delay(struct phy_device *phydev) { - return at803x_debug_reg_mask(phydev, AT803X_DEBUG_REG_5, 0, + return at803x_debug_reg_mask(phydev, AT803X_DEBUG_SYSTEM_CTRL_MODE, 0, AT803X_DEBUG_TX_CLK_DLY_EN); } static int at803x_disable_rx_delay(struct phy_device *phydev) { - return at803x_debug_reg_mask(phydev, AT803X_DEBUG_REG_0, + return at803x_debug_reg_mask(phydev, AT803X_DEBUG_ANALOG_TEST_CTRL, AT803X_DEBUG_RX_CLK_DLY_EN, 0); } static int at803x_disable_tx_delay(struct phy_device *phydev) { - return at803x_debug_reg_mask(phydev, AT803X_DEBUG_REG_5, + return at803x_debug_reg_mask(phydev, AT803X_DEBUG_SYSTEM_CTRL_MODE, AT803X_DEBUG_TX_CLK_DLY_EN, 0); } @@ -1296,9 +1303,9 @@ static int qca83xx_config_init(struct phy_device *phydev) switch (switch_revision) { case 1: /* For 100M waveform */ - at803x_debug_reg_write(phydev, AT803X_DEBUG_REG_0, 0x02ea); + at803x_debug_reg_write(phydev, AT803X_DEBUG_ANALOG_TEST_CTRL, 0x02ea); /* Turn on Gigabit clock */ - at803x_debug_reg_write(phydev, AT803X_DEBUG_REG_3D, 0x68a0); + at803x_debug_reg_write(phydev, AT803X_DEBUG_REG_GREEN, 0x68a0); break; case 2: @@ -1306,12 +1313,95 @@ static int qca83xx_config_init(struct phy_device *phydev) fallthrough; case 4: phy_write_mmd(phydev, MDIO_MMD_PCS, MDIO_AZ_DEBUG, 0x803f); - at803x_debug_reg_write(phydev, AT803X_DEBUG_REG_3D, 0x6860); - at803x_debug_reg_write(phydev, AT803X_DEBUG_REG_5, 0x2c46); + at803x_debug_reg_write(phydev, AT803X_DEBUG_REG_GREEN, 0x6860); + at803x_debug_reg_write(phydev, AT803X_DEBUG_SYSTEM_CTRL_MODE, 0x2c46); at803x_debug_reg_write(phydev, AT803X_DEBUG_REG_3C, 0x6000); break; } + /* QCA8327 require DAC amplitude adjustment for 100m set to +6%. + * Disable on init and enable only with 100m speed following + * qca original source code. + */ + if (phydev->drv->phy_id == QCA8327_A_PHY_ID || + phydev->drv->phy_id == QCA8327_B_PHY_ID) + at803x_debug_reg_mask(phydev, AT803X_DEBUG_ANALOG_TEST_CTRL, + QCA8327_DEBUG_MANU_CTRL_EN, 0); + + /* Following original QCA sourcecode set port to prefer master */ + phy_set_bits(phydev, MII_CTRL1000, CTL1000_PREFER_MASTER); + + return 0; +} + +static void qca83xx_link_change_notify(struct phy_device *phydev) +{ + /* QCA8337 doesn't require DAC Amplitude adjustement */ + if (phydev->drv->phy_id == QCA8337_PHY_ID) + return; + + /* Set DAC Amplitude adjustment to +6% for 100m on link running */ + if (phydev->state == PHY_RUNNING) { + if (phydev->speed == SPEED_100) + at803x_debug_reg_mask(phydev, AT803X_DEBUG_ANALOG_TEST_CTRL, + QCA8327_DEBUG_MANU_CTRL_EN, + QCA8327_DEBUG_MANU_CTRL_EN); + } else { + /* Reset DAC Amplitude adjustment */ + at803x_debug_reg_mask(phydev, AT803X_DEBUG_ANALOG_TEST_CTRL, + QCA8327_DEBUG_MANU_CTRL_EN, 0); + } +} + +static int qca83xx_resume(struct phy_device *phydev) +{ + int ret, val; + + /* Skip reset if not suspended */ + if (!phydev->suspended) + return 0; + + /* Reinit the port, reset values set by suspend */ + qca83xx_config_init(phydev); + + /* Reset the port on port resume */ + phy_set_bits(phydev, MII_BMCR, BMCR_RESET | BMCR_ANENABLE); + + /* On resume from suspend the switch execute a reset and + * restart auto-negotiation. Wait for reset to complete. + */ + ret = phy_read_poll_timeout(phydev, MII_BMCR, val, !(val & BMCR_RESET), + 50000, 600000, true); + if (ret) + return ret; + + msleep(1); + + return 0; +} + +static int qca83xx_suspend(struct phy_device *phydev) +{ + u16 mask = 0; + + /* Only QCA8337 support actual suspend. + * QCA8327 cause port unreliability when phy suspend + * is set. + */ + if (phydev->drv->phy_id == QCA8337_PHY_ID) { + genphy_suspend(phydev); + } else { + mask |= ~(BMCR_SPEED1000 | BMCR_FULLDPLX); + phy_modify(phydev, MII_BMCR, mask, 0); + } + + at803x_debug_reg_mask(phydev, AT803X_DEBUG_REG_GREEN, + AT803X_DEBUG_GATE_CLK_IN1000, 0); + + at803x_debug_reg_mask(phydev, AT803X_DEBUG_REG_HIB_CTRL, + AT803X_DEBUG_HIB_CTRL_EN_ANY_CHANGE | + AT803X_DEBUG_HIB_CTRL_SEL_RST_80U, 0); + return 0; } @@ -1432,6 +1522,7 @@ static struct phy_driver at803x_driver[] = { .phy_id_mask = QCA8K_PHY_ID_MASK, .name = "Qualcomm Atheros 8337 internal PHY", /* PHY_GBIT_FEATURES */ + .link_change_notify = qca83xx_link_change_notify, .probe = at803x_probe, .flags = PHY_IS_INTERNAL, .config_init = qca83xx_config_init, @@ -1439,14 +1530,15 @@ static struct phy_driver at803x_driver[] = { .get_sset_count = at803x_get_sset_count, .get_strings = at803x_get_strings, .get_stats = at803x_get_stats, - .suspend = genphy_suspend, - .resume = genphy_resume, + .suspend = qca83xx_suspend, + .resume = qca83xx_resume, }, { /* QCA8327-A from switch QCA8327-AL1A */ .phy_id = QCA8327_A_PHY_ID, .phy_id_mask = QCA8K_PHY_ID_MASK, .name = "Qualcomm Atheros 8327-A internal PHY", /* PHY_GBIT_FEATURES */ + .link_change_notify = qca83xx_link_change_notify, .probe = at803x_probe, .flags = PHY_IS_INTERNAL, .config_init = qca83xx_config_init, @@ -1454,14 +1546,15 @@ static struct phy_driver at803x_driver[] = { .get_sset_count = at803x_get_sset_count, .get_strings = at803x_get_strings, .get_stats = at803x_get_stats, - .suspend = genphy_suspend, - .resume = genphy_resume, + .suspend = qca83xx_suspend, + .resume = qca83xx_resume, }, { /* QCA8327-B from switch QCA8327-BL1A */ .phy_id = QCA8327_B_PHY_ID, .phy_id_mask = QCA8K_PHY_ID_MASK, .name = "Qualcomm Atheros 8327-B internal PHY", /* PHY_GBIT_FEATURES */ + .link_change_notify = qca83xx_link_change_notify, .probe = at803x_probe, .flags = PHY_IS_INTERNAL, .config_init = qca83xx_config_init, @@ -1469,8 +1562,8 @@ static struct phy_driver at803x_driver[] = { .get_sset_count = at803x_get_sset_count, .get_strings = at803x_get_strings, .get_stats = at803x_get_stats, - .suspend = genphy_suspend, - .resume = genphy_resume, + .suspend = qca83xx_suspend, + .resume = qca83xx_resume, }, }; module_phy_driver(at803x_driver); diff --git a/drivers/net/phy/dp83867.c b/drivers/net/phy/dp83867.c index 6bbc81ad295f..914619f3f0e3 100644 --- a/drivers/net/phy/dp83867.c +++ b/drivers/net/phy/dp83867.c @@ -619,6 +619,25 @@ static int dp83867_of_init(struct phy_device *phydev) #else static int dp83867_of_init(struct phy_device *phydev) { + struct dp83867_private *dp83867 = phydev->priv; + u16 delay; + + /* For non-OF device, the RX and TX ID values are either strapped + * or take from default value. So, we init RX & TX ID values here + * so that the RGMIIDCTL is configured correctly later in + * dp83867_config_init(); + */ + delay = phy_read_mmd(phydev, DP83867_DEVADDR, DP83867_RGMIIDCTL); + dp83867->rx_id_delay = delay & DP83867_RGMII_RX_CLK_DELAY_MAX; + dp83867->tx_id_delay = (delay >> DP83867_RGMII_TX_CLK_DELAY_SHIFT) & + DP83867_RGMII_TX_CLK_DELAY_MAX; + + /* Per datasheet, IO impedance is default to 50-ohm, so we set the + * same here or else the default '0' means highest IO impedance + * which is wrong. + */ + dp83867->io_impedance = DP83867_IO_MUX_CFG_IO_IMPEDANCE_MIN / 2; + return 0; } #endif /* CONFIG_OF_MDIO */ diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c index daf8356b54f3..c204067f1890 100644 --- a/drivers/net/phy/mdio_bus.c +++ b/drivers/net/phy/mdio_bus.c @@ -971,8 +971,14 @@ EXPORT_SYMBOL_GPL(mdiobus_modify_changed); */ static int mdio_bus_match(struct device *dev, struct device_driver *drv) { + struct mdio_driver *mdiodrv = to_mdio_driver(drv); struct mdio_device *mdio = to_mdio_device(dev); + /* Both the driver and device must type-match */ + if (!(mdiodrv->mdiodrv.flags & MDIO_DEVICE_IS_PHY) != + !(mdio->flags & MDIO_DEVICE_FLAG_PHY)) + return 0; + if (of_driver_match_device(dev, drv)) return 1; diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index c330a5a9f665..44a24b99c894 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -863,9 +863,9 @@ static int ksz9031_config_init(struct phy_device *phydev) MII_KSZ9031RN_TX_DATA_PAD_SKEW, 4, tx_data_skews, 4, &update); - if (update && phydev->interface != PHY_INTERFACE_MODE_RGMII) + if (update && !phy_interface_is_rgmii(phydev)) phydev_warn(phydev, - "*-skew-ps values should be used only with phy-mode = \"rgmii\"\n"); + "*-skew-ps values should be used only with RGMII PHY modes\n"); /* Silicon Errata Sheet (DS80000691D or DS80000692D): * When the device links in the 1000BASE-T slave mode only, @@ -1003,6 +1003,26 @@ static int ksz9131_config_rgmii_delay(struct phy_device *phydev) txcdll_val); } +/* Silicon Errata DS80000693B + * + * When LEDs are configured in Individual Mode, LED1 is ON in a no-link + * condition. Workaround is to set register 0x1e, bit 9, this way LED1 behaves + * according to the datasheet (off if there is no link). + */ +static int ksz9131_led_errata(struct phy_device *phydev) +{ + int reg; + + reg = phy_read_mmd(phydev, 2, 0); + if (reg < 0) + return reg; + + if (!(reg & BIT(4))) + return 0; + + return phy_set_bits(phydev, 0x1e, BIT(9)); +} + static int ksz9131_config_init(struct phy_device *phydev) { struct device_node *of_node; @@ -1058,6 +1078,10 @@ static int ksz9131_config_init(struct phy_device *phydev) if (ret < 0) return ret; + ret = ksz9131_led_errata(phydev); + if (ret < 0) + return ret; + return 0; } @@ -1652,8 +1676,9 @@ static struct phy_driver ksphy_driver[] = { .get_sset_count = kszphy_get_sset_count, .get_strings = kszphy_get_strings, .get_stats = kszphy_get_stats, - .suspend = genphy_suspend, - .resume = genphy_resume, + /* No suspend/resume callbacks because of errata DS80000700A, + * receiver error following software power down. + */ }, { .phy_id = PHY_ID_KSZ8041RNLI, .phy_id_mask = MICREL_PHY_ID_MASK, diff --git a/drivers/net/phy/mscc/mscc_main.c b/drivers/net/phy/mscc/mscc_main.c index 6e32da28e138..ebfeeb3c67c1 100644 --- a/drivers/net/phy/mscc/mscc_main.c +++ b/drivers/net/phy/mscc/mscc_main.c @@ -273,12 +273,12 @@ static int vsc85xx_downshift_set(struct phy_device *phydev, u8 count) static int vsc85xx_wol_set(struct phy_device *phydev, struct ethtool_wolinfo *wol) { + const u8 *mac_addr = phydev->attached_dev->dev_addr; int rc; u16 reg_val; u8 i; u16 pwd[3] = {0, 0, 0}; struct ethtool_wolinfo *wol_conf = wol; - u8 *mac_addr = phydev->attached_dev->dev_addr; mutex_lock(&phydev->lock); rc = phy_select_page(phydev, MSCC_PHY_PAGE_EXTENDED_2); diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 4f9990b47a37..74d8e1dc125f 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -3149,6 +3149,16 @@ int phy_driver_register(struct phy_driver *new_driver, struct module *owner) return -EINVAL; } + /* PHYLIB device drivers must not match using a DT compatible table + * as this bypasses our checks that the mdiodev that is being matched + * is backed by a struct phy_device. If such a case happens, we will + * make out-of-bounds accesses and lockup in phydev->lock. + */ + if (WARN(new_driver->mdiodrv.driver.of_match_table, + "%s: driver must not provide a DT match table\n", + new_driver->name)) + return -EINVAL; + new_driver->mdiodrv.flags |= MDIO_DEVICE_IS_PHY; new_driver->mdiodrv.driver.name = new_driver->name; new_driver->mdiodrv.driver.bus = &mdio_bus_type; diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 16240f2dd161..7e93d81fa5ad 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -551,9 +551,15 @@ static void phylink_mac_pcs_get_state(struct phylink *pl, linkmode_zero(state->lp_advertising); state->interface = pl->link_config.interface; state->an_enabled = pl->link_config.an_enabled; - state->speed = SPEED_UNKNOWN; - state->duplex = DUPLEX_UNKNOWN; - state->pause = MLO_PAUSE_NONE; + if (state->an_enabled) { + state->speed = SPEED_UNKNOWN; + state->duplex = DUPLEX_UNKNOWN; + state->pause = MLO_PAUSE_NONE; + } else { + state->speed = pl->link_config.speed; + state->duplex = pl->link_config.duplex; + state->pause = pl->link_config.pause; + } state->an_complete = 0; state->link = 1; @@ -1612,20 +1618,11 @@ int phylink_ethtool_ksettings_set(struct phylink *pl, linkmode_mod_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, config.advertising, config.an_enabled); - /* Validate without changing the current supported mask. */ - linkmode_copy(support, pl->supported); - if (phylink_validate(pl, support, &config)) - return -EINVAL; - - /* If autonegotiation is enabled, we must have an advertisement */ - if (config.an_enabled && phylink_is_empty_linkmode(config.advertising)) - return -EINVAL; - /* If this link is with an SFP, ensure that changes to advertised modes * also cause the associated interface to be selected such that the * link can be configured correctly. */ - if (pl->sfp_port && pl->sfp_bus) { + if (pl->sfp_bus) { config.interface = sfp_select_interface(pl->sfp_bus, config.advertising); if (config.interface == PHY_INTERFACE_MODE_NA) { @@ -1645,8 +1642,17 @@ int phylink_ethtool_ksettings_set(struct phylink *pl, __ETHTOOL_LINK_MODE_MASK_NBITS, support); return -EINVAL; } + } else { + /* Validate without changing the current supported mask. */ + linkmode_copy(support, pl->supported); + if (phylink_validate(pl, support, &config)) + return -EINVAL; } + /* If autonegotiation is enabled, we must have an advertisement */ + if (config.an_enabled && phylink_is_empty_linkmode(config.advertising)) + return -EINVAL; + mutex_lock(&pl->state_mutex); pl->link_config.speed = config.speed; pl->link_config.duplex = config.duplex; @@ -2549,7 +2555,10 @@ void phylink_mii_c22_pcs_get_state(struct mdio_device *pcs, state->link = !!(bmsr & BMSR_LSTATUS); state->an_complete = !!(bmsr & BMSR_ANEGCOMPLETE); - if (!state->link) + /* If there is no link or autonegotiation is disabled, the LP advertisement + * data is not meaningful, so don't go any further. + */ + if (!state->link || !state->an_enabled) return; switch (state->interface) { @@ -2651,7 +2660,12 @@ int phylink_mii_c22_pcs_config(struct mdio_device *pcs, unsigned int mode, changed = ret > 0; /* Ensure ISOLATE bit is disabled */ - bmcr = mode == MLO_AN_INBAND ? BMCR_ANENABLE : 0; + if (mode == MLO_AN_INBAND && + linkmode_test_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, advertising)) + bmcr = BMCR_ANENABLE; + else + bmcr = 0; + ret = mdiobus_modify(pcs->bus, pcs->addr, MII_BMCR, BMCR_ANENABLE | BMCR_ISOLATE, bmcr); if (ret < 0) diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c index 11be60333fa8..a5671ab896b3 100644 --- a/drivers/net/phy/realtek.c +++ b/drivers/net/phy/realtek.c @@ -1023,6 +1023,14 @@ static struct phy_driver realtek_drvs[] = { .resume = genphy_resume, .read_page = rtl821x_read_page, .write_page = rtl821x_write_page, + }, { + PHY_ID_MATCH_EXACT(0x001cc942), + .name = "RTL8365MB-VC Gigabit Ethernet", + /* Interrupt handling analogous to RTL8366RB */ + .config_intr = genphy_no_config_intr, + .handle_interrupt = genphy_handle_interrupt_no_ack, + .suspend = genphy_suspend, + .resume = genphy_resume, }, }; diff --git a/drivers/net/plip/plip.c b/drivers/net/plip/plip.c index 82d609401711..0d491b4d6667 100644 --- a/drivers/net/plip/plip.c +++ b/drivers/net/plip/plip.c @@ -284,12 +284,16 @@ static const struct net_device_ops plip_netdev_ops = { static void plip_init_netdev(struct net_device *dev) { + static const u8 addr_init[ETH_ALEN] = { + 0xfc, 0xfc, 0xfc, + 0xfc, 0xfc, 0xfc, + }; struct net_local *nl = netdev_priv(dev); /* Then, override parts of it */ dev->tx_queue_len = 10; dev->flags = IFF_POINTOPOINT|IFF_NOARP; - memset(dev->dev_addr, 0xfc, ETH_ALEN); + eth_hw_addr_set(dev, addr_init); dev->netdev_ops = &plip_netdev_ops; dev->header_ops = &plip_header_ops; @@ -1109,7 +1113,7 @@ plip_open(struct net_device *dev) plip_init_dev(). */ const struct in_ifaddr *ifa = rcu_dereference(in_dev->ifa_list); if (ifa != NULL) { - memcpy(dev->dev_addr+2, &ifa->ifa_local, 4); + dev_addr_mod(dev, 2, &ifa->ifa_local, 4); } } diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index fb52cd175b45..1180a0e2445f 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -1161,7 +1161,7 @@ static int ppp_unit_register(struct ppp *ppp, int unit, bool ifname_is_set) if (!ifname_is_set) { while (1) { snprintf(ppp->dev->name, IFNAMSIZ, "ppp%i", ret); - if (!__dev_get_by_name(ppp->ppp_net, ppp->dev->name)) + if (!netdev_name_in_use(ppp->ppp_net, ppp->dev->name)) break; unit_put(&pn->units_idr, ret); ret = unit_get(&pn->units_idr, ppp, ret + 1); diff --git a/drivers/net/rionet.c b/drivers/net/rionet.c index 2056d6ad04b5..1a95f3beb784 100644 --- a/drivers/net/rionet.c +++ b/drivers/net/rionet.c @@ -482,6 +482,7 @@ static int rionet_setup_netdev(struct rio_mport *mport, struct net_device *ndev) { int rc = 0; struct rionet_private *rnet; + u8 addr[ETH_ALEN]; u16 device_id; const size_t rionet_active_bytes = sizeof(void *) * RIO_MAX_ROUTE_ENTRIES(mport->sys_size); @@ -501,12 +502,13 @@ static int rionet_setup_netdev(struct rio_mport *mport, struct net_device *ndev) /* Set the default MAC address */ device_id = rio_local_get_device_id(mport); - ndev->dev_addr[0] = 0x00; - ndev->dev_addr[1] = 0x01; - ndev->dev_addr[2] = 0x00; - ndev->dev_addr[3] = 0x01; - ndev->dev_addr[4] = device_id >> 8; - ndev->dev_addr[5] = device_id & 0xff; + addr[0] = 0x00; + addr[1] = 0x01; + addr[2] = 0x00; + addr[3] = 0x01; + addr[4] = device_id >> 8; + addr[5] = device_id & 0xff; + eth_hw_addr_set(ndev, addr); ndev->netdev_ops = &rionet_netdev_ops; ndev->mtu = RIONET_MAX_MTU; diff --git a/drivers/net/sb1000.c b/drivers/net/sb1000.c index f01c9db01b16..57a6d598467b 100644 --- a/drivers/net/sb1000.c +++ b/drivers/net/sb1000.c @@ -149,6 +149,7 @@ sb1000_probe_one(struct pnp_dev *pdev, const struct pnp_device_id *id) unsigned short ioaddr[2], irq; unsigned int serial_number; int error = -ENODEV; + u8 addr[ETH_ALEN]; if (pnp_device_attach(pdev) < 0) return -ENODEV; @@ -203,10 +204,13 @@ sb1000_probe_one(struct pnp_dev *pdev, const struct pnp_device_id *id) dev->netdev_ops = &sb1000_netdev_ops; /* hardware address is 0:0:serial_number */ - dev->dev_addr[2] = serial_number >> 24 & 0xff; - dev->dev_addr[3] = serial_number >> 16 & 0xff; - dev->dev_addr[4] = serial_number >> 8 & 0xff; - dev->dev_addr[5] = serial_number >> 0 & 0xff; + addr[0] = 0; + addr[1] = 0; + addr[2] = serial_number >> 24 & 0xff; + addr[3] = serial_number >> 16 & 0xff; + addr[4] = serial_number >> 8 & 0xff; + addr[5] = serial_number >> 0 & 0xff; + eth_hw_addr_set(dev, addr); pnp_set_drvdata(pdev, dev); diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index dd7917cab2b1..8b2adc56b92a 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -1790,7 +1790,7 @@ static int team_set_mac_address(struct net_device *dev, void *p) if (dev->type == ARPHRD_ETHER && !is_valid_ether_addr(addr->sa_data)) return -EADDRNOTAVAIL; - memcpy(dev->dev_addr, addr->sa_data, dev->addr_len); + dev_addr_set(dev, addr->sa_data); mutex_lock(&team->lock); list_for_each_entry(port, &team->port_list, list) if (team->ops.port_change_dev_addr) diff --git a/drivers/net/usb/aqc111.c b/drivers/net/usb/aqc111.c index 981ac1c33780..ea06d10e1c21 100644 --- a/drivers/net/usb/aqc111.c +++ b/drivers/net/usb/aqc111.c @@ -119,7 +119,7 @@ static int aqc111_write_cmd_nopm(struct usbnet *dev, u8 cmd, u16 value, } static int aqc111_write_cmd(struct usbnet *dev, u8 cmd, u16 value, - u16 index, u16 size, void *data) + u16 index, u16 size, const void *data) { int ret; diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c index 5ed59d9dd631..ea8aa8c33241 100644 --- a/drivers/net/usb/ax88179_178a.c +++ b/drivers/net/usb/ax88179_178a.c @@ -209,7 +209,7 @@ static int __ax88179_read_cmd(struct usbnet *dev, u8 cmd, u16 value, u16 index, } static int __ax88179_write_cmd(struct usbnet *dev, u8 cmd, u16 value, u16 index, - u16 size, void *data, int in_pm) + u16 size, const void *data, int in_pm) { int ret; int (*fn)(struct usbnet *, u8, u8, u16, u16, const void *, u16); @@ -272,7 +272,7 @@ static int ax88179_read_cmd_nopm(struct usbnet *dev, u8 cmd, u16 value, } static int ax88179_write_cmd_nopm(struct usbnet *dev, u8 cmd, u16 value, - u16 index, u16 size, void *data) + u16 index, u16 size, const void *data) { int ret; @@ -313,7 +313,7 @@ static int ax88179_read_cmd(struct usbnet *dev, u8 cmd, u16 value, u16 index, } static int ax88179_write_cmd(struct usbnet *dev, u8 cmd, u16 value, u16 index, - u16 size, void *data) + u16 size, const void *data) { int ret; @@ -463,7 +463,7 @@ static int ax88179_auto_detach(struct usbnet *dev, int in_pm) u16 tmp16; u8 tmp8; int (*fnr)(struct usbnet *, u8, u16, u16, u16, void *); - int (*fnw)(struct usbnet *, u8, u16, u16, u16, void *); + int (*fnw)(struct usbnet *, u8, u16, u16, u16, const void *); if (!in_pm) { fnr = ax88179_read_cmd; diff --git a/drivers/net/usb/catc.c b/drivers/net/usb/catc.c index 97ba67042d12..24db5768a3c0 100644 --- a/drivers/net/usb/catc.c +++ b/drivers/net/usb/catc.c @@ -615,7 +615,7 @@ static void catc_stats_timer(struct timer_list *t) * Receive modes. Broadcast, Multicast, Promisc. */ -static void catc_multicast(unsigned char *addr, u8 *multicast) +static void catc_multicast(const unsigned char *addr, u8 *multicast) { u32 crc; diff --git a/drivers/net/usb/cdc-phonet.c b/drivers/net/usb/cdc-phonet.c index e1da9102a540..ad5121e9cf5d 100644 --- a/drivers/net/usb/cdc-phonet.c +++ b/drivers/net/usb/cdc-phonet.c @@ -275,6 +275,8 @@ static const struct net_device_ops usbpn_ops = { static void usbpn_setup(struct net_device *dev) { + const u8 addr = PN_MEDIA_USB; + dev->features = 0; dev->netdev_ops = &usbpn_ops; dev->header_ops = &phonet_header_ops; @@ -284,8 +286,8 @@ static void usbpn_setup(struct net_device *dev) dev->min_mtu = PHONET_MIN_MTU; dev->max_mtu = PHONET_MAX_MTU; dev->hard_header_len = 1; - dev->dev_addr[0] = PN_MEDIA_USB; dev->addr_len = 1; + dev_addr_set(dev, &addr); dev->tx_queue_len = 3; dev->needs_free_netdev = true; diff --git a/drivers/net/usb/ch9200.c b/drivers/net/usb/ch9200.c index d7f3b70d5477..f69d9b902da0 100644 --- a/drivers/net/usb/ch9200.c +++ b/drivers/net/usb/ch9200.c @@ -336,6 +336,7 @@ static int ch9200_bind(struct usbnet *dev, struct usb_interface *intf) { int retval = 0; unsigned char data[2]; + u8 addr[ETH_ALEN]; retval = usbnet_get_endpoints(dev, intf); if (retval) @@ -383,7 +384,8 @@ static int ch9200_bind(struct usbnet *dev, struct usb_interface *intf) retval = control_write(dev, REQUEST_WRITE, 0, MAC_REG_CTRL, data, 0x02, CONTROL_TIMEOUT_MS); - retval = get_mac_address(dev, dev->net->dev_addr); + retval = get_mac_address(dev, addr); + eth_hw_addr_set(dev->net, addr); return retval; } diff --git a/drivers/net/usb/cx82310_eth.c b/drivers/net/usb/cx82310_eth.c index c4568a491dc4..79a47e2fd437 100644 --- a/drivers/net/usb/cx82310_eth.c +++ b/drivers/net/usb/cx82310_eth.c @@ -146,6 +146,7 @@ static int cx82310_bind(struct usbnet *dev, struct usb_interface *intf) u8 link[3]; int timeout = 50; struct cx82310_priv *priv; + u8 addr[ETH_ALEN]; /* avoid ADSL modems - continue only if iProduct is "USB NET CARD" */ if (usb_string(udev, udev->descriptor.iProduct, buf, sizeof(buf)) > 0 @@ -202,12 +203,12 @@ static int cx82310_bind(struct usbnet *dev, struct usb_interface *intf) goto err; /* get the MAC address */ - ret = cx82310_cmd(dev, CMD_GET_MAC_ADDR, true, NULL, 0, - dev->net->dev_addr, ETH_ALEN); + ret = cx82310_cmd(dev, CMD_GET_MAC_ADDR, true, NULL, 0, addr, ETH_ALEN); if (ret) { netdev_err(dev->net, "unable to read MAC address: %d\n", ret); goto err; } + eth_hw_addr_set(dev->net, addr); /* start (does not seem to have any effect?) */ ret = cx82310_cmd(dev, CMD_START, false, NULL, 0, NULL, 0); diff --git a/drivers/net/usb/dm9601.c b/drivers/net/usb/dm9601.c index dcdb46314685..48d7d278631e 100644 --- a/drivers/net/usb/dm9601.c +++ b/drivers/net/usb/dm9601.c @@ -93,7 +93,8 @@ static int dm_write_reg(struct usbnet *dev, u8 reg, u8 value) value, reg, NULL, 0); } -static void dm_write_async(struct usbnet *dev, u8 reg, u16 length, void *data) +static void dm_write_async(struct usbnet *dev, u8 reg, u16 length, + const void *data) { usbnet_write_cmd_async(dev, DM_WRITE_REGS, USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_DEVICE, diff --git a/drivers/net/usb/kaweth.c b/drivers/net/usb/kaweth.c index 144c686b4333..9b2bc1993ece 100644 --- a/drivers/net/usb/kaweth.c +++ b/drivers/net/usb/kaweth.c @@ -1044,8 +1044,7 @@ err_fw: goto err_all_but_rxbuf; memcpy(netdev->broadcast, &bcast_addr, sizeof(bcast_addr)); - memcpy(netdev->dev_addr, &kaweth->configuration.hw_addr, - sizeof(kaweth->configuration.hw_addr)); + eth_hw_addr_set(netdev, (u8 *)&kaweth->configuration.hw_addr); netdev->netdev_ops = &kaweth_netdev_ops; netdev->watchdog_timeo = KAWETH_TX_TIMEOUT; diff --git a/drivers/net/usb/mcs7830.c b/drivers/net/usb/mcs7830.c index cead742da381..326cc4e749d8 100644 --- a/drivers/net/usb/mcs7830.c +++ b/drivers/net/usb/mcs7830.c @@ -132,7 +132,8 @@ static int mcs7830_hif_get_mac_address(struct usbnet *dev, unsigned char *addr) return 0; } -static int mcs7830_hif_set_mac_address(struct usbnet *dev, unsigned char *addr) +static int mcs7830_hif_set_mac_address(struct usbnet *dev, + const unsigned char *addr) { int ret = mcs7830_set_reg(dev, HIF_REG_ETHERNET_ADDR, ETH_ALEN, addr); @@ -472,17 +473,19 @@ static const struct net_device_ops mcs7830_netdev_ops = { static int mcs7830_bind(struct usbnet *dev, struct usb_interface *udev) { struct net_device *net = dev->net; + u8 addr[ETH_ALEN]; int ret; int retry; /* Initial startup: Gather MAC address setting from EEPROM */ ret = -EINVAL; for (retry = 0; retry < 5 && ret; retry++) - ret = mcs7830_hif_get_mac_address(dev, net->dev_addr); + ret = mcs7830_hif_get_mac_address(dev, addr); if (ret) { dev_warn(&dev->udev->dev, "Cannot read MAC address\n"); goto out; } + eth_hw_addr_set(net, addr); mcs7830_data_set_multicast(net); diff --git a/drivers/net/usb/pegasus.c b/drivers/net/usb/pegasus.c index 6a92a3fef75e..c4cd40b090fd 100644 --- a/drivers/net/usb/pegasus.c +++ b/drivers/net/usb/pegasus.c @@ -357,7 +357,7 @@ static void set_ethernet_addr(pegasus_t *pegasus) goto err; } - memcpy(pegasus->net->dev_addr, node_id, sizeof(node_id)); + eth_hw_addr_set(pegasus->net, node_id); return; err: diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 33ada2c59952..86b814e99224 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -835,8 +835,11 @@ static int qmi_wwan_bind(struct usbnet *dev, struct usb_interface *intf) /* make MAC addr easily distinguishable from an IP header */ if (possibly_iphdr(dev->net->dev_addr)) { - dev->net->dev_addr[0] |= 0x02; /* set local assignment bit */ - dev->net->dev_addr[0] &= 0xbf; /* clear "IP" bit */ + u8 addr = dev->net->dev_addr[0]; + + addr |= 0x02; /* set local assignment bit */ + addr &= 0xbf; /* clear "IP" bit */ + dev_addr_mod(dev->net, 0, &addr, 1); } dev->net->netdev_ops = &qmi_wwan_netdev_ops; dev->net->sysfs_groups[0] = &qmi_wwan_sysfs_attr_group; diff --git a/drivers/net/usb/sierra_net.c b/drivers/net/usb/sierra_net.c index 55025202dc4f..bb4cbe8fc846 100644 --- a/drivers/net/usb/sierra_net.c +++ b/drivers/net/usb/sierra_net.c @@ -669,6 +669,7 @@ static int sierra_net_bind(struct usbnet *dev, struct usb_interface *intf) 0x00, 0x00, SIERRA_NET_HIP_MSYNC_ID, 0x00}; static const u8 shdwn_tmplate[sizeof(priv->shdwn_msg)] = { 0x00, 0x00, SIERRA_NET_HIP_SHUTD_ID, 0x00}; + u8 mod[2]; dev_dbg(&dev->udev->dev, "%s", __func__); @@ -698,8 +699,9 @@ static int sierra_net_bind(struct usbnet *dev, struct usb_interface *intf) dev->net->netdev_ops = &sierra_net_device_ops; /* change MAC addr to include, ifacenum, and to be unique */ - dev->net->dev_addr[ETH_ALEN-2] = atomic_inc_return(&iface_counter); - dev->net->dev_addr[ETH_ALEN-1] = ifacenum; + mod[0] = atomic_inc_return(&iface_counter); + mod[1] = ifacenum; + dev_addr_mod(dev->net, ETH_ALEN - 2, mod, 2); /* prepare shutdown message template */ memcpy(priv->shdwn_msg, shdwn_tmplate, sizeof(priv->shdwn_msg)); diff --git a/drivers/net/usb/smsc75xx.c b/drivers/net/usb/smsc75xx.c index 76f7af161313..95de452ff4da 100644 --- a/drivers/net/usb/smsc75xx.c +++ b/drivers/net/usb/smsc75xx.c @@ -757,9 +757,10 @@ static int smsc75xx_ioctl(struct net_device *netdev, struct ifreq *rq, int cmd) static void smsc75xx_init_mac_address(struct usbnet *dev) { + u8 addr[ETH_ALEN]; + /* maybe the boot loader passed the MAC address in devicetree */ - if (!eth_platform_get_mac_address(&dev->udev->dev, - dev->net->dev_addr)) { + if (!platform_get_ethdev_address(&dev->udev->dev, dev->net)) { if (is_valid_ether_addr(dev->net->dev_addr)) { /* device tree values are valid so use them */ netif_dbg(dev, ifup, dev->net, "MAC address read from the device tree\n"); @@ -768,8 +769,8 @@ static void smsc75xx_init_mac_address(struct usbnet *dev) } /* try reading mac address from EEPROM */ - if (smsc75xx_read_eeprom(dev, EEPROM_MAC_OFFSET, ETH_ALEN, - dev->net->dev_addr) == 0) { + if (smsc75xx_read_eeprom(dev, EEPROM_MAC_OFFSET, ETH_ALEN, addr) == 0) { + eth_hw_addr_set(dev->net, addr); if (is_valid_ether_addr(dev->net->dev_addr)) { /* eeprom values are valid so use them */ netif_dbg(dev, ifup, dev->net, diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c index 26b1bd8e845b..20fe4cd8f784 100644 --- a/drivers/net/usb/smsc95xx.c +++ b/drivers/net/usb/smsc95xx.c @@ -755,9 +755,10 @@ static int smsc95xx_ioctl(struct net_device *netdev, struct ifreq *rq, int cmd) static void smsc95xx_init_mac_address(struct usbnet *dev) { + u8 addr[ETH_ALEN]; + /* maybe the boot loader passed the MAC address in devicetree */ - if (!eth_platform_get_mac_address(&dev->udev->dev, - dev->net->dev_addr)) { + if (!platform_get_ethdev_address(&dev->udev->dev, dev->net)) { if (is_valid_ether_addr(dev->net->dev_addr)) { /* device tree values are valid so use them */ netif_dbg(dev, ifup, dev->net, "MAC address read from the device tree\n"); @@ -766,8 +767,8 @@ static void smsc95xx_init_mac_address(struct usbnet *dev) } /* try reading mac address from EEPROM */ - if (smsc95xx_read_eeprom(dev, EEPROM_MAC_OFFSET, ETH_ALEN, - dev->net->dev_addr) == 0) { + if (smsc95xx_read_eeprom(dev, EEPROM_MAC_OFFSET, ETH_ALEN, addr) == 0) { + eth_hw_addr_set(dev->net, addr); if (is_valid_ether_addr(dev->net->dev_addr)) { /* eeprom values are valid so use them */ netif_dbg(dev, ifup, dev->net, "MAC address read from EEPROM\n"); diff --git a/drivers/net/usb/sr9700.c b/drivers/net/usb/sr9700.c index 068f197f1786..b658510cc9a4 100644 --- a/drivers/net/usb/sr9700.c +++ b/drivers/net/usb/sr9700.c @@ -56,7 +56,8 @@ static int sr_write_reg(struct usbnet *dev, u8 reg, u8 value) value, reg, NULL, 0); } -static void sr_write_async(struct usbnet *dev, u8 reg, u16 length, void *data) +static void sr_write_async(struct usbnet *dev, u8 reg, u16 length, + const void *data) { usbnet_write_cmd_async(dev, SR_WR_REGS, SR_REQ_WR_REG, 0, reg, data, length); @@ -319,6 +320,7 @@ static int sr9700_bind(struct usbnet *dev, struct usb_interface *intf) { struct net_device *netdev; struct mii_if_info *mii; + u8 addr[ETH_ALEN]; int ret; ret = usbnet_get_endpoints(dev, intf); @@ -349,11 +351,12 @@ static int sr9700_bind(struct usbnet *dev, struct usb_interface *intf) * EEPROM automatically to PAR. In case there is no EEPROM externally, * a default MAC address is stored in PAR for making chip work properly. */ - if (sr_read(dev, SR_PAR, ETH_ALEN, netdev->dev_addr) < 0) { + if (sr_read(dev, SR_PAR, ETH_ALEN, addr) < 0) { netdev_err(netdev, "Error reading MAC address\n"); ret = -ENODEV; goto out; } + eth_hw_addr_set(netdev, addr); /* power up and reset phy */ sr_write_reg(dev, SR_PRR, PRR_PHY_RST); diff --git a/drivers/net/usb/sr9800.c b/drivers/net/usb/sr9800.c index 838f4e9e8b58..f5e19f3ef6cd 100644 --- a/drivers/net/usb/sr9800.c +++ b/drivers/net/usb/sr9800.c @@ -731,6 +731,7 @@ static int sr9800_bind(struct usbnet *dev, struct usb_interface *intf) struct sr_data *data = (struct sr_data *)&dev->data; u16 led01_mux, led23_mux; int ret, embd_phy; + u8 addr[ETH_ALEN]; u32 phyid; u16 rx_ctl; @@ -754,12 +755,12 @@ static int sr9800_bind(struct usbnet *dev, struct usb_interface *intf) } /* Get the MAC address */ - ret = sr_read_cmd(dev, SR_CMD_READ_NODE_ID, 0, 0, ETH_ALEN, - dev->net->dev_addr); + ret = sr_read_cmd(dev, SR_CMD_READ_NODE_ID, 0, 0, ETH_ALEN, addr); if (ret < 0) { netdev_dbg(dev->net, "Failed to read MAC address: %d\n", ret); return ret; } + eth_hw_addr_set(dev->net, addr); netdev_dbg(dev->net, "mac addr : %pM\n", dev->net->dev_addr); /* Initialize MII structure */ diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index a33d7fb82a00..9a6450f796dc 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -165,12 +165,13 @@ EXPORT_SYMBOL_GPL(usbnet_get_endpoints); int usbnet_get_ethernet_addr(struct usbnet *dev, int iMACAddress) { + u8 addr[ETH_ALEN]; int tmp = -1, ret; unsigned char buf [13]; ret = usb_string(dev->udev, iMACAddress, buf, sizeof buf); if (ret == 12) - tmp = hex2bin(dev->net->dev_addr, buf, 6); + tmp = hex2bin(addr, buf, 6); if (tmp < 0) { dev_dbg(&dev->udev->dev, "bad MAC string %d fetch, %d\n", iMACAddress, tmp); @@ -178,6 +179,7 @@ int usbnet_get_ethernet_addr(struct usbnet *dev, int iMACAddress) ret = -EINVAL; return ret; } + eth_hw_addr_set(dev->net, addr); return 0; } EXPORT_SYMBOL_GPL(usbnet_get_ethernet_addr); @@ -1726,7 +1728,7 @@ usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod) dev->net = net; strscpy(net->name, "usb%d", sizeof(net->name)); - memcpy (net->dev_addr, node_id, sizeof node_id); + eth_hw_addr_set(net, node_id); /* rx and tx sides can use different message sizes; * bind() should set rx_urb_size in that case. diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 0febc3522d7a..c501b5974aee 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -734,6 +734,12 @@ static struct sk_buff *receive_small(struct net_device *dev, dev->stats.rx_length_errors++; goto err_len; } + + if (likely(!vi->xdp_enabled)) { + xdp_prog = NULL; + goto skip_xdp; + } + rcu_read_lock(); xdp_prog = rcu_dereference(rq->xdp_prog); if (xdp_prog) { @@ -816,6 +822,7 @@ static struct sk_buff *receive_small(struct net_device *dev, } rcu_read_unlock(); +skip_xdp: skb = build_skb(buf, buflen); if (!skb) { put_page(page); @@ -897,6 +904,12 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, dev->stats.rx_length_errors++; goto err_skb; } + + if (likely(!vi->xdp_enabled)) { + xdp_prog = NULL; + goto skip_xdp; + } + rcu_read_lock(); xdp_prog = rcu_dereference(rq->xdp_prog); if (xdp_prog) { @@ -1024,6 +1037,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, } rcu_read_unlock(); +skip_xdp: head_skb = page_to_skb(vi, rq, page, offset, len, truesize, !xdp_prog, metasize, headroom); curr_skb = head_skb; diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c index 8799854bacb2..063ecceba5db 100644 --- a/drivers/net/vmxnet3/vmxnet3_drv.c +++ b/drivers/net/vmxnet3/vmxnet3_drv.c @@ -2824,7 +2824,7 @@ vmxnet3_set_mac_addr(struct net_device *netdev, void *p) struct sockaddr *addr = p; struct vmxnet3_adapter *adapter = netdev_priv(netdev); - memcpy(netdev->dev_addr, addr->sa_data, netdev->addr_len); + dev_addr_set(netdev, addr->sa_data); vmxnet3_write_mac_addr(adapter, addr->sa_data); return 0; @@ -3638,7 +3638,7 @@ vmxnet3_probe_device(struct pci_dev *pdev, #endif vmxnet3_read_mac_addr(adapter, mac); - memcpy(netdev->dev_addr, mac, netdev->addr_len); + dev_addr_set(netdev, mac); netdev->netdev_ops = &vmxnet3_netdev_ops; vmxnet3_set_ethtool_ops(netdev); diff --git a/drivers/net/wan/hdlc_fr.c b/drivers/net/wan/hdlc_fr.c index 7637edce443e..81e72bc1891f 100644 --- a/drivers/net/wan/hdlc_fr.c +++ b/drivers/net/wan/hdlc_fr.c @@ -1093,7 +1093,9 @@ static int fr_add_pvc(struct net_device *frad, unsigned int dlci, int type) dev->priv_flags &= ~IFF_TX_SKB_SHARING; eth_hw_addr_random(dev); } else { - *(__be16 *)dev->dev_addr = htons(dlci); + __be16 addr = htons(dlci); + + dev_addr_set(dev, (u8 *)&addr); dlci_to_q922(dev->broadcast, dlci); } dev->netdev_ops = &pvc_ops; diff --git a/drivers/net/wan/lapbether.c b/drivers/net/wan/lapbether.c index 89d31adc3809..282192b82404 100644 --- a/drivers/net/wan/lapbether.c +++ b/drivers/net/wan/lapbether.c @@ -301,7 +301,7 @@ static int lapbeth_set_mac_address(struct net_device *dev, void *addr) { struct sockaddr *sa = addr; - memcpy(dev->dev_addr, sa->sa_data, dev->addr_len); + dev_addr_set(dev, sa->sa_data); return 0; } diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c index 31f0cfba5bf5..da850f4b2919 100644 --- a/drivers/net/wireless/ath/ath11k/mac.c +++ b/drivers/net/wireless/ath/ath11k/mac.c @@ -2076,8 +2076,8 @@ static void ath11k_peer_assoc_h_smps(struct ieee80211_sta *sta, smps = ht_cap->cap & IEEE80211_HT_CAP_SM_PS; smps >>= IEEE80211_HT_CAP_SM_PS_SHIFT; } else { - smps = FIELD_GET(IEEE80211_HE_6GHZ_CAP_SM_PS, - le16_to_cpu(sta->he_6ghz_capa.capa)); + smps = le16_get_bits(sta->he_6ghz_capa.capa, + IEEE80211_HE_6GHZ_CAP_SM_PS); } switch (smps) { diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 0adae76eb8df..23219f3747f8 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -2802,7 +2802,6 @@ out_err: static const struct ieee80211_sband_iftype_data he_capa_2ghz[] = { { - /* TODO: should we support other types, e.g., P2P?*/ .types_mask = BIT(NL80211_IFTYPE_STATION) | BIT(NL80211_IFTYPE_AP), .he_cap = { @@ -2850,7 +2849,6 @@ static const struct ieee80211_sband_iftype_data he_capa_2ghz[] = { }, #ifdef CONFIG_MAC80211_MESH { - /* TODO: should we support other types, e.g., IBSS?*/ .types_mask = BIT(NL80211_IFTYPE_MESH_POINT), .he_cap = { .has_he = true, @@ -2988,6 +2986,122 @@ static const struct ieee80211_sband_iftype_data he_capa_5ghz[] = { #endif }; +static const struct ieee80211_sband_iftype_data he_capa_6ghz[] = { + { + /* TODO: should we support other types, e.g., P2P?*/ + .types_mask = BIT(NL80211_IFTYPE_STATION) | + BIT(NL80211_IFTYPE_AP), + .he_6ghz_capa = { + .capa = cpu_to_le16(IEEE80211_HE_6GHZ_CAP_MIN_MPDU_START | + IEEE80211_HE_6GHZ_CAP_MAX_AMPDU_LEN_EXP | + IEEE80211_HE_6GHZ_CAP_MAX_MPDU_LEN | + IEEE80211_HE_6GHZ_CAP_SM_PS | + IEEE80211_HE_6GHZ_CAP_RD_RESPONDER | + IEEE80211_HE_6GHZ_CAP_TX_ANTPAT_CONS | + IEEE80211_HE_6GHZ_CAP_RX_ANTPAT_CONS), + }, + .he_cap = { + .has_he = true, + .he_cap_elem = { + .mac_cap_info[0] = + IEEE80211_HE_MAC_CAP0_HTC_HE, + .mac_cap_info[1] = + IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_16US | + IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_8, + .mac_cap_info[2] = + IEEE80211_HE_MAC_CAP2_BSR | + IEEE80211_HE_MAC_CAP2_MU_CASCADING | + IEEE80211_HE_MAC_CAP2_ACK_EN, + .mac_cap_info[3] = + IEEE80211_HE_MAC_CAP3_OMI_CONTROL | + IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_EXT_3, + .mac_cap_info[4] = IEEE80211_HE_MAC_CAP4_AMSDU_IN_AMPDU, + .phy_cap_info[0] = + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G | + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G | + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G, + .phy_cap_info[1] = + IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_MASK | + IEEE80211_HE_PHY_CAP1_DEVICE_CLASS_A | + IEEE80211_HE_PHY_CAP1_LDPC_CODING_IN_PAYLOAD | + IEEE80211_HE_PHY_CAP1_MIDAMBLE_RX_TX_MAX_NSTS, + .phy_cap_info[2] = + IEEE80211_HE_PHY_CAP2_NDP_4x_LTF_AND_3_2US | + IEEE80211_HE_PHY_CAP2_STBC_TX_UNDER_80MHZ | + IEEE80211_HE_PHY_CAP2_STBC_RX_UNDER_80MHZ | + IEEE80211_HE_PHY_CAP2_UL_MU_FULL_MU_MIMO | + IEEE80211_HE_PHY_CAP2_UL_MU_PARTIAL_MU_MIMO, + + /* Leave all the other PHY capability bytes + * unset, as DCM, beam forming, RU and PPE + * threshold information are not supported + */ + }, + .he_mcs_nss_supp = { + .rx_mcs_80 = cpu_to_le16(0xfffa), + .tx_mcs_80 = cpu_to_le16(0xfffa), + .rx_mcs_160 = cpu_to_le16(0xfffa), + .tx_mcs_160 = cpu_to_le16(0xfffa), + .rx_mcs_80p80 = cpu_to_le16(0xfffa), + .tx_mcs_80p80 = cpu_to_le16(0xfffa), + }, + }, + }, +#ifdef CONFIG_MAC80211_MESH + { + /* TODO: should we support other types, e.g., IBSS?*/ + .types_mask = BIT(NL80211_IFTYPE_MESH_POINT), + .he_6ghz_capa = { + .capa = cpu_to_le16(IEEE80211_HE_6GHZ_CAP_MIN_MPDU_START | + IEEE80211_HE_6GHZ_CAP_MAX_AMPDU_LEN_EXP | + IEEE80211_HE_6GHZ_CAP_MAX_MPDU_LEN | + IEEE80211_HE_6GHZ_CAP_SM_PS | + IEEE80211_HE_6GHZ_CAP_RD_RESPONDER | + IEEE80211_HE_6GHZ_CAP_TX_ANTPAT_CONS | + IEEE80211_HE_6GHZ_CAP_RX_ANTPAT_CONS), + }, + .he_cap = { + .has_he = true, + .he_cap_elem = { + .mac_cap_info[0] = + IEEE80211_HE_MAC_CAP0_HTC_HE, + .mac_cap_info[1] = + IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_8, + .mac_cap_info[2] = + IEEE80211_HE_MAC_CAP2_ACK_EN, + .mac_cap_info[3] = + IEEE80211_HE_MAC_CAP3_OMI_CONTROL | + IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_EXT_3, + .mac_cap_info[4] = IEEE80211_HE_MAC_CAP4_AMSDU_IN_AMPDU, + .phy_cap_info[0] = + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G | + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G | + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G, + .phy_cap_info[1] = + IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_MASK | + IEEE80211_HE_PHY_CAP1_DEVICE_CLASS_A | + IEEE80211_HE_PHY_CAP1_LDPC_CODING_IN_PAYLOAD | + IEEE80211_HE_PHY_CAP1_MIDAMBLE_RX_TX_MAX_NSTS, + .phy_cap_info[2] = 0, + + /* Leave all the other PHY capability bytes + * unset, as DCM, beam forming, RU and PPE + * threshold information are not supported + */ + }, + .he_mcs_nss_supp = { + .rx_mcs_80 = cpu_to_le16(0xfffa), + .tx_mcs_80 = cpu_to_le16(0xfffa), + .rx_mcs_160 = cpu_to_le16(0xfffa), + .tx_mcs_160 = cpu_to_le16(0xfffa), + .rx_mcs_80p80 = cpu_to_le16(0xfffa), + .tx_mcs_80p80 = cpu_to_le16(0xfffa), + }, + }, + }, +#endif +}; + static void mac80211_hwsim_he_capab(struct ieee80211_supported_band *sband) { u16 n_iftype_data; @@ -3000,6 +3114,10 @@ static void mac80211_hwsim_he_capab(struct ieee80211_supported_band *sband) n_iftype_data = ARRAY_SIZE(he_capa_5ghz); sband->iftype_data = (struct ieee80211_sband_iftype_data *)he_capa_5ghz; + } else if (sband->band == NL80211_BAND_6GHZ) { + n_iftype_data = ARRAY_SIZE(he_capa_6ghz); + sband->iftype_data = + (struct ieee80211_sband_iftype_data *)he_capa_6ghz; } else { return; } @@ -3290,6 +3408,12 @@ static int mac80211_hwsim_new_radio(struct genl_info *info, sband->vht_cap.vht_mcs.tx_mcs_map = sband->vht_cap.vht_mcs.rx_mcs_map; break; + case NL80211_BAND_6GHZ: + sband->channels = data->channels_6ghz; + sband->n_channels = ARRAY_SIZE(hwsim_channels_6ghz); + sband->bitrates = data->rates + 4; + sband->n_bitrates = ARRAY_SIZE(hwsim_rates) - 4; + break; case NL80211_BAND_S1GHZ: memcpy(&sband->s1g_cap, &hwsim_s1g_cap, sizeof(sband->s1g_cap)); @@ -3300,19 +3424,21 @@ static int mac80211_hwsim_new_radio(struct genl_info *info, continue; } - sband->ht_cap.ht_supported = true; - sband->ht_cap.cap = IEEE80211_HT_CAP_SUP_WIDTH_20_40 | - IEEE80211_HT_CAP_GRN_FLD | - IEEE80211_HT_CAP_SGI_20 | - IEEE80211_HT_CAP_SGI_40 | - IEEE80211_HT_CAP_DSSSCCK40; - sband->ht_cap.ampdu_factor = 0x3; - sband->ht_cap.ampdu_density = 0x6; - memset(&sband->ht_cap.mcs, 0, - sizeof(sband->ht_cap.mcs)); - sband->ht_cap.mcs.rx_mask[0] = 0xff; - sband->ht_cap.mcs.rx_mask[1] = 0xff; - sband->ht_cap.mcs.tx_params = IEEE80211_HT_MCS_TX_DEFINED; + if (band != NL80211_BAND_6GHZ){ + sband->ht_cap.ht_supported = true; + sband->ht_cap.cap = IEEE80211_HT_CAP_SUP_WIDTH_20_40 | + IEEE80211_HT_CAP_GRN_FLD | + IEEE80211_HT_CAP_SGI_20 | + IEEE80211_HT_CAP_SGI_40 | + IEEE80211_HT_CAP_DSSSCCK40; + sband->ht_cap.ampdu_factor = 0x3; + sband->ht_cap.ampdu_density = 0x6; + memset(&sband->ht_cap.mcs, 0, + sizeof(sband->ht_cap.mcs)); + sband->ht_cap.mcs.rx_mask[0] = 0xff; + sband->ht_cap.mcs.rx_mask[1] = 0xff; + sband->ht_cap.mcs.tx_params = IEEE80211_HT_MCS_TX_DEFINED; + } mac80211_hwsim_he_capab(sband); @@ -3527,13 +3653,16 @@ static const struct net_device_ops hwsim_netdev_ops = { static void hwsim_mon_setup(struct net_device *dev) { + u8 addr[ETH_ALEN]; + dev->netdev_ops = &hwsim_netdev_ops; dev->needs_free_netdev = true; ether_setup(dev); dev->priv_flags |= IFF_NO_QUEUE; dev->type = ARPHRD_IEEE80211_RADIOTAP; - eth_zero_addr(dev->dev_addr); - dev->dev_addr[0] = 0x12; + eth_zero_addr(addr); + addr[0] = 0x12; + eth_hw_addr_set(dev, addr); } static struct mac80211_hwsim_data *get_hwsim_data_ref_from_addr(const u8 *addr) diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c index c58996c1e230..fe8e21ad8ed9 100644 --- a/drivers/net/xen-netback/interface.c +++ b/drivers/net/xen-netback/interface.c @@ -494,6 +494,9 @@ static const struct net_device_ops xenvif_netdev_ops = { struct xenvif *xenvif_alloc(struct device *parent, domid_t domid, unsigned int handle) { + static const u8 dummy_addr[ETH_ALEN] = { + 0xfe, 0xff, 0xff, 0xff, 0xff, 0xff, + }; int err; struct net_device *dev; struct xenvif *vif; @@ -551,8 +554,7 @@ struct xenvif *xenvif_alloc(struct device *parent, domid_t domid, * stolen by an Ethernet bridge for STP purposes. * (FE:FF:FF:FF:FF:FF) */ - eth_broadcast_addr(dev->dev_addr); - dev->dev_addr[0] &= ~0x01; + eth_hw_addr_set(dev, dummy_addr); netif_carrier_off(dev); diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index 32d5bc4919d8..0f7fd159f0f2 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -1474,7 +1474,7 @@ int xenvif_map_frontend_data_rings(struct xenvif_queue *queue, struct xen_netif_tx_sring *txs; struct xen_netif_rx_sring *rxs; RING_IDX rsp_prod, req_prod; - int err = -ENOMEM; + int err; err = xenbus_map_ring_valloc(xenvif_to_xenbus_device(queue->vif), &tx_ring_ref, 1, &addr); diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index fc41ba95f81d..911f43986a8c 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -2161,6 +2161,7 @@ static int talk_to_netback(struct xenbus_device *dev, unsigned int max_queues = 0; struct netfront_queue *queue = NULL; unsigned int num_queues = 1; + u8 addr[ETH_ALEN]; info->netdev->irq = 0; @@ -2174,11 +2175,12 @@ static int talk_to_netback(struct xenbus_device *dev, "feature-split-event-channels", 0); /* Read mac addr. */ - err = xen_net_read_mac(dev, info->netdev->dev_addr); + err = xen_net_read_mac(dev, addr); if (err) { xenbus_dev_fatal(dev, err, "parsing %s/mac", dev->nodename); goto out_unlocked; } + eth_hw_addr_set(info->netdev, addr); info->netback_has_xdp_headroom = xenbus_read_unsigned(info->xbdev->otherend, "feature-xdp-headroom", 0); diff --git a/drivers/nfc/microread/i2c.c b/drivers/nfc/microread/i2c.c index 86f593c73ed6..067295124eb9 100644 --- a/drivers/nfc/microread/i2c.c +++ b/drivers/nfc/microread/i2c.c @@ -237,8 +237,6 @@ static int microread_i2c_probe(struct i2c_client *client, struct microread_i2c_phy *phy; int r; - dev_dbg(&client->dev, "client %p\n", client); - phy = devm_kzalloc(&client->dev, sizeof(struct microread_i2c_phy), GFP_KERNEL); if (!phy) @@ -262,8 +260,6 @@ static int microread_i2c_probe(struct i2c_client *client, if (r < 0) goto err_irq; - nfc_info(&client->dev, "Probed\n"); - return 0; err_irq: diff --git a/drivers/nfc/microread/mei.c b/drivers/nfc/microread/mei.c index 00689e18dc46..e2a77a5fc887 100644 --- a/drivers/nfc/microread/mei.c +++ b/drivers/nfc/microread/mei.c @@ -23,8 +23,6 @@ static int microread_mei_probe(struct mei_cl_device *cldev, struct nfc_mei_phy *phy; int r; - pr_info("Probing NFC microread\n"); - phy = nfc_mei_phy_alloc(cldev); if (!phy) return -ENOMEM; diff --git a/drivers/nfc/s3fwrn5/firmware.c b/drivers/nfc/s3fwrn5/firmware.c index 1af7a1e632cf..c20fdbac51c5 100644 --- a/drivers/nfc/s3fwrn5/firmware.c +++ b/drivers/nfc/s3fwrn5/firmware.c @@ -357,6 +357,7 @@ s3fwrn5_fw_is_custom(const struct s3fwrn5_fw_cmd_get_bootinfo_rsp *bootinfo) int s3fwrn5_fw_setup(struct s3fwrn5_fw_info *fw_info) { + struct device *dev = &fw_info->ndev->nfc_dev->dev; struct s3fwrn5_fw_cmd_get_bootinfo_rsp bootinfo; int ret; @@ -364,8 +365,7 @@ int s3fwrn5_fw_setup(struct s3fwrn5_fw_info *fw_info) ret = s3fwrn5_fw_get_bootinfo(fw_info, &bootinfo); if (ret < 0) { - dev_err(&fw_info->ndev->nfc_dev->dev, - "Failed to get bootinfo, ret=%02x\n", ret); + dev_err(dev, "Failed to get bootinfo, ret=%02x\n", ret); goto err; } @@ -373,8 +373,7 @@ int s3fwrn5_fw_setup(struct s3fwrn5_fw_info *fw_info) ret = s3fwrn5_fw_get_base_addr(&bootinfo, &fw_info->base_addr); if (ret < 0) { - dev_err(&fw_info->ndev->nfc_dev->dev, - "Unknown hardware version\n"); + dev_err(dev, "Unknown hardware version\n"); goto err; } @@ -409,6 +408,7 @@ bool s3fwrn5_fw_check_version(const struct s3fwrn5_fw_info *fw_info, u32 version int s3fwrn5_fw_download(struct s3fwrn5_fw_info *fw_info) { + struct device *dev = &fw_info->ndev->nfc_dev->dev; struct s3fwrn5_fw_image *fw = &fw_info->fw; u8 hash_data[SHA1_DIGEST_SIZE]; struct crypto_shash *tfm; @@ -421,8 +421,7 @@ int s3fwrn5_fw_download(struct s3fwrn5_fw_info *fw_info) tfm = crypto_alloc_shash("sha1", 0, 0); if (IS_ERR(tfm)) { - dev_err(&fw_info->ndev->nfc_dev->dev, - "Cannot allocate shash (code=%pe)\n", tfm); + dev_err(dev, "Cannot allocate shash (code=%pe)\n", tfm); return PTR_ERR(tfm); } @@ -430,21 +429,18 @@ int s3fwrn5_fw_download(struct s3fwrn5_fw_info *fw_info) crypto_free_shash(tfm); if (ret) { - dev_err(&fw_info->ndev->nfc_dev->dev, - "Cannot compute hash (code=%d)\n", ret); + dev_err(dev, "Cannot compute hash (code=%d)\n", ret); return ret; } /* Firmware update process */ - dev_info(&fw_info->ndev->nfc_dev->dev, - "Firmware update: %s\n", fw_info->fw_name); + dev_info(dev, "Firmware update: %s\n", fw_info->fw_name); ret = s3fwrn5_fw_enter_update_mode(fw_info, hash_data, SHA1_DIGEST_SIZE, fw_info->sig, fw_info->sig_size); if (ret < 0) { - dev_err(&fw_info->ndev->nfc_dev->dev, - "Unable to enter update mode\n"); + dev_err(dev, "Unable to enter update mode\n"); return ret; } @@ -452,21 +448,18 @@ int s3fwrn5_fw_download(struct s3fwrn5_fw_info *fw_info) ret = s3fwrn5_fw_update_sector(fw_info, fw_info->base_addr + off, fw->image + off); if (ret < 0) { - dev_err(&fw_info->ndev->nfc_dev->dev, - "Firmware update error (code=%d)\n", ret); + dev_err(dev, "Firmware update error (code=%d)\n", ret); return ret; } } ret = s3fwrn5_fw_complete_update_mode(fw_info); if (ret < 0) { - dev_err(&fw_info->ndev->nfc_dev->dev, - "Unable to complete update mode\n"); + dev_err(dev, "Unable to complete update mode\n"); return ret; } - dev_info(&fw_info->ndev->nfc_dev->dev, - "Firmware update: success\n"); + dev_info(dev, "Firmware update: success\n"); return ret; } diff --git a/drivers/nfc/s3fwrn5/nci.c b/drivers/nfc/s3fwrn5/nci.c index e374e670b36b..ca6828f55ba0 100644 --- a/drivers/nfc/s3fwrn5/nci.c +++ b/drivers/nfc/s3fwrn5/nci.c @@ -47,6 +47,7 @@ const struct nci_driver_ops s3fwrn5_nci_prop_ops[4] = { int s3fwrn5_nci_rf_configure(struct s3fwrn5_info *info, const char *fw_name) { + struct device *dev = &info->ndev->nfc_dev->dev; const struct firmware *fw; struct nci_prop_fw_cfg_cmd fw_cfg; struct nci_prop_set_rfreg_cmd set_rfreg; @@ -55,7 +56,7 @@ int s3fwrn5_nci_rf_configure(struct s3fwrn5_info *info, const char *fw_name) int i, len; int ret; - ret = request_firmware(&fw, fw_name, &info->ndev->nfc_dev->dev); + ret = request_firmware(&fw, fw_name, dev); if (ret < 0) return ret; @@ -77,13 +78,11 @@ int s3fwrn5_nci_rf_configure(struct s3fwrn5_info *info, const char *fw_name) /* Start rfreg configuration */ - dev_info(&info->ndev->nfc_dev->dev, - "rfreg configuration update: %s\n", fw_name); + dev_info(dev, "rfreg configuration update: %s\n", fw_name); ret = nci_prop_cmd(info->ndev, NCI_PROP_START_RFREG, 0, NULL); if (ret < 0) { - dev_err(&info->ndev->nfc_dev->dev, - "Unable to start rfreg update\n"); + dev_err(dev, "Unable to start rfreg update\n"); goto out; } @@ -97,8 +96,7 @@ int s3fwrn5_nci_rf_configure(struct s3fwrn5_info *info, const char *fw_name) ret = nci_prop_cmd(info->ndev, NCI_PROP_SET_RFREG, len+1, (__u8 *)&set_rfreg); if (ret < 0) { - dev_err(&info->ndev->nfc_dev->dev, - "rfreg update error (code=%d)\n", ret); + dev_err(dev, "rfreg update error (code=%d)\n", ret); goto out; } set_rfreg.index++; @@ -110,13 +108,11 @@ int s3fwrn5_nci_rf_configure(struct s3fwrn5_info *info, const char *fw_name) ret = nci_prop_cmd(info->ndev, NCI_PROP_STOP_RFREG, sizeof(stop_rfreg), (__u8 *)&stop_rfreg); if (ret < 0) { - dev_err(&info->ndev->nfc_dev->dev, - "Unable to stop rfreg update\n"); + dev_err(dev, "Unable to stop rfreg update\n"); goto out; } - dev_info(&info->ndev->nfc_dev->dev, - "rfreg configuration update: success\n"); + dev_info(dev, "rfreg configuration update: success\n"); out: release_firmware(fw); return ret; diff --git a/drivers/nfc/st-nci/i2c.c b/drivers/nfc/st-nci/i2c.c index ccf6152ebb9f..cbd968f013c7 100644 --- a/drivers/nfc/st-nci/i2c.c +++ b/drivers/nfc/st-nci/i2c.c @@ -157,7 +157,6 @@ static int st_nci_i2c_read(struct st_nci_i2c_phy *phy, static irqreturn_t st_nci_irq_thread_fn(int irq, void *phy_id) { struct st_nci_i2c_phy *phy = phy_id; - struct i2c_client *client; struct sk_buff *skb = NULL; int r; @@ -166,9 +165,6 @@ static irqreturn_t st_nci_irq_thread_fn(int irq, void *phy_id) return IRQ_NONE; } - client = phy->i2c_dev; - dev_dbg(&client->dev, "IRQ\n"); - if (phy->ndlc->hard_fault) return IRQ_HANDLED; diff --git a/drivers/nfc/st-nci/ndlc.c b/drivers/nfc/st-nci/ndlc.c index e9dc313b333e..755460a73c0d 100644 --- a/drivers/nfc/st-nci/ndlc.c +++ b/drivers/nfc/st-nci/ndlc.c @@ -239,8 +239,6 @@ static void ndlc_t1_timeout(struct timer_list *t) { struct llt_ndlc *ndlc = from_timer(ndlc, t, t1_timer); - pr_debug("\n"); - schedule_work(&ndlc->sm_work); } @@ -248,8 +246,6 @@ static void ndlc_t2_timeout(struct timer_list *t) { struct llt_ndlc *ndlc = from_timer(ndlc, t, t2_timer); - pr_debug("\n"); - schedule_work(&ndlc->sm_work); } diff --git a/drivers/nfc/st-nci/se.c b/drivers/nfc/st-nci/se.c index 5fd89f72969d..7764b1a4c3cf 100644 --- a/drivers/nfc/st-nci/se.c +++ b/drivers/nfc/st-nci/se.c @@ -638,8 +638,6 @@ int st_nci_se_io(struct nci_dev *ndev, u32 se_idx, { struct st_nci_info *info = nci_get_drvdata(ndev); - pr_debug("\n"); - switch (se_idx) { case ST_NCI_ESE_HOST_ID: info->se_info.cb = cb; @@ -671,8 +669,6 @@ static void st_nci_se_wt_timeout(struct timer_list *t) u8 param = 0x01; struct st_nci_info *info = from_timer(info, t, se_info.bwi_timer); - pr_debug("\n"); - info->se_info.bwi_active = false; if (!info->se_info.xch_error) { @@ -692,8 +688,6 @@ static void st_nci_se_activation_timeout(struct timer_list *t) struct st_nci_info *info = from_timer(info, t, se_info.se_active_timer); - pr_debug("\n"); - info->se_info.se_active = false; complete(&info->se_info.req_completion); diff --git a/drivers/nfc/st-nci/spi.c b/drivers/nfc/st-nci/spi.c index 0875b773fb41..4e723992e74c 100644 --- a/drivers/nfc/st-nci/spi.c +++ b/drivers/nfc/st-nci/spi.c @@ -169,7 +169,6 @@ static int st_nci_spi_read(struct st_nci_spi_phy *phy, static irqreturn_t st_nci_irq_thread_fn(int irq, void *phy_id) { struct st_nci_spi_phy *phy = phy_id; - struct spi_device *dev; struct sk_buff *skb = NULL; int r; @@ -178,9 +177,6 @@ static irqreturn_t st_nci_irq_thread_fn(int irq, void *phy_id) return IRQ_NONE; } - dev = phy->spi_dev; - dev_dbg(&dev->dev, "IRQ\n"); - if (phy->ndlc->hard_fault) return IRQ_HANDLED; diff --git a/drivers/nfc/st21nfca/i2c.c b/drivers/nfc/st21nfca/i2c.c index 279d88128b2e..f126ce96a7df 100644 --- a/drivers/nfc/st21nfca/i2c.c +++ b/drivers/nfc/st21nfca/i2c.c @@ -421,7 +421,6 @@ static int st21nfca_hci_i2c_read(struct st21nfca_i2c_phy *phy, static irqreturn_t st21nfca_hci_irq_thread_fn(int irq, void *phy_id) { struct st21nfca_i2c_phy *phy = phy_id; - struct i2c_client *client; int r; @@ -430,9 +429,6 @@ static irqreturn_t st21nfca_hci_irq_thread_fn(int irq, void *phy_id) return IRQ_NONE; } - client = phy->i2c_dev; - dev_dbg(&client->dev, "IRQ\n"); - if (phy->hard_fault != 0) return IRQ_HANDLED; diff --git a/drivers/nfc/st21nfca/se.c b/drivers/nfc/st21nfca/se.c index c8bdf078d111..a43fc4117fa5 100644 --- a/drivers/nfc/st21nfca/se.c +++ b/drivers/nfc/st21nfca/se.c @@ -257,8 +257,6 @@ static void st21nfca_se_wt_timeout(struct timer_list *t) struct st21nfca_hci_info *info = from_timer(info, t, se_info.bwi_timer); - pr_debug("\n"); - info->se_info.bwi_active = false; if (!info->se_info.xch_error) { @@ -278,8 +276,6 @@ static void st21nfca_se_activation_timeout(struct timer_list *t) struct st21nfca_hci_info *info = from_timer(info, t, se_info.se_active_timer); - pr_debug("\n"); - info->se_info.se_active = false; complete(&info->se_info.req_completion); diff --git a/drivers/nfc/trf7970a.c b/drivers/nfc/trf7970a.c index 8890fcd59c39..29ca9c328df2 100644 --- a/drivers/nfc/trf7970a.c +++ b/drivers/nfc/trf7970a.c @@ -2170,8 +2170,6 @@ static int trf7970a_suspend(struct device *dev) struct spi_device *spi = to_spi_device(dev); struct trf7970a *trf = spi_get_drvdata(spi); - dev_dbg(dev, "Suspend\n"); - mutex_lock(&trf->lock); trf7970a_shutdown(trf); @@ -2187,8 +2185,6 @@ static int trf7970a_resume(struct device *dev) struct trf7970a *trf = spi_get_drvdata(spi); int ret; - dev_dbg(dev, "Resume\n"); - mutex_lock(&trf->lock); ret = trf7970a_startup(trf); @@ -2206,8 +2202,6 @@ static int trf7970a_pm_runtime_suspend(struct device *dev) struct trf7970a *trf = spi_get_drvdata(spi); int ret; - dev_dbg(dev, "Runtime suspend\n"); - mutex_lock(&trf->lock); ret = trf7970a_power_down(trf); @@ -2223,8 +2217,6 @@ static int trf7970a_pm_runtime_resume(struct device *dev) struct trf7970a *trf = spi_get_drvdata(spi); int ret; - dev_dbg(dev, "Runtime resume\n"); - ret = trf7970a_power_up(trf); if (!ret) pm_runtime_mark_last_busy(dev); diff --git a/drivers/pcmcia/pcmcia_cis.c b/drivers/pcmcia/pcmcia_cis.c index d2d0ed4b27c8..f650e19a315c 100644 --- a/drivers/pcmcia/pcmcia_cis.c +++ b/drivers/pcmcia/pcmcia_cis.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include @@ -398,7 +399,6 @@ static int pcmcia_do_get_mac(struct pcmcia_device *p_dev, tuple_t *tuple, void *priv) { struct net_device *dev = priv; - int i; if (tuple->TupleData[0] != CISTPL_FUNCE_LAN_NODE_ID) return -EINVAL; @@ -412,8 +412,7 @@ static int pcmcia_do_get_mac(struct pcmcia_device *p_dev, tuple_t *tuple, dev_warn(&p_dev->dev, "Invalid header for LAN_NODE_ID\n"); return -EINVAL; } - for (i = 0; i < 6; i++) - dev->dev_addr[i] = tuple->TupleData[i+2]; + eth_hw_addr_set(dev, &tuple->TupleData[2]); return 0; } diff --git a/drivers/s390/net/lcs.c b/drivers/s390/net/lcs.c index c18fd48e02b6..2a6479740600 100644 --- a/drivers/s390/net/lcs.c +++ b/drivers/s390/net/lcs.c @@ -2162,7 +2162,7 @@ lcs_new_device(struct ccwgroup_device *ccwgdev) card->dev->ml_priv = card; card->dev->netdev_ops = &lcs_netdev_ops; card->dev->dev_port = card->portno; - memcpy(card->dev->dev_addr, card->mac, LCS_MAC_LENGTH); + eth_hw_addr_set(card->dev, card->mac); #ifdef CONFIG_IP_MULTICAST if (!lcs_check_multicast_support(card)) card->dev->netdev_ops = &lcs_mc_netdev_ops; diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index e9807d2996a9..15999a816054 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -4375,7 +4375,7 @@ static int qeth_setadpparms_change_macaddr_cb(struct qeth_card *card, !(adp_cmd->hdr.flags & QETH_SETADP_FLAGS_VIRTUAL_MAC)) return -EADDRNOTAVAIL; - ether_addr_copy(card->dev->dev_addr, adp_cmd->data.change_addr.addr); + eth_hw_addr_set(card->dev, adp_cmd->data.change_addr.addr); return 0; } @@ -5046,7 +5046,7 @@ int qeth_vm_request_mac(struct qeth_card *card) QETH_CARD_TEXT(card, 2, "badmac"); QETH_CARD_HEX(card, 2, response->mac, ETH_ALEN); } else { - ether_addr_copy(card->dev->dev_addr, response->mac); + eth_hw_addr_set(card->dev, response->mac); } out: diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index dc6c00768d91..5b6187f2d9d6 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -71,7 +71,7 @@ static int qeth_l2_send_setdelmac_cb(struct qeth_card *card, return qeth_l2_setdelmac_makerc(card, cmd->hdr.return_code); } -static int qeth_l2_send_setdelmac(struct qeth_card *card, __u8 *mac, +static int qeth_l2_send_setdelmac(struct qeth_card *card, const __u8 *mac, enum qeth_ipa_cmds ipacmd) { struct qeth_ipa_cmd *cmd; @@ -88,7 +88,7 @@ static int qeth_l2_send_setdelmac(struct qeth_card *card, __u8 *mac, return qeth_send_ipa_cmd(card, iob, qeth_l2_send_setdelmac_cb, NULL); } -static int qeth_l2_send_setmac(struct qeth_card *card, __u8 *mac) +static int qeth_l2_send_setmac(struct qeth_card *card, const __u8 *mac) { int rc; @@ -377,7 +377,7 @@ static int qeth_l2_set_mac_address(struct net_device *dev, void *p) if (rc) return rc; ether_addr_copy(old_addr, dev->dev_addr); - ether_addr_copy(dev->dev_addr, addr->sa_data); + eth_hw_addr_set(dev, addr->sa_data); if (card->info.dev_addr_is_registered) qeth_l2_remove_mac(card, old_addr); diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index 6fd3e288f059..e6e921310211 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -913,8 +913,7 @@ static int qeth_l3_iqd_read_initial_mac_cb(struct qeth_card *card, if (!is_valid_ether_addr(cmd->data.create_destroy_addr.mac_addr)) return -EADDRNOTAVAIL; - ether_addr_copy(card->dev->dev_addr, - cmd->data.create_destroy_addr.mac_addr); + eth_hw_addr_set(card->dev, cmd->data.create_destroy_addr.mac_addr); return 0; } diff --git a/drivers/soc/fsl/Kconfig b/drivers/soc/fsl/Kconfig index 4df32bc4c7a6..07d52cafbb31 100644 --- a/drivers/soc/fsl/Kconfig +++ b/drivers/soc/fsl/Kconfig @@ -24,6 +24,7 @@ config FSL_MC_DPIO tristate "QorIQ DPAA2 DPIO driver" depends on FSL_MC_BUS select SOC_BUS + select DIMLIB help Driver for the DPAA2 DPIO object. A DPIO provides queue and buffer management facilities for software to interact with diff --git a/drivers/soc/fsl/dpio/dpio-cmd.h b/drivers/soc/fsl/dpio/dpio-cmd.h index e13fd3ac1939..2fbcb78cdaaf 100644 --- a/drivers/soc/fsl/dpio/dpio-cmd.h +++ b/drivers/soc/fsl/dpio/dpio-cmd.h @@ -46,6 +46,9 @@ struct dpio_rsp_get_attr { __le64 qbman_portal_ci_addr; /* cmd word 3 */ __le32 qbman_version; + __le32 pad1; + /* cmd word 4 */ + __le32 clk; }; struct dpio_stashing_dest { diff --git a/drivers/soc/fsl/dpio/dpio-driver.c b/drivers/soc/fsl/dpio/dpio-driver.c index 7f397b4ad878..dd948889eeab 100644 --- a/drivers/soc/fsl/dpio/dpio-driver.c +++ b/drivers/soc/fsl/dpio/dpio-driver.c @@ -162,6 +162,7 @@ static int dpaa2_dpio_probe(struct fsl_mc_device *dpio_dev) goto err_get_attr; } desc.qman_version = dpio_attrs.qbman_version; + desc.qman_clk = dpio_attrs.clk; err = dpio_enable(dpio_dev->mc_io, 0, dpio_dev->mc_handle); if (err) { diff --git a/drivers/soc/fsl/dpio/dpio-service.c b/drivers/soc/fsl/dpio/dpio-service.c index 7351f3030550..3fd0d0840287 100644 --- a/drivers/soc/fsl/dpio/dpio-service.c +++ b/drivers/soc/fsl/dpio/dpio-service.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include "dpio.h" @@ -28,6 +29,14 @@ struct dpaa2_io { spinlock_t lock_notifications; struct list_head notifications; struct device *dev; + + /* Net DIM */ + struct dim rx_dim; + /* protect against concurrent Net DIM updates */ + spinlock_t dim_lock; + u16 event_ctr; + u64 bytes; + u64 frames; }; struct dpaa2_io_store { @@ -100,6 +109,17 @@ struct dpaa2_io *dpaa2_io_service_select(int cpu) } EXPORT_SYMBOL_GPL(dpaa2_io_service_select); +static void dpaa2_io_dim_work(struct work_struct *w) +{ + struct dim *dim = container_of(w, struct dim, work); + struct dim_cq_moder moder = + net_dim_get_rx_moderation(dim->mode, dim->profile_ix); + struct dpaa2_io *d = container_of(dim, struct dpaa2_io, rx_dim); + + dpaa2_io_set_irq_coalescing(d, moder.usec); + dim->state = DIM_START_MEASURE; +} + /** * dpaa2_io_create() - create a dpaa2_io object. * @desc: the dpaa2_io descriptor @@ -114,6 +134,7 @@ struct dpaa2_io *dpaa2_io_create(const struct dpaa2_io_desc *desc, struct device *dev) { struct dpaa2_io *obj = kmalloc(sizeof(*obj), GFP_KERNEL); + u32 qman_256_cycles_per_ns; if (!obj) return NULL; @@ -127,7 +148,15 @@ struct dpaa2_io *dpaa2_io_create(const struct dpaa2_io_desc *desc, obj->dpio_desc = *desc; obj->swp_desc.cena_bar = obj->dpio_desc.regs_cena; obj->swp_desc.cinh_bar = obj->dpio_desc.regs_cinh; + obj->swp_desc.qman_clk = obj->dpio_desc.qman_clk; obj->swp_desc.qman_version = obj->dpio_desc.qman_version; + + /* Compute how many 256 QBMAN cycles fit into one ns. This is because + * the interrupt timeout period register needs to be specified in QBMAN + * clock cycles in increments of 256. + */ + qman_256_cycles_per_ns = 256000 / (obj->swp_desc.qman_clk / 1000000); + obj->swp_desc.qman_256_cycles_per_ns = qman_256_cycles_per_ns; obj->swp = qbman_swp_init(&obj->swp_desc); if (!obj->swp) { @@ -138,6 +167,7 @@ struct dpaa2_io *dpaa2_io_create(const struct dpaa2_io_desc *desc, INIT_LIST_HEAD(&obj->node); spin_lock_init(&obj->lock_mgmt_cmd); spin_lock_init(&obj->lock_notifications); + spin_lock_init(&obj->dim_lock); INIT_LIST_HEAD(&obj->notifications); /* For now only enable DQRR interrupts */ @@ -155,6 +185,12 @@ struct dpaa2_io *dpaa2_io_create(const struct dpaa2_io_desc *desc, obj->dev = dev; + memset(&obj->rx_dim, 0, sizeof(obj->rx_dim)); + INIT_WORK(&obj->rx_dim.work, dpaa2_io_dim_work); + obj->event_ctr = 0; + obj->bytes = 0; + obj->frames = 0; + return obj; } @@ -194,6 +230,8 @@ irqreturn_t dpaa2_io_irq(struct dpaa2_io *obj) struct qbman_swp *swp; u32 status; + obj->event_ctr++; + swp = obj->swp; status = qbman_swp_interrupt_read_status(swp); if (!status) @@ -779,3 +817,82 @@ int dpaa2_io_query_bp_count(struct dpaa2_io *d, u16 bpid, u32 *num) return 0; } EXPORT_SYMBOL_GPL(dpaa2_io_query_bp_count); + +/** + * dpaa2_io_set_irq_coalescing() - Set new IRQ coalescing values + * @d: the given DPIO object + * @irq_holdoff: interrupt holdoff (timeout) period in us + * + * Return 0 for success, or negative error code on error. + */ +int dpaa2_io_set_irq_coalescing(struct dpaa2_io *d, u32 irq_holdoff) +{ + struct qbman_swp *swp = d->swp; + + return qbman_swp_set_irq_coalescing(swp, swp->dqrr.dqrr_size - 1, + irq_holdoff); +} +EXPORT_SYMBOL(dpaa2_io_set_irq_coalescing); + +/** + * dpaa2_io_get_irq_coalescing() - Get the current IRQ coalescing parameters + * @d: the given DPIO object + * @irq_holdoff: interrupt holdoff (timeout) period in us + */ +void dpaa2_io_get_irq_coalescing(struct dpaa2_io *d, u32 *irq_holdoff) +{ + struct qbman_swp *swp = d->swp; + + qbman_swp_get_irq_coalescing(swp, NULL, irq_holdoff); +} +EXPORT_SYMBOL(dpaa2_io_get_irq_coalescing); + +/** + * dpaa2_io_set_adaptive_coalescing() - Enable/disable adaptive coalescing + * @d: the given DPIO object + * @use_adaptive_rx_coalesce: adaptive coalescing state + */ +void dpaa2_io_set_adaptive_coalescing(struct dpaa2_io *d, + int use_adaptive_rx_coalesce) +{ + d->swp->use_adaptive_rx_coalesce = use_adaptive_rx_coalesce; +} +EXPORT_SYMBOL(dpaa2_io_set_adaptive_coalescing); + +/** + * dpaa2_io_get_adaptive_coalescing() - Query adaptive coalescing state + * @d: the given DPIO object + * + * Return 1 when adaptive coalescing is enabled on the DPIO object and 0 + * otherwise. + */ +int dpaa2_io_get_adaptive_coalescing(struct dpaa2_io *d) +{ + return d->swp->use_adaptive_rx_coalesce; +} +EXPORT_SYMBOL(dpaa2_io_get_adaptive_coalescing); + +/** + * dpaa2_io_update_net_dim() - Update Net DIM + * @d: the given DPIO object + * @frames: how many frames have been dequeued by the user since the last call + * @bytes: how many bytes have been dequeued by the user since the last call + */ +void dpaa2_io_update_net_dim(struct dpaa2_io *d, __u64 frames, __u64 bytes) +{ + struct dim_sample dim_sample = {}; + + if (!d->swp->use_adaptive_rx_coalesce) + return; + + spin_lock(&d->dim_lock); + + d->bytes += bytes; + d->frames += frames; + + dim_update_sample(d->event_ctr, d->frames, d->bytes, &dim_sample); + net_dim(&d->rx_dim, dim_sample); + + spin_unlock(&d->dim_lock); +} +EXPORT_SYMBOL(dpaa2_io_update_net_dim); diff --git a/drivers/soc/fsl/dpio/dpio.c b/drivers/soc/fsl/dpio/dpio.c index af74c597a675..8ed606ffaac5 100644 --- a/drivers/soc/fsl/dpio/dpio.c +++ b/drivers/soc/fsl/dpio/dpio.c @@ -162,6 +162,7 @@ int dpio_get_attributes(struct fsl_mc_io *mc_io, attr->qbman_portal_ci_offset = le64_to_cpu(dpio_rsp->qbman_portal_ci_addr); attr->qbman_version = le32_to_cpu(dpio_rsp->qbman_version); + attr->clk = le32_to_cpu(dpio_rsp->clk); return 0; } diff --git a/drivers/soc/fsl/dpio/dpio.h b/drivers/soc/fsl/dpio/dpio.h index da06f7258098..7fda44f0d7f4 100644 --- a/drivers/soc/fsl/dpio/dpio.h +++ b/drivers/soc/fsl/dpio/dpio.h @@ -59,6 +59,7 @@ int dpio_disable(struct fsl_mc_io *mc_io, * @num_priorities: Number of priorities for the notification channel (1-8); * relevant only if 'channel_mode = DPIO_LOCAL_CHANNEL' * @qbman_version: QBMAN version + * @clk: QBMAN clock frequency value in Hz */ struct dpio_attr { int id; @@ -68,6 +69,7 @@ struct dpio_attr { enum dpio_channel_mode channel_mode; u8 num_priorities; u32 qbman_version; + u32 clk; }; int dpio_get_attributes(struct fsl_mc_io *mc_io, diff --git a/drivers/soc/fsl/dpio/qbman-portal.c b/drivers/soc/fsl/dpio/qbman-portal.c index f13da4d7d1c5..3474bf5f88d5 100644 --- a/drivers/soc/fsl/dpio/qbman-portal.c +++ b/drivers/soc/fsl/dpio/qbman-portal.c @@ -29,6 +29,7 @@ #define QBMAN_CINH_SWP_EQCR_AM_RT 0x980 #define QBMAN_CINH_SWP_RCR_AM_RT 0x9c0 #define QBMAN_CINH_SWP_DQPI 0xa00 +#define QBMAN_CINH_SWP_DQRR_ITR 0xa80 #define QBMAN_CINH_SWP_DCAP 0xac0 #define QBMAN_CINH_SWP_SDQCR 0xb00 #define QBMAN_CINH_SWP_EQCR_AM_RT2 0xb40 @@ -38,6 +39,7 @@ #define QBMAN_CINH_SWP_IER 0xe40 #define QBMAN_CINH_SWP_ISDR 0xe80 #define QBMAN_CINH_SWP_IIR 0xec0 +#define QBMAN_CINH_SWP_ITPR 0xf40 /* CENA register offsets */ #define QBMAN_CENA_SWP_EQCR(n) (0x000 + ((u32)(n) << 6)) @@ -355,6 +357,9 @@ struct qbman_swp *qbman_swp_init(const struct qbman_swp_desc *d) & p->eqcr.pi_ci_mask; p->eqcr.available = p->eqcr.pi_ring_size; + /* Initialize the software portal with a irq timeout period of 0us */ + qbman_swp_set_irq_coalescing(p, p->dqrr.dqrr_size - 1, 0); + return p; } @@ -1796,3 +1801,56 @@ u32 qbman_bp_info_num_free_bufs(struct qbman_bp_query_rslt *a) { return le32_to_cpu(a->fill); } + +/** + * qbman_swp_set_irq_coalescing() - Set new IRQ coalescing values + * @p: the software portal object + * @irq_threshold: interrupt threshold + * @irq_holdoff: interrupt holdoff (timeout) period in us + * + * Return 0 for success, or negative error code on error. + */ +int qbman_swp_set_irq_coalescing(struct qbman_swp *p, u32 irq_threshold, + u32 irq_holdoff) +{ + u32 itp, max_holdoff; + + /* Convert irq_holdoff value from usecs to 256 QBMAN clock cycles + * increments. This depends on the QBMAN internal frequency. + */ + itp = (irq_holdoff * 1000) / p->desc->qman_256_cycles_per_ns; + if (itp > 4096) { + max_holdoff = (p->desc->qman_256_cycles_per_ns * 4096) / 1000; + pr_err("irq_holdoff must be <= %uus\n", max_holdoff); + return -EINVAL; + } + + if (irq_threshold >= p->dqrr.dqrr_size) { + pr_err("irq_threshold must be < %u\n", p->dqrr.dqrr_size - 1); + return -EINVAL; + } + + p->irq_threshold = irq_threshold; + p->irq_holdoff = irq_holdoff; + + qbman_write_register(p, QBMAN_CINH_SWP_DQRR_ITR, irq_threshold); + qbman_write_register(p, QBMAN_CINH_SWP_ITPR, itp); + + return 0; +} + +/** + * qbman_swp_get_irq_coalescing() - Get the current IRQ coalescing parameters + * @p: the software portal object + * @irq_threshold: interrupt threshold (an IRQ is generated when there are more + * DQRR entries in the portal than the threshold) + * @irq_holdoff: interrupt holdoff (timeout) period in us + */ +void qbman_swp_get_irq_coalescing(struct qbman_swp *p, u32 *irq_threshold, + u32 *irq_holdoff) +{ + if (irq_threshold) + *irq_threshold = p->irq_threshold; + if (irq_holdoff) + *irq_holdoff = p->irq_holdoff; +} diff --git a/drivers/soc/fsl/dpio/qbman-portal.h b/drivers/soc/fsl/dpio/qbman-portal.h index c7c2225b7d91..b23883dd2725 100644 --- a/drivers/soc/fsl/dpio/qbman-portal.h +++ b/drivers/soc/fsl/dpio/qbman-portal.h @@ -24,6 +24,8 @@ struct qbman_swp_desc { void *cena_bar; /* Cache-enabled portal base address */ void __iomem *cinh_bar; /* Cache-inhibited portal base address */ u32 qman_version; + u32 qman_clk; + u32 qman_256_cycles_per_ns; }; #define QBMAN_SWP_INTERRUPT_EQRI 0x01 @@ -156,6 +158,11 @@ struct qbman_swp { } eqcr; spinlock_t access_spinlock; + + /* Interrupt coalescing */ + u32 irq_threshold; + u32 irq_holdoff; + int use_adaptive_rx_coalesce; }; /* Function pointers */ @@ -648,4 +655,10 @@ static inline const struct dpaa2_dq *qbman_swp_dqrr_next(struct qbman_swp *s) return qbman_swp_dqrr_next_ptr(s); } +int qbman_swp_set_irq_coalescing(struct qbman_swp *p, u32 irq_threshold, + u32 irq_holdoff); + +void qbman_swp_get_irq_coalescing(struct qbman_swp *p, u32 *irq_threshold, + u32 *irq_holdoff); + #endif /* __FSL_QBMAN_PORTAL_H */ diff --git a/drivers/usb/gadget/function/f_phonet.c b/drivers/usb/gadget/function/f_phonet.c index 0b468f5d55bc..068ed8417e5a 100644 --- a/drivers/usb/gadget/function/f_phonet.c +++ b/drivers/usb/gadget/function/f_phonet.c @@ -267,6 +267,8 @@ static const struct net_device_ops pn_netdev_ops = { static void pn_net_setup(struct net_device *dev) { + const u8 addr = PN_MEDIA_USB; + dev->features = 0; dev->type = ARPHRD_PHONET; dev->flags = IFF_POINTOPOINT | IFF_NOARP; @@ -274,8 +276,9 @@ static void pn_net_setup(struct net_device *dev) dev->min_mtu = PHONET_MIN_MTU; dev->max_mtu = PHONET_MAX_MTU; dev->hard_header_len = 1; - dev->dev_addr[0] = PN_MEDIA_USB; dev->addr_len = 1; + dev_addr_set(dev, &addr); + dev->tx_queue_len = 1; dev->netdev_ops = &pn_netdev_ops; diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h index c7fa4a3498fe..254b165f2b44 100644 --- a/include/linux/dsa/8021q.h +++ b/include/linux/dsa/8021q.h @@ -9,6 +9,7 @@ #include struct dsa_switch; +struct dsa_port; struct sk_buff; struct net_device; @@ -45,9 +46,9 @@ void dsa_tag_8021q_bridge_tx_fwd_unoffload(struct dsa_switch *ds, int port, u16 dsa_8021q_bridge_tx_fwd_offload_vid(int bridge_num); -u16 dsa_8021q_tx_vid(struct dsa_switch *ds, int port); +u16 dsa_tag_8021q_tx_vid(const struct dsa_port *dp); -u16 dsa_8021q_rx_vid(struct dsa_switch *ds, int port); +u16 dsa_tag_8021q_rx_vid(const struct dsa_port *dp); int dsa_8021q_rx_switch_id(u16 vid); diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index e75116f48cd1..2ad71cc90b37 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -29,6 +29,7 @@ struct device; struct fwnode_handle; int eth_platform_get_mac_address(struct device *dev, u8 *mac_addr); +int platform_get_ethdev_address(struct device *dev, struct net_device *netdev); unsigned char *arch_get_platform_mac_address(void); int nvmem_get_mac_address(struct device *dev, void *addrbuf); int device_get_mac_address(struct device *dev, char *addr); @@ -233,8 +234,6 @@ static inline void eth_random_addr(u8 *addr) addr[0] |= 0x02; /* set local assignment bit (IEEE802) */ } -#define random_ether_addr(addr) eth_random_addr(addr) - /** * eth_broadcast_addr - Assign broadcast address * @addr: Pointer to a six-byte array containing the Ethernet address @@ -268,8 +267,11 @@ static inline void eth_zero_addr(u8 *addr) */ static inline void eth_hw_addr_random(struct net_device *dev) { + u8 addr[ETH_ALEN]; + + eth_random_addr(addr); + __dev_addr_set(dev, addr, ETH_ALEN); dev->addr_assign_type = NET_ADDR_RANDOM; - eth_random_addr(dev->dev_addr); } /** @@ -549,6 +551,27 @@ static inline unsigned long compare_ether_header(const void *a, const void *b) #endif } +/** + * eth_hw_addr_gen - Generate and assign Ethernet address to a port + * @dev: pointer to port's net_device structure + * @base_addr: base Ethernet address + * @id: offset to add to the base address + * + * Generate a MAC address using a base address and an offset and assign it + * to a net_device. Commonly used by switch drivers which need to compute + * addresses for all their ports. addr_assign_type is not changed. + */ +static inline void eth_hw_addr_gen(struct net_device *dev, const u8 *base_addr, + unsigned int id) +{ + u64 u = ether_addr_to_u64(base_addr); + u8 addr[ETH_ALEN]; + + u += id; + u64_to_ether_addr(u, addr); + eth_hw_addr_set(dev, addr); +} + /** * eth_skb_pad - Pad buffer to mininum number of octets for Ethernet frame * @skb: Buffer to pad diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 64bf910e56d8..11d7af260f20 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1988,6 +1988,44 @@ int ieee80211_get_vht_max_nss(struct ieee80211_vht_cap *cap, int mcs, bool ext_nss_bw_capable, unsigned int max_vht_nss); +/** + * enum ieee80211_ap_reg_power - regulatory power for a Access Point + * + * @IEEE80211_REG_UNSET_AP: Access Point has no regulatory power mode + * @IEEE80211_REG_LPI: Indoor Access Point + * @IEEE80211_REG_SP: Standard power Access Point + * @IEEE80211_REG_VLP: Very low power Access Point + * @IEEE80211_REG_AP_POWER_AFTER_LAST: internal + * @IEEE80211_REG_AP_POWER_MAX: maximum value + */ +enum ieee80211_ap_reg_power { + IEEE80211_REG_UNSET_AP, + IEEE80211_REG_LPI_AP, + IEEE80211_REG_SP_AP, + IEEE80211_REG_VLP_AP, + IEEE80211_REG_AP_POWER_AFTER_LAST, + IEEE80211_REG_AP_POWER_MAX = + IEEE80211_REG_AP_POWER_AFTER_LAST - 1, +}; + +/** + * enum ieee80211_client_reg_power - regulatory power for a client + * + * @IEEE80211_REG_UNSET_CLIENT: Client has no regulatory power mode + * @IEEE80211_REG_DEFAULT_CLIENT: Default Client + * @IEEE80211_REG_SUBORDINATE_CLIENT: Subordinate Client + * @IEEE80211_REG_CLIENT_POWER_AFTER_LAST: internal + * @IEEE80211_REG_CLIENT_POWER_MAX: maximum value + */ +enum ieee80211_client_reg_power { + IEEE80211_REG_UNSET_CLIENT, + IEEE80211_REG_DEFAULT_CLIENT, + IEEE80211_REG_SUBORDINATE_CLIENT, + IEEE80211_REG_CLIENT_POWER_AFTER_LAST, + IEEE80211_REG_CLIENT_POWER_MAX = + IEEE80211_REG_CLIENT_POWER_AFTER_LAST - 1, +}; + /* 802.11ax HE MAC capabilities */ #define IEEE80211_HE_MAC_CAP0_HTC_HE 0x01 #define IEEE80211_HE_MAC_CAP0_TWT_REQ 0x02 diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 66eaf0aa7f69..347167c18802 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -577,7 +577,9 @@ struct mlx5_init_seg { __be32 rsvd1[120]; __be32 initializing; struct health_buffer health; - __be32 rsvd2[880]; + __be32 rsvd2[878]; + __be32 cmd_exec_to; + __be32 cmd_q_init_to; __be32 internal_timer_h; __be32 internal_timer_l; __be32 rsvd3[2]; @@ -1183,6 +1185,7 @@ enum mlx5_cap_type { MLX5_CAP_DEV_EVENT = 0x14, MLX5_CAP_IPSEC, MLX5_CAP_GENERAL_2 = 0x20, + MLX5_CAP_PORT_SELECTION = 0x25, /* NUM OF CAP Types */ MLX5_CAP_NUM }; @@ -1340,6 +1343,20 @@ enum mlx5_qcam_feature_groups { MLX5_GET(e_switch_cap, \ mdev->caps.hca[MLX5_CAP_ESWITCH]->max, cap) +#define MLX5_CAP_PORT_SELECTION(mdev, cap) \ + MLX5_GET(port_selection_cap, \ + mdev->caps.hca[MLX5_CAP_PORT_SELECTION]->cur, cap) + +#define MLX5_CAP_PORT_SELECTION_MAX(mdev, cap) \ + MLX5_GET(port_selection_cap, \ + mdev->caps.hca[MLX5_CAP_PORT_SELECTION]->max, cap) + +#define MLX5_CAP_FLOWTABLE_PORT_SELECTION(mdev, cap) \ + MLX5_CAP_PORT_SELECTION(mdev, flow_table_properties_port_selection.cap) + +#define MLX5_CAP_FLOWTABLE_PORT_SELECTION_MAX(mdev, cap) \ + MLX5_CAP_PORT_SELECTION_MAX(mdev, flow_table_properties_port_selection.cap) + #define MLX5_CAP_ODP(mdev, cap)\ MLX5_GET(odp_cap, mdev->caps.hca[MLX5_CAP_ODP]->cur, cap) diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index fd9581d705a5..3f4c0f2314a5 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -66,10 +66,6 @@ enum { }; enum { - /* one minute for the sake of bringup. Generally, commands must always - * complete and we may need to increase this timeout value - */ - MLX5_CMD_TIMEOUT_MSEC = 60 * 1000, MLX5_CMD_WQ_MAX_NAME = 32, }; @@ -156,6 +152,7 @@ enum { MLX5_REG_MIRC = 0x9162, MLX5_REG_SBCAM = 0xB01F, MLX5_REG_RESOURCE_DUMP = 0xC000, + MLX5_REG_DTOR = 0xC00E, }; enum mlx5_qpts_trust_state { @@ -754,6 +751,7 @@ struct mlx5_core_dev { u32 qcam[MLX5_ST_SZ_DW(qcam_reg)]; u8 embedded_cpu; } caps; + struct mlx5_timeouts *timeouts; u64 sys_image_guid; phys_addr_t iseg_base; struct mlx5_init_seg __iomem *iseg; @@ -1244,6 +1242,16 @@ static inline int mlx5_core_native_port_num(struct mlx5_core_dev *dev) return MLX5_CAP_GEN(dev, native_port_num); } +static inline int mlx5_get_dev_index(struct mlx5_core_dev *dev) +{ + int idx = MLX5_CAP_GEN(dev, native_port_num); + + if (idx >= 1 && idx <= MLX5_MAX_PORTS) + return idx - 1; + else + return PCI_FUNC(dev->pdev->devfn); +} + enum { MLX5_TRIGGERED_CMD_COMP = (u64)1 << 32, }; @@ -1252,11 +1260,12 @@ static inline bool mlx5_is_roce_init_enabled(struct mlx5_core_dev *dev) { struct devlink *devlink = priv_to_devlink(dev); union devlink_param_value val; + int err; - devlink_param_driverinit_value_get(devlink, - DEVLINK_PARAM_GENERIC_ID_ENABLE_ROCE, - &val); - return val.vbool; + err = devlink_param_driverinit_value_get(devlink, + DEVLINK_PARAM_GENERIC_ID_ENABLE_ROCE, + &val); + return err ? MLX5_CAP_GEN(dev, roce) : val.vbool; } #endif /* MLX5_DRIVER_H */ diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 0106c67e8ccb..7a43fec63a35 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -83,6 +83,7 @@ enum mlx5_flow_namespace_type { MLX5_FLOW_NAMESPACE_RDMA_RX, MLX5_FLOW_NAMESPACE_RDMA_RX_KERNEL, MLX5_FLOW_NAMESPACE_RDMA_TX, + MLX5_FLOW_NAMESPACE_PORT_SEL, }; enum { @@ -97,6 +98,7 @@ enum { struct mlx5_pkt_reformat; struct mlx5_modify_hdr; +struct mlx5_flow_definer; struct mlx5_flow_table; struct mlx5_flow_group; struct mlx5_flow_namespace; @@ -257,6 +259,13 @@ struct mlx5_modify_hdr *mlx5_modify_header_alloc(struct mlx5_core_dev *dev, void *modify_actions); void mlx5_modify_header_dealloc(struct mlx5_core_dev *dev, struct mlx5_modify_hdr *modify_hdr); +struct mlx5_flow_definer * +mlx5_create_match_definer(struct mlx5_core_dev *dev, + enum mlx5_flow_namespace_type ns_type, u16 format_id, + u32 *match_mask); +void mlx5_destroy_match_definer(struct mlx5_core_dev *dev, + struct mlx5_flow_definer *definer); +int mlx5_get_match_definer_id(struct mlx5_flow_definer *definer); struct mlx5_pkt_reformat_params { int type; diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 993204a6c1a1..09e43019d877 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -94,6 +94,7 @@ enum { enum { MLX5_OBJ_TYPE_GENEVE_TLV_OPT = 0x000b, MLX5_OBJ_TYPE_VIRTIO_NET_Q = 0x000d, + MLX5_OBJ_TYPE_MATCH_DEFINER = 0x0018, MLX5_OBJ_TYPE_MKEY = 0xff01, MLX5_OBJ_TYPE_QP = 0xff02, MLX5_OBJ_TYPE_PSV = 0xff03, @@ -767,6 +768,18 @@ struct mlx5_ifc_flow_table_nic_cap_bits { u8 reserved_at_20c0[0x5f40]; }; +struct mlx5_ifc_port_selection_cap_bits { + u8 reserved_at_0[0x10]; + u8 port_select_flow_table[0x1]; + u8 reserved_at_11[0xf]; + + u8 reserved_at_20[0x1e0]; + + struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_port_selection; + + u8 reserved_at_400[0x7c00]; +}; + enum { MLX5_FDB_TO_VPORT_REG_C_0 = 0x01, MLX5_FDB_TO_VPORT_REG_C_1 = 0x02, @@ -1306,7 +1319,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 vhca_resource_manager[0x1]; u8 hca_cap_2[0x1]; - u8 reserved_at_21[0x2]; + u8 reserved_at_21[0x1]; + u8 dtor[0x1]; u8 event_on_vhca_state_teardown_request[0x1]; u8 event_on_vhca_state_in_use[0x1]; u8 event_on_vhca_state_active[0x1]; @@ -1514,7 +1528,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 uar_4k[0x1]; u8 reserved_at_241[0x9]; u8 uar_sz[0x6]; - u8 reserved_at_248[0x2]; + u8 port_selection_cap[0x1]; + u8 reserved_at_248[0x1]; u8 umem_uid_0[0x1]; u8 reserved_at_250[0x5]; u8 log_pg_sz[0x8]; @@ -1587,7 +1602,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 log_max_tis_per_sq[0x5]; u8 ext_stride_num_range[0x1]; - u8 reserved_at_3a1[0x2]; + u8 roce_rw_supported[0x1]; + u8 reserved_at_3a2[0x1]; u8 log_max_stride_sz_rq[0x5]; u8 reserved_at_3a8[0x3]; u8 log_min_stride_sz_rq[0x5]; @@ -1716,7 +1732,7 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 flex_parser_id_outer_first_mpls_over_gre[0x4]; u8 flex_parser_id_outer_first_mpls_over_udp_label[0x4]; - u8 reserved_at_6e0[0x10]; + u8 max_num_match_definer[0x10]; u8 sf_base_id[0x10]; u8 flex_parser_id_gtpu_dw_2[0x4]; @@ -1731,7 +1747,7 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_760[0x20]; u8 vhca_tunnel_commands[0x40]; - u8 reserved_at_7c0[0x40]; + u8 match_definer_format_supported[0x40]; }; struct mlx5_ifc_cmd_hca_cap_2_bits { @@ -1750,6 +1766,7 @@ enum mlx5_flow_destination_type { MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE = 0x1, MLX5_FLOW_DESTINATION_TYPE_TIR = 0x2, MLX5_FLOW_DESTINATION_TYPE_FLOW_SAMPLER = 0x6, + MLX5_FLOW_DESTINATION_TYPE_UPLINK = 0x8, MLX5_FLOW_DESTINATION_TYPE_PORT = 0x99, MLX5_FLOW_DESTINATION_TYPE_COUNTER = 0x100, @@ -2807,6 +2824,40 @@ struct mlx5_ifc_dropped_packet_logged_bits { u8 reserved_at_0[0xe0]; }; +struct mlx5_ifc_default_timeout_bits { + u8 to_multiplier[0x3]; + u8 reserved_at_3[0x9]; + u8 to_value[0x14]; +}; + +struct mlx5_ifc_dtor_reg_bits { + u8 reserved_at_0[0x20]; + + struct mlx5_ifc_default_timeout_bits pcie_toggle_to; + + u8 reserved_at_40[0x60]; + + struct mlx5_ifc_default_timeout_bits health_poll_to; + + struct mlx5_ifc_default_timeout_bits full_crdump_to; + + struct mlx5_ifc_default_timeout_bits fw_reset_to; + + struct mlx5_ifc_default_timeout_bits flush_on_err_to; + + struct mlx5_ifc_default_timeout_bits pci_sync_update_to; + + struct mlx5_ifc_default_timeout_bits tear_down_to; + + struct mlx5_ifc_default_timeout_bits fsm_reactivate_to; + + struct mlx5_ifc_default_timeout_bits reclaim_pages_to; + + struct mlx5_ifc_default_timeout_bits reclaim_vfs_pages_to; + + u8 reserved_at_1c0[0x40]; +}; + enum { MLX5_CQ_ERROR_SYNDROME_CQ_OVERRUN = 0x1, MLX5_CQ_ERROR_SYNDROME_CQ_ACCESS_VIOLATION_ERROR = 0x2, @@ -3128,6 +3179,7 @@ union mlx5_ifc_hca_cap_union_bits { struct mlx5_ifc_flow_table_nic_cap_bits flow_table_nic_cap; struct mlx5_ifc_flow_table_eswitch_cap_bits flow_table_eswitch_cap; struct mlx5_ifc_e_switch_cap_bits e_switch_cap; + struct mlx5_ifc_port_selection_cap_bits port_selection_cap; struct mlx5_ifc_vector_calc_cap_bits vector_calc_cap; struct mlx5_ifc_qos_cap_bits qos_cap; struct mlx5_ifc_debug_cap_bits debug_cap; @@ -5616,6 +5668,236 @@ struct mlx5_ifc_query_fte_in_bits { u8 reserved_at_120[0xe0]; }; +struct mlx5_ifc_match_definer_format_0_bits { + u8 reserved_at_0[0x100]; + + u8 metadata_reg_c_0[0x20]; + + u8 metadata_reg_c_1[0x20]; + + u8 outer_dmac_47_16[0x20]; + + u8 outer_dmac_15_0[0x10]; + u8 outer_ethertype[0x10]; + + u8 reserved_at_180[0x1]; + u8 sx_sniffer[0x1]; + u8 functional_lb[0x1]; + u8 outer_ip_frag[0x1]; + u8 outer_qp_type[0x2]; + u8 outer_encap_type[0x2]; + u8 port_number[0x2]; + u8 outer_l3_type[0x2]; + u8 outer_l4_type[0x2]; + u8 outer_first_vlan_type[0x2]; + u8 outer_first_vlan_prio[0x3]; + u8 outer_first_vlan_cfi[0x1]; + u8 outer_first_vlan_vid[0xc]; + + u8 outer_l4_type_ext[0x4]; + u8 reserved_at_1a4[0x2]; + u8 outer_ipsec_layer[0x2]; + u8 outer_l2_type[0x2]; + u8 force_lb[0x1]; + u8 outer_l2_ok[0x1]; + u8 outer_l3_ok[0x1]; + u8 outer_l4_ok[0x1]; + u8 outer_second_vlan_type[0x2]; + u8 outer_second_vlan_prio[0x3]; + u8 outer_second_vlan_cfi[0x1]; + u8 outer_second_vlan_vid[0xc]; + + u8 outer_smac_47_16[0x20]; + + u8 outer_smac_15_0[0x10]; + u8 inner_ipv4_checksum_ok[0x1]; + u8 inner_l4_checksum_ok[0x1]; + u8 outer_ipv4_checksum_ok[0x1]; + u8 outer_l4_checksum_ok[0x1]; + u8 inner_l3_ok[0x1]; + u8 inner_l4_ok[0x1]; + u8 outer_l3_ok_duplicate[0x1]; + u8 outer_l4_ok_duplicate[0x1]; + u8 outer_tcp_cwr[0x1]; + u8 outer_tcp_ece[0x1]; + u8 outer_tcp_urg[0x1]; + u8 outer_tcp_ack[0x1]; + u8 outer_tcp_psh[0x1]; + u8 outer_tcp_rst[0x1]; + u8 outer_tcp_syn[0x1]; + u8 outer_tcp_fin[0x1]; +}; + +struct mlx5_ifc_match_definer_format_22_bits { + u8 reserved_at_0[0x100]; + + u8 outer_ip_src_addr[0x20]; + + u8 outer_ip_dest_addr[0x20]; + + u8 outer_l4_sport[0x10]; + u8 outer_l4_dport[0x10]; + + u8 reserved_at_160[0x1]; + u8 sx_sniffer[0x1]; + u8 functional_lb[0x1]; + u8 outer_ip_frag[0x1]; + u8 outer_qp_type[0x2]; + u8 outer_encap_type[0x2]; + u8 port_number[0x2]; + u8 outer_l3_type[0x2]; + u8 outer_l4_type[0x2]; + u8 outer_first_vlan_type[0x2]; + u8 outer_first_vlan_prio[0x3]; + u8 outer_first_vlan_cfi[0x1]; + u8 outer_first_vlan_vid[0xc]; + + u8 metadata_reg_c_0[0x20]; + + u8 outer_dmac_47_16[0x20]; + + u8 outer_smac_47_16[0x20]; + + u8 outer_smac_15_0[0x10]; + u8 outer_dmac_15_0[0x10]; +}; + +struct mlx5_ifc_match_definer_format_23_bits { + u8 reserved_at_0[0x100]; + + u8 inner_ip_src_addr[0x20]; + + u8 inner_ip_dest_addr[0x20]; + + u8 inner_l4_sport[0x10]; + u8 inner_l4_dport[0x10]; + + u8 reserved_at_160[0x1]; + u8 sx_sniffer[0x1]; + u8 functional_lb[0x1]; + u8 inner_ip_frag[0x1]; + u8 inner_qp_type[0x2]; + u8 inner_encap_type[0x2]; + u8 port_number[0x2]; + u8 inner_l3_type[0x2]; + u8 inner_l4_type[0x2]; + u8 inner_first_vlan_type[0x2]; + u8 inner_first_vlan_prio[0x3]; + u8 inner_first_vlan_cfi[0x1]; + u8 inner_first_vlan_vid[0xc]; + + u8 tunnel_header_0[0x20]; + + u8 inner_dmac_47_16[0x20]; + + u8 inner_smac_47_16[0x20]; + + u8 inner_smac_15_0[0x10]; + u8 inner_dmac_15_0[0x10]; +}; + +struct mlx5_ifc_match_definer_format_29_bits { + u8 reserved_at_0[0xc0]; + + u8 outer_ip_dest_addr[0x80]; + + u8 outer_ip_src_addr[0x80]; + + u8 outer_l4_sport[0x10]; + u8 outer_l4_dport[0x10]; + + u8 reserved_at_1e0[0x20]; +}; + +struct mlx5_ifc_match_definer_format_30_bits { + u8 reserved_at_0[0xa0]; + + u8 outer_ip_dest_addr[0x80]; + + u8 outer_ip_src_addr[0x80]; + + u8 outer_dmac_47_16[0x20]; + + u8 outer_smac_47_16[0x20]; + + u8 outer_smac_15_0[0x10]; + u8 outer_dmac_15_0[0x10]; +}; + +struct mlx5_ifc_match_definer_format_31_bits { + u8 reserved_at_0[0xc0]; + + u8 inner_ip_dest_addr[0x80]; + + u8 inner_ip_src_addr[0x80]; + + u8 inner_l4_sport[0x10]; + u8 inner_l4_dport[0x10]; + + u8 reserved_at_1e0[0x20]; +}; + +struct mlx5_ifc_match_definer_format_32_bits { + u8 reserved_at_0[0xa0]; + + u8 inner_ip_dest_addr[0x80]; + + u8 inner_ip_src_addr[0x80]; + + u8 inner_dmac_47_16[0x20]; + + u8 inner_smac_47_16[0x20]; + + u8 inner_smac_15_0[0x10]; + u8 inner_dmac_15_0[0x10]; +}; + +struct mlx5_ifc_match_definer_bits { + u8 modify_field_select[0x40]; + + u8 reserved_at_40[0x40]; + + u8 reserved_at_80[0x10]; + u8 format_id[0x10]; + + u8 reserved_at_a0[0x160]; + + u8 match_mask[16][0x20]; +}; + +struct mlx5_ifc_general_obj_in_cmd_hdr_bits { + u8 opcode[0x10]; + u8 uid[0x10]; + + u8 vhca_tunnel_id[0x10]; + u8 obj_type[0x10]; + + u8 obj_id[0x20]; + + u8 reserved_at_60[0x20]; +}; + +struct mlx5_ifc_general_obj_out_cmd_hdr_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 obj_id[0x20]; + + u8 reserved_at_60[0x20]; +}; + +struct mlx5_ifc_create_match_definer_in_bits { + struct mlx5_ifc_general_obj_in_cmd_hdr_bits general_obj_in_cmd_hdr; + + struct mlx5_ifc_match_definer_bits obj_context; +}; + +struct mlx5_ifc_create_match_definer_out_bits { + struct mlx5_ifc_general_obj_out_cmd_hdr_bits general_obj_out_cmd_hdr; +}; + enum { MLX5_QUERY_FLOW_GROUP_OUT_MATCH_CRITERIA_ENABLE_OUTER_HEADERS = 0x0, MLX5_QUERY_FLOW_GROUP_OUT_MATCH_CRITERIA_ENABLE_MISC_PARAMETERS = 0x1, @@ -8089,6 +8371,11 @@ struct mlx5_ifc_create_flow_group_out_bits { u8 reserved_at_60[0x20]; }; +enum { + MLX5_CREATE_FLOW_GROUP_IN_GROUP_TYPE_TCAM_SUBTABLE = 0x0, + MLX5_CREATE_FLOW_GROUP_IN_GROUP_TYPE_HASH_SPLIT = 0x1, +}; + enum { MLX5_CREATE_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_OUTER_HEADERS = 0x0, MLX5_CREATE_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_MISC_PARAMETERS = 0x1, @@ -8110,7 +8397,9 @@ struct mlx5_ifc_create_flow_group_in_bits { u8 reserved_at_60[0x20]; u8 table_type[0x8]; - u8 reserved_at_88[0x18]; + u8 reserved_at_88[0x4]; + u8 group_type[0x4]; + u8 reserved_at_90[0x10]; u8 reserved_at_a0[0x8]; u8 table_id[0x18]; @@ -8125,7 +8414,10 @@ struct mlx5_ifc_create_flow_group_in_bits { u8 end_flow_index[0x20]; - u8 reserved_at_140[0xa0]; + u8 reserved_at_140[0x10]; + u8 match_definer_id[0x10]; + + u8 reserved_at_160[0x80]; u8 reserved_at_1e0[0x18]; u8 match_criteria_enable[0x8]; @@ -10398,9 +10690,16 @@ struct mlx5_ifc_dcbx_param_bits { u8 reserved_at_a0[0x160]; }; +enum { + MLX5_LAG_PORT_SELECT_MODE_QUEUE_AFFINITY = 0, + MLX5_LAG_PORT_SELECT_MODE_PORT_SELECT_FT, +}; + struct mlx5_ifc_lagc_bits { u8 fdb_selection_mode[0x1]; - u8 reserved_at_1[0x1c]; + u8 reserved_at_1[0x14]; + u8 port_select_mode[0x3]; + u8 reserved_at_18[0x5]; u8 lag_state[0x3]; u8 reserved_at_20[0x14]; @@ -10614,29 +10913,6 @@ struct mlx5_ifc_dealloc_memic_out_bits { u8 reserved_at_40[0x40]; }; -struct mlx5_ifc_general_obj_in_cmd_hdr_bits { - u8 opcode[0x10]; - u8 uid[0x10]; - - u8 vhca_tunnel_id[0x10]; - u8 obj_type[0x10]; - - u8 obj_id[0x20]; - - u8 reserved_at_60[0x20]; -}; - -struct mlx5_ifc_general_obj_out_cmd_hdr_bits { - u8 status[0x8]; - u8 reserved_at_8[0x18]; - - u8 syndrome[0x20]; - - u8 obj_id[0x20]; - - u8 reserved_at_60[0x20]; -}; - struct mlx5_ifc_umem_bits { u8 reserved_at_0[0x80]; diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index be8e4cbe282a..3971db2c6d4b 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -105,18 +105,7 @@ struct page { struct page_pool *pp; unsigned long _pp_mapping_pad; unsigned long dma_addr; - union { - /** - * dma_addr_upper: might require a 64-bit - * value on 32-bit architectures. - */ - unsigned long dma_addr_upper; - /** - * For frag page support, not supported in - * 32-bit architectures with 64-bit DMA. - */ - atomic_long_t pp_frag_count; - }; + atomic_long_t pp_frag_count; }; struct { /* slab, slob and slub */ union { diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index d79163208dfd..3ec42495a43a 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1861,6 +1861,7 @@ enum netdev_ml_priv_type { * @xps_maps: XXX: need comments on this one * @miniq_egress: clsact qdisc specific data for * egress processing + * @nf_hooks_egress: netfilter hooks executed for egress packets * @qdisc_hash: qdisc hash table * @watchdog_timeo: Represents the timeout that is used by * the watchdog (see dev_watchdog()) @@ -1916,7 +1917,6 @@ enum netdev_ml_priv_type { * @sfp_bus: attached &struct sfp_bus structure. * * @qdisc_tx_busylock: lockdep class annotating Qdisc->busylock spinlock - * @qdisc_running_key: lockdep class annotating Qdisc->running seqcount * * @proto_down: protocol port state information can be sent to the * switch driver and used to set the phys state of the @@ -2161,6 +2161,9 @@ struct net_device { #ifdef CONFIG_NET_CLS_ACT struct mini_Qdisc __rcu *miniq_egress; #endif +#ifdef CONFIG_NETFILTER_EGRESS + struct nf_hook_entries __rcu *nf_hooks_egress; +#endif #ifdef CONFIG_NET_SCHED DECLARE_HASHTABLE (qdisc_hash, 4); @@ -2250,7 +2253,6 @@ struct net_device { struct phy_device *phydev; struct sfp_bus *sfp_bus; struct lock_class_key *qdisc_tx_busylock; - struct lock_class_key *qdisc_running_key; bool proto_down; unsigned wol_enabled:1; unsigned threaded:1; @@ -2360,13 +2362,11 @@ static inline void netdev_for_each_tx_queue(struct net_device *dev, #define netdev_lockdep_set_classes(dev) \ { \ static struct lock_class_key qdisc_tx_busylock_key; \ - static struct lock_class_key qdisc_running_key; \ static struct lock_class_key qdisc_xmit_lock_key; \ static struct lock_class_key dev_addr_list_lock_key; \ unsigned int i; \ \ (dev)->qdisc_tx_busylock = &qdisc_tx_busylock_key; \ - (dev)->qdisc_running_key = &qdisc_running_key; \ lockdep_set_class(&(dev)->addr_list_lock, \ &dev_addr_list_lock_key); \ for (i = 0; i < (dev)->num_tx_queues; i++) \ @@ -2955,6 +2955,7 @@ struct net_device *__dev_get_by_flags(struct net *net, unsigned short flags, struct net_device *dev_get_by_name(struct net *net, const char *name); struct net_device *dev_get_by_name_rcu(struct net *net, const char *name); struct net_device *__dev_get_by_name(struct net *net, const char *name); +bool netdev_name_in_use(struct net *net, const char *name); int dev_alloc_name(struct net_device *dev, const char *name); int dev_open(struct net_device *dev, struct netlink_ext_ack *extack); void dev_close(struct net_device *dev); @@ -4642,7 +4643,7 @@ void __hw_addr_init(struct netdev_hw_addr_list *list); /* Functions used for device addresses handling */ static inline void -__dev_addr_set(struct net_device *dev, const u8 *addr, size_t len) +__dev_addr_set(struct net_device *dev, const void *addr, size_t len) { memcpy(dev->dev_addr, addr, len); } @@ -4654,7 +4655,7 @@ static inline void dev_addr_set(struct net_device *dev, const u8 *addr) static inline void dev_addr_mod(struct net_device *dev, unsigned int offset, - const u8 *addr, size_t len) + const void *addr, size_t len) { memcpy(&dev->dev_addr[offset], addr, len); } @@ -4800,8 +4801,6 @@ struct netdev_nested_priv { bool netdev_has_upper_dev(struct net_device *dev, struct net_device *upper_dev); struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev, struct list_head **iter); -struct net_device *netdev_all_upper_get_next_dev_rcu(struct net_device *dev, - struct list_head **iter); #ifdef CONFIG_LOCKDEP static LIST_HEAD(net_unlink_list); @@ -5236,7 +5235,7 @@ static inline void netif_keep_dst(struct net_device *dev) static inline bool netif_reduces_vlan_mtu(struct net_device *dev) { /* TODO: reserve and use an additional IFF bit, if we get more users */ - return dev->priv_flags & IFF_MACSEC; + return netif_is_macsec(dev); } extern struct pernet_operations __net_initdata loopback_net_ops; diff --git a/include/linux/netfilter_arp/arp_tables.h b/include/linux/netfilter_arp/arp_tables.h index 4f9a4b3c5892..a40aaf645fa4 100644 --- a/include/linux/netfilter_arp/arp_tables.h +++ b/include/linux/netfilter_arp/arp_tables.h @@ -54,9 +54,8 @@ int arpt_register_table(struct net *net, const struct xt_table *table, const struct nf_hook_ops *ops); void arpt_unregister_table(struct net *net, const char *name); void arpt_unregister_table_pre_exit(struct net *net, const char *name); -extern unsigned int arpt_do_table(struct sk_buff *skb, - const struct nf_hook_state *state, - struct xt_table *table); +extern unsigned int arpt_do_table(void *priv, struct sk_buff *skb, + const struct nf_hook_state *state); #ifdef CONFIG_NETFILTER_XTABLES_COMPAT #include diff --git a/include/linux/netfilter_bridge/ebtables.h b/include/linux/netfilter_bridge/ebtables.h index 10a01978bc0d..a13296d6c7ce 100644 --- a/include/linux/netfilter_bridge/ebtables.h +++ b/include/linux/netfilter_bridge/ebtables.h @@ -112,9 +112,8 @@ extern int ebt_register_table(struct net *net, const struct nf_hook_ops *ops); extern void ebt_unregister_table(struct net *net, const char *tablename); void ebt_unregister_table_pre_exit(struct net *net, const char *tablename); -extern unsigned int ebt_do_table(struct sk_buff *skb, - const struct nf_hook_state *state, - struct ebt_table *table); +extern unsigned int ebt_do_table(void *priv, struct sk_buff *skb, + const struct nf_hook_state *state); /* True if the hook mask denotes that the rule is in a base chain, * used in the check() functions */ diff --git a/include/linux/netfilter_ingress.h b/include/linux/netfilter_ingress.h deleted file mode 100644 index a13774be2eb5..000000000000 --- a/include/linux/netfilter_ingress.h +++ /dev/null @@ -1,58 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _NETFILTER_INGRESS_H_ -#define _NETFILTER_INGRESS_H_ - -#include -#include - -#ifdef CONFIG_NETFILTER_INGRESS -static inline bool nf_hook_ingress_active(const struct sk_buff *skb) -{ -#ifdef CONFIG_JUMP_LABEL - if (!static_key_false(&nf_hooks_needed[NFPROTO_NETDEV][NF_NETDEV_INGRESS])) - return false; -#endif - return rcu_access_pointer(skb->dev->nf_hooks_ingress); -} - -/* caller must hold rcu_read_lock */ -static inline int nf_hook_ingress(struct sk_buff *skb) -{ - struct nf_hook_entries *e = rcu_dereference(skb->dev->nf_hooks_ingress); - struct nf_hook_state state; - int ret; - - /* Must recheck the ingress hook head, in the event it became NULL - * after the check in nf_hook_ingress_active evaluated to true. - */ - if (unlikely(!e)) - return 0; - - nf_hook_state_init(&state, NF_NETDEV_INGRESS, - NFPROTO_NETDEV, skb->dev, NULL, NULL, - dev_net(skb->dev), NULL); - ret = nf_hook_slow(skb, &state, e, 0); - if (ret == 0) - return -1; - - return ret; -} - -static inline void nf_hook_ingress_init(struct net_device *dev) -{ - RCU_INIT_POINTER(dev->nf_hooks_ingress, NULL); -} -#else /* CONFIG_NETFILTER_INGRESS */ -static inline int nf_hook_ingress_active(struct sk_buff *skb) -{ - return 0; -} - -static inline int nf_hook_ingress(struct sk_buff *skb) -{ - return 0; -} - -static inline void nf_hook_ingress_init(struct net_device *dev) {} -#endif /* CONFIG_NETFILTER_INGRESS */ -#endif /* _NETFILTER_INGRESS_H_ */ diff --git a/include/linux/netfilter_ipv4/ip_tables.h b/include/linux/netfilter_ipv4/ip_tables.h index 8d09bfe850dc..132b0e4a6d4d 100644 --- a/include/linux/netfilter_ipv4/ip_tables.h +++ b/include/linux/netfilter_ipv4/ip_tables.h @@ -63,9 +63,9 @@ struct ipt_error { } extern void *ipt_alloc_initial_table(const struct xt_table *); -extern unsigned int ipt_do_table(struct sk_buff *skb, - const struct nf_hook_state *state, - struct xt_table *table); +extern unsigned int ipt_do_table(void *priv, + struct sk_buff *skb, + const struct nf_hook_state *state); #ifdef CONFIG_NETFILTER_XTABLES_COMPAT #include diff --git a/include/linux/netfilter_ipv6/ip6_tables.h b/include/linux/netfilter_ipv6/ip6_tables.h index 79e73fd7d965..8b8885a73c76 100644 --- a/include/linux/netfilter_ipv6/ip6_tables.h +++ b/include/linux/netfilter_ipv6/ip6_tables.h @@ -29,9 +29,8 @@ int ip6t_register_table(struct net *net, const struct xt_table *table, const struct nf_hook_ops *ops); void ip6t_unregister_table_pre_exit(struct net *net, const char *name); void ip6t_unregister_table_exit(struct net *net, const char *name); -extern unsigned int ip6t_do_table(struct sk_buff *skb, - const struct nf_hook_state *state, - struct xt_table *table); +extern unsigned int ip6t_do_table(void *priv, struct sk_buff *skb, + const struct nf_hook_state *state); #ifdef CONFIG_NETFILTER_XTABLES_COMPAT #include diff --git a/include/linux/netfilter_netdev.h b/include/linux/netfilter_netdev.h new file mode 100644 index 000000000000..b71b57a83bb4 --- /dev/null +++ b/include/linux/netfilter_netdev.h @@ -0,0 +1,146 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _NETFILTER_NETDEV_H_ +#define _NETFILTER_NETDEV_H_ + +#include +#include + +#ifdef CONFIG_NETFILTER_INGRESS +static inline bool nf_hook_ingress_active(const struct sk_buff *skb) +{ +#ifdef CONFIG_JUMP_LABEL + if (!static_key_false(&nf_hooks_needed[NFPROTO_NETDEV][NF_NETDEV_INGRESS])) + return false; +#endif + return rcu_access_pointer(skb->dev->nf_hooks_ingress); +} + +/* caller must hold rcu_read_lock */ +static inline int nf_hook_ingress(struct sk_buff *skb) +{ + struct nf_hook_entries *e = rcu_dereference(skb->dev->nf_hooks_ingress); + struct nf_hook_state state; + int ret; + + /* Must recheck the ingress hook head, in the event it became NULL + * after the check in nf_hook_ingress_active evaluated to true. + */ + if (unlikely(!e)) + return 0; + + nf_hook_state_init(&state, NF_NETDEV_INGRESS, + NFPROTO_NETDEV, skb->dev, NULL, NULL, + dev_net(skb->dev), NULL); + ret = nf_hook_slow(skb, &state, e, 0); + if (ret == 0) + return -1; + + return ret; +} + +#else /* CONFIG_NETFILTER_INGRESS */ +static inline int nf_hook_ingress_active(struct sk_buff *skb) +{ + return 0; +} + +static inline int nf_hook_ingress(struct sk_buff *skb) +{ + return 0; +} +#endif /* CONFIG_NETFILTER_INGRESS */ + +#ifdef CONFIG_NETFILTER_EGRESS +static inline bool nf_hook_egress_active(void) +{ +#ifdef CONFIG_JUMP_LABEL + if (!static_key_false(&nf_hooks_needed[NFPROTO_NETDEV][NF_NETDEV_EGRESS])) + return false; +#endif + return true; +} + +/** + * nf_hook_egress - classify packets before transmission + * @skb: packet to be classified + * @rc: result code which shall be returned by __dev_queue_xmit() on failure + * @dev: netdev whose egress hooks shall be applied to @skb + * + * Returns @skb on success or %NULL if the packet was consumed or filtered. + * Caller must hold rcu_read_lock. + * + * On ingress, packets are classified first by tc, then by netfilter. + * On egress, the order is reversed for symmetry. Conceptually, tc and + * netfilter can be thought of as layers, with netfilter layered above tc: + * When tc redirects a packet to another interface, netfilter is not applied + * because the packet is on the tc layer. + * + * The nf_skip_egress flag controls whether netfilter is applied on egress. + * It is updated by __netif_receive_skb_core() and __dev_queue_xmit() when the + * packet passes through tc and netfilter. Because __dev_queue_xmit() may be + * called recursively by tunnel drivers such as vxlan, the flag is reverted to + * false after sch_handle_egress(). This ensures that netfilter is applied + * both on the overlay and underlying network. + */ +static inline struct sk_buff *nf_hook_egress(struct sk_buff *skb, int *rc, + struct net_device *dev) +{ + struct nf_hook_entries *e; + struct nf_hook_state state; + int ret; + +#ifdef CONFIG_NETFILTER_SKIP_EGRESS + if (skb->nf_skip_egress) + return skb; +#endif + + e = rcu_dereference(dev->nf_hooks_egress); + if (!e) + return skb; + + nf_hook_state_init(&state, NF_NETDEV_EGRESS, + NFPROTO_NETDEV, dev, NULL, NULL, + dev_net(dev), NULL); + ret = nf_hook_slow(skb, &state, e, 0); + + if (ret == 1) { + return skb; + } else if (ret < 0) { + *rc = NET_XMIT_DROP; + return NULL; + } else { /* ret == 0 */ + *rc = NET_XMIT_SUCCESS; + return NULL; + } +} +#else /* CONFIG_NETFILTER_EGRESS */ +static inline bool nf_hook_egress_active(void) +{ + return false; +} + +static inline struct sk_buff *nf_hook_egress(struct sk_buff *skb, int *rc, + struct net_device *dev) +{ + return skb; +} +#endif /* CONFIG_NETFILTER_EGRESS */ + +static inline void nf_skip_egress(struct sk_buff *skb, bool skip) +{ +#ifdef CONFIG_NETFILTER_SKIP_EGRESS + skb->nf_skip_egress = skip; +#endif +} + +static inline void nf_hook_netdev_init(struct net_device *dev) +{ +#ifdef CONFIG_NETFILTER_INGRESS + RCU_INIT_POINTER(dev->nf_hooks_ingress, NULL); +#endif +#ifdef CONFIG_NETFILTER_EGRESS + RCU_INIT_POINTER(dev->nf_hooks_egress, NULL); +#endif +} + +#endif /* _NETFILTER_NETDEV_H_ */ diff --git a/include/linux/of_net.h b/include/linux/of_net.h index 0797e2edb8c2..0484b613ca64 100644 --- a/include/linux/of_net.h +++ b/include/linux/of_net.h @@ -8,7 +8,7 @@ #include -#ifdef CONFIG_OF +#if defined(CONFIG_OF) && defined(CONFIG_NET) #include struct net_device; diff --git a/include/linux/qed/qed_eth_if.h b/include/linux/qed/qed_eth_if.h index 4df0bf0a0864..e1bf3219b4e6 100644 --- a/include/linux/qed/qed_eth_if.h +++ b/include/linux/qed/qed_eth_if.h @@ -331,7 +331,7 @@ struct qed_eth_ops { int (*configure_arfs_searcher)(struct qed_dev *cdev, enum qed_filter_config_mode mode); int (*get_coalesce)(struct qed_dev *cdev, u16 *coal, void *handle); - int (*req_bulletin_update_mac)(struct qed_dev *cdev, u8 *mac); + int (*req_bulletin_update_mac)(struct qed_dev *cdev, const u8 *mac); }; const struct qed_eth_ops *qed_get_eth_ops(void); diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index ad220d5da18f..0dae7fcc5ef2 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -1113,7 +1113,7 @@ struct qed_common_ops { * * Return: Int. */ - int (*update_mac)(struct qed_dev *cdev, u8 *mac); + int (*update_mac)(struct qed_dev *cdev, const u8 *mac); /** * update_mtu(): API to inform the change in the mtu. diff --git a/include/linux/qed/qed_rdma_if.h b/include/linux/qed/qed_rdma_if.h index aeb242cefebf..3b76c07fbcf8 100644 --- a/include/linux/qed/qed_rdma_if.h +++ b/include/linux/qed/qed_rdma_if.h @@ -662,7 +662,8 @@ struct qed_rdma_ops { u8 connection_handle, struct qed_ll2_stats *p_stats); int (*ll2_set_mac_filter)(struct qed_dev *cdev, - u8 *old_mac_address, u8 *new_mac_address); + u8 *old_mac_address, + const u8 *new_mac_address); int (*iwarp_set_engine_affin)(struct qed_dev *cdev, bool b_reset); diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 841e2f0f5240..cb96f1e6460c 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -652,6 +652,7 @@ typedef unsigned char *sk_buff_data_t; * @tc_at_ingress: used within tc_classify to distinguish in/egress * @redirected: packet was redirected by packet classifier * @from_ingress: packet was redirected from the ingress path + * @nf_skip_egress: packet shall skip nf egress - see netfilter_netdev.h * @peeked: this packet has been seen already, so stats have been * done for it, don't do them again * @nf_trace: netfilter packet trace flag @@ -868,6 +869,9 @@ struct sk_buff { #ifdef CONFIG_NET_REDIRECT __u8 from_ingress:1; #endif +#ifdef CONFIG_NETFILTER_SKIP_EGRESS + __u8 nf_skip_egress:1; +#endif #ifdef CONFIG_TLS_DEVICE __u8 decrypted:1; #endif diff --git a/include/linux/u64_stats_sync.h b/include/linux/u64_stats_sync.h index e81856c0ba13..e8ec116c916b 100644 --- a/include/linux/u64_stats_sync.h +++ b/include/linux/u64_stats_sync.h @@ -83,6 +83,11 @@ static inline u64 u64_stats_read(const u64_stats_t *p) return local64_read(&p->v); } +static inline void u64_stats_set(u64_stats_t *p, u64 val) +{ + local64_set(&p->v, val); +} + static inline void u64_stats_add(u64_stats_t *p, unsigned long val) { local64_add(val, &p->v); @@ -104,6 +109,11 @@ static inline u64 u64_stats_read(const u64_stats_t *p) return p->v; } +static inline void u64_stats_set(u64_stats_t *p, u64 val) +{ + p->v = val; +} + static inline void u64_stats_add(u64_stats_t *p, unsigned long val) { p->v += val; diff --git a/include/net/act_api.h b/include/net/act_api.h index f19f7f4a463c..b5b624c7e488 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -30,13 +30,13 @@ struct tc_action { atomic_t tcfa_bindcnt; int tcfa_action; struct tcf_t tcfa_tm; - struct gnet_stats_basic_packed tcfa_bstats; - struct gnet_stats_basic_packed tcfa_bstats_hw; + struct gnet_stats_basic_sync tcfa_bstats; + struct gnet_stats_basic_sync tcfa_bstats_hw; struct gnet_stats_queue tcfa_qstats; struct net_rate_estimator __rcu *tcfa_rate_est; spinlock_t tcfa_lock; - struct gnet_stats_basic_cpu __percpu *cpu_bstats; - struct gnet_stats_basic_cpu __percpu *cpu_bstats_hw; + struct gnet_stats_basic_sync __percpu *cpu_bstats; + struct gnet_stats_basic_sync __percpu *cpu_bstats_hw; struct gnet_stats_queue __percpu *cpu_qstats; struct tc_cookie __rcu *act_cookie; struct tcf_chain __rcu *goto_chain; @@ -206,7 +206,7 @@ static inline void tcf_action_update_bstats(struct tc_action *a, struct sk_buff *skb) { if (likely(a->cpu_bstats)) { - bstats_cpu_update(this_cpu_ptr(a->cpu_bstats), skb); + bstats_update(this_cpu_ptr(a->cpu_bstats), skb); return; } spin_lock(&a->tcfa_lock); diff --git a/include/net/ax25.h b/include/net/ax25.h index 8b7eb46ad72d..03d409de61ad 100644 --- a/include/net/ax25.h +++ b/include/net/ax25.h @@ -304,7 +304,7 @@ extern spinlock_t ax25_list_lock; void ax25_cb_add(ax25_cb *); struct sock *ax25_find_listener(ax25_address *, int, struct net_device *, int); struct sock *ax25_get_socket(ax25_address *, ax25_address *, int); -ax25_cb *ax25_find_cb(ax25_address *, ax25_address *, ax25_digi *, +ax25_cb *ax25_find_cb(const ax25_address *, ax25_address *, ax25_digi *, struct net_device *); void ax25_send_to_raw(ax25_address *, struct sk_buff *, int); void ax25_destroy_socket(ax25_cb *); @@ -384,10 +384,11 @@ struct ax25_linkfail { void ax25_linkfail_register(struct ax25_linkfail *lf); void ax25_linkfail_release(struct ax25_linkfail *lf); -int __must_check ax25_listen_register(ax25_address *, struct net_device *); -void ax25_listen_release(ax25_address *, struct net_device *); +int __must_check ax25_listen_register(const ax25_address *, + struct net_device *); +void ax25_listen_release(const ax25_address *, struct net_device *); int(*ax25_protocol_function(unsigned int))(struct sk_buff *, ax25_cb *); -int ax25_listen_mine(ax25_address *, struct net_device *); +int ax25_listen_mine(const ax25_address *, struct net_device *); void ax25_link_failed(ax25_cb *, int); int ax25_protocol_is_registered(unsigned int); @@ -401,8 +402,8 @@ netdev_tx_t ax25_ip_xmit(struct sk_buff *skb); extern const struct header_ops ax25_header_ops; /* ax25_out.c */ -ax25_cb *ax25_send_frame(struct sk_buff *, int, ax25_address *, ax25_address *, - ax25_digi *, struct net_device *); +ax25_cb *ax25_send_frame(struct sk_buff *, int, const ax25_address *, + ax25_address *, ax25_digi *, struct net_device *); void ax25_output(ax25_cb *, int, struct sk_buff *); void ax25_kick(ax25_cb *); void ax25_transmit_buffer(ax25_cb *, struct sk_buff *, int); diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 27336fc70467..423f97b982ff 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -739,6 +739,22 @@ struct cfg80211_tid_config { struct cfg80211_tid_cfg tid_conf[]; }; +/** + * struct cfg80211_fils_aad - FILS AAD data + * @macaddr: STA MAC address + * @kek: FILS KEK + * @kek_len: FILS KEK length + * @snonce: STA Nonce + * @anonce: AP Nonce + */ +struct cfg80211_fils_aad { + const u8 *macaddr; + const u8 *kek; + u8 kek_len; + const u8 *snonce; + const u8 *anonce; +}; + /** * cfg80211_get_chandef_type - return old channel type from chandef * @chandef: the channel definition @@ -1040,6 +1056,36 @@ struct cfg80211_crypto_settings { enum nl80211_sae_pwe_mechanism sae_pwe; }; +/** + * struct cfg80211_mbssid_config - AP settings for multi bssid + * + * @tx_wdev: pointer to the transmitted interface in the MBSSID set + * @index: index of this AP in the multi bssid group. + * @ema: set to true if the beacons should be sent out in EMA mode. + */ +struct cfg80211_mbssid_config { + struct wireless_dev *tx_wdev; + u8 index; + bool ema; +}; + +/** + * struct cfg80211_mbssid_elems - Multiple BSSID elements + * + * @cnt: Number of elements in array %elems. + * + * @elem: Array of multiple BSSID element(s) to be added into Beacon frames. + * @elem.data: Data for multiple BSSID elements. + * @elem.len: Length of data. + */ +struct cfg80211_mbssid_elems { + u8 cnt; + struct { + const u8 *data; + size_t len; + } elem[]; +}; + /** * struct cfg80211_beacon_data - beacon data * @head: head portion of beacon (before TIM IE) @@ -1058,6 +1104,7 @@ struct cfg80211_crypto_settings { * @assocresp_ies_len: length of assocresp_ies in octets * @probe_resp_len: length of probe response template (@probe_resp) * @probe_resp: probe response template (AP mode only) + * @mbssid_ies: multiple BSSID elements * @ftm_responder: enable FTM responder functionality; -1 for no change * (which also implies no change in LCI/civic location data) * @lci: Measurement Report element content, starting with Measurement Token @@ -1075,6 +1122,7 @@ struct cfg80211_beacon_data { const u8 *probe_resp; const u8 *lci; const u8 *civicloc; + struct cfg80211_mbssid_elems *mbssid_ies; s8 ftm_responder; size_t head_len, tail_len; @@ -1189,6 +1237,7 @@ enum cfg80211_ap_settings_flags { * @he_oper: HE operation IE (or %NULL if HE isn't enabled) * @fils_discovery: FILS discovery transmission parameters * @unsol_bcast_probe_resp: Unsolicited broadcast probe response parameters + * @mbssid_config: AP settings for multiple bssid */ struct cfg80211_ap_settings { struct cfg80211_chan_def chandef; @@ -1221,6 +1270,7 @@ struct cfg80211_ap_settings { struct cfg80211_he_bss_color he_bss_color; struct cfg80211_fils_discovery fils_discovery; struct cfg80211_unsol_bcast_probe_resp unsol_bcast_probe_resp; + struct cfg80211_mbssid_config mbssid_config; }; /** @@ -4018,6 +4068,10 @@ struct mgmt_frame_regs { * @set_sar_specs: Update the SAR (TX power) settings. * * @color_change: Initiate a color change. + * + * @set_fils_aad: Set FILS AAD data to the AP driver so that the driver can use + * those to decrypt (Re)Association Request and encrypt (Re)Association + * Response frame. */ struct cfg80211_ops { int (*suspend)(struct wiphy *wiphy, struct cfg80211_wowlan *wow); @@ -4348,6 +4402,8 @@ struct cfg80211_ops { int (*color_change)(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_color_change_settings *params); + int (*set_fils_aad)(struct wiphy *wiphy, struct net_device *dev, + struct cfg80211_fils_aad *fils_aad); }; /* @@ -4981,6 +5037,13 @@ struct wiphy_iftype_akm_suites { * %NL80211_TID_CONFIG_ATTR_RETRY_LONG attributes * @sar_capa: SAR control capabilities * @rfkill: a pointer to the rfkill structure + * + * @mbssid_max_interfaces: maximum number of interfaces supported by the driver + * in a multiple BSSID set. This field must be set to a non-zero value + * by the driver to advertise MBSSID support. + * @ema_max_profile_periodicity: maximum profile periodicity supported by + * the driver. Setting this field to a non-zero value indicates that the + * driver supports enhanced multi-BSSID advertisements (EMA AP). */ struct wiphy { struct mutex mtx; @@ -5125,6 +5188,9 @@ struct wiphy { struct rfkill *rfkill; + u8 mbssid_max_interfaces; + u8 ema_max_profile_periodicity; + char priv[] __aligned(NETDEV_ALIGN); }; @@ -5490,7 +5556,7 @@ struct wireless_dev { unsigned long unprot_beacon_reported; }; -static inline u8 *wdev_address(struct wireless_dev *wdev) +static inline const u8 *wdev_address(struct wireless_dev *wdev) { if (wdev->netdev) return wdev->netdev->dev_addr; @@ -6308,6 +6374,17 @@ static inline void cfg80211_gen_new_bssid(const u8 *bssid, u8 max_bssid, u64_to_ether_addr(new_bssid_u64, new_bssid); } +/** + * cfg80211_get_ies_channel_number - returns the channel number from ies + * @ie: IEs + * @ielen: length of IEs + * @band: enum nl80211_band of the channel + * + * Returns the channel number, or -1 if none could be determined. + */ +int cfg80211_get_ies_channel_number(const u8 *ie, size_t ielen, + enum nl80211_band band); + /** * cfg80211_is_element_inherited - returns if element ID should be inherited * @element: element to check diff --git a/include/net/codel.h b/include/net/codel.h index a6e428f80135..a6c9e34e62b8 100644 --- a/include/net/codel.h +++ b/include/net/codel.h @@ -102,6 +102,9 @@ static inline u32 codel_time_to_us(codel_time_t val) * @interval: width of moving time window * @mtu: device mtu, or minimal queue backlog in bytes. * @ecn: is Explicit Congestion Notification enabled + * @ce_threshold_selector: apply ce_threshold to packets matching this value + * in the diffserv/ECN byte of the IP header + * @ce_threshold_mask: mask to apply to ce_threshold_selector comparison */ struct codel_params { codel_time_t target; @@ -109,6 +112,8 @@ struct codel_params { codel_time_t interval; u32 mtu; bool ecn; + u8 ce_threshold_selector; + u8 ce_threshold_mask; }; /** diff --git a/include/net/codel_impl.h b/include/net/codel_impl.h index d289b91dcd65..137d40d8cbeb 100644 --- a/include/net/codel_impl.h +++ b/include/net/codel_impl.h @@ -54,6 +54,8 @@ static void codel_params_init(struct codel_params *params) params->interval = MS2TIME(100); params->target = MS2TIME(5); params->ce_threshold = CODEL_DISABLED_THRESHOLD; + params->ce_threshold_mask = 0; + params->ce_threshold_selector = 0; params->ecn = false; } @@ -246,9 +248,19 @@ static struct sk_buff *codel_dequeue(void *ctx, vars->rec_inv_sqrt); } end: - if (skb && codel_time_after(vars->ldelay, params->ce_threshold) && - INET_ECN_set_ce(skb)) - stats->ce_mark++; + if (skb && codel_time_after(vars->ldelay, params->ce_threshold)) { + bool set_ce = true; + + if (params->ce_threshold_mask) { + int dsfield = skb_get_dsfield(skb); + + set_ce = (dsfield >= 0 && + (((u8)dsfield & params->ce_threshold_mask) == + params->ce_threshold_selector)); + } + if (set_ce && INET_ECN_set_ce(skb)) + stats->ce_mark++; + } return skb; } diff --git a/include/net/datalink.h b/include/net/datalink.h index a9663229b913..d9b7faaa539f 100644 --- a/include/net/datalink.h +++ b/include/net/datalink.h @@ -12,7 +12,7 @@ struct datalink_proto { int (*rcvfunc)(struct sk_buff *, struct net_device *, struct packet_type *, struct net_device *); int (*request)(struct datalink_proto *, struct sk_buff *, - unsigned char *); + const unsigned char *); struct list_head node; }; diff --git a/include/net/devlink.h b/include/net/devlink.h index a7852a257bf6..da3ceeb8b87b 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -21,45 +21,7 @@ #include #include -#define DEVLINK_RELOAD_STATS_ARRAY_SIZE \ - (__DEVLINK_RELOAD_LIMIT_MAX * __DEVLINK_RELOAD_ACTION_MAX) - -struct devlink_dev_stats { - u32 reload_stats[DEVLINK_RELOAD_STATS_ARRAY_SIZE]; - u32 remote_reload_stats[DEVLINK_RELOAD_STATS_ARRAY_SIZE]; -}; - -struct devlink_ops; - -struct devlink { - u32 index; - struct list_head port_list; - struct list_head rate_list; - struct list_head sb_list; - struct list_head dpipe_table_list; - struct list_head resource_list; - struct list_head param_list; - struct list_head region_list; - struct list_head reporter_list; - struct mutex reporters_lock; /* protects reporter_list */ - struct devlink_dpipe_headers *dpipe_headers; - struct list_head trap_list; - struct list_head trap_group_list; - struct list_head trap_policer_list; - const struct devlink_ops *ops; - struct xarray snapshot_ids; - struct devlink_dev_stats stats; - struct device *dev; - possible_net_t _net; - struct mutex lock; /* Serializes access to devlink instance specific objects such as - * port, sb, dpipe, resource, params, region, traps and more. - */ - u8 reload_failed:1, - reload_enabled:1; - refcount_t refcount; - struct completion comp; - char priv[0] __aligned(NETDEV_ALIGN); -}; +struct devlink; struct devlink_port_phys_attrs { u32 port_number; /* Same value as "split group". @@ -1224,6 +1186,11 @@ enum devlink_trap_group_generic_id { .min_burst = _min_burst, \ } +enum { + /* device supports reload operations */ + DEVLINK_F_RELOAD = 1UL << 0, +}; + struct devlink_ops { /** * @supported_flash_update_params: @@ -1520,34 +1487,9 @@ struct devlink_ops { struct netlink_ext_ack *extack); }; -static inline void *devlink_priv(struct devlink *devlink) -{ - BUG_ON(!devlink); - return &devlink->priv; -} - -static inline struct devlink *priv_to_devlink(void *priv) -{ - BUG_ON(!priv); - return container_of(priv, struct devlink, priv); -} - -static inline struct devlink_port * -netdev_to_devlink_port(struct net_device *dev) -{ - if (dev->netdev_ops->ndo_get_devlink_port) - return dev->netdev_ops->ndo_get_devlink_port(dev); - return NULL; -} - -static inline struct devlink *netdev_to_devlink(struct net_device *dev) -{ - struct devlink_port *devlink_port = netdev_to_devlink_port(dev); - - if (devlink_port) - return devlink_port->devlink; - return NULL; -} +void *devlink_priv(struct devlink *devlink); +struct devlink *priv_to_devlink(void *priv); +struct device *devlink_to_dev(const struct devlink *devlink); struct ib_device; @@ -1566,10 +1508,9 @@ static inline struct devlink *devlink_alloc(const struct devlink_ops *ops, { return devlink_alloc_ns(ops, priv_size, &init_net, dev); } +void devlink_set_features(struct devlink *devlink, u64 features); void devlink_register(struct devlink *devlink); void devlink_unregister(struct devlink *devlink); -void devlink_reload_enable(struct devlink *devlink); -void devlink_reload_disable(struct devlink *devlink); void devlink_free(struct devlink *devlink); int devlink_port_register(struct devlink *devlink, struct devlink_port *devlink_port, diff --git a/include/net/dn.h b/include/net/dn.h index 56ab0726c641..ba9655b0098a 100644 --- a/include/net/dn.h +++ b/include/net/dn.h @@ -166,7 +166,7 @@ struct dn_skb_cb { int iif; }; -static inline __le16 dn_eth2dn(unsigned char *ethaddr) +static inline __le16 dn_eth2dn(const unsigned char *ethaddr) { return get_unaligned((__le16 *)(ethaddr + 4)); } diff --git a/include/net/dsa.h b/include/net/dsa.h index d784e76113b8..1cd9c2461f0d 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -51,6 +51,7 @@ struct phylink_link_state; #define DSA_TAG_PROTO_SEVILLE_VALUE 21 #define DSA_TAG_PROTO_BRCM_LEGACY_VALUE 22 #define DSA_TAG_PROTO_SJA1110_VALUE 23 +#define DSA_TAG_PROTO_RTL8_4_VALUE 24 enum dsa_tag_protocol { DSA_TAG_PROTO_NONE = DSA_TAG_PROTO_NONE_VALUE, @@ -77,6 +78,7 @@ enum dsa_tag_protocol { DSA_TAG_PROTO_OCELOT_8021Q = DSA_TAG_PROTO_OCELOT_8021Q_VALUE, DSA_TAG_PROTO_SEVILLE = DSA_TAG_PROTO_SEVILLE_VALUE, DSA_TAG_PROTO_SJA1110 = DSA_TAG_PROTO_SJA1110_VALUE, + DSA_TAG_PROTO_RTL8_4 = DSA_TAG_PROTO_RTL8_4_VALUE, }; struct dsa_switch; @@ -472,14 +474,41 @@ static inline bool dsa_is_user_port(struct dsa_switch *ds, int p) return dsa_to_port(ds, p)->type == DSA_PORT_TYPE_USER; } +#define dsa_tree_for_each_user_port(_dp, _dst) \ + list_for_each_entry((_dp), &(_dst)->ports, list) \ + if (dsa_port_is_user((_dp))) + +#define dsa_switch_for_each_port(_dp, _ds) \ + list_for_each_entry((_dp), &(_ds)->dst->ports, list) \ + if ((_dp)->ds == (_ds)) + +#define dsa_switch_for_each_port_safe(_dp, _next, _ds) \ + list_for_each_entry_safe((_dp), (_next), &(_ds)->dst->ports, list) \ + if ((_dp)->ds == (_ds)) + +#define dsa_switch_for_each_port_continue_reverse(_dp, _ds) \ + list_for_each_entry_continue_reverse((_dp), &(_ds)->dst->ports, list) \ + if ((_dp)->ds == (_ds)) + +#define dsa_switch_for_each_available_port(_dp, _ds) \ + dsa_switch_for_each_port((_dp), (_ds)) \ + if (!dsa_port_is_unused((_dp))) + +#define dsa_switch_for_each_user_port(_dp, _ds) \ + dsa_switch_for_each_port((_dp), (_ds)) \ + if (dsa_port_is_user((_dp))) + +#define dsa_switch_for_each_cpu_port(_dp, _ds) \ + dsa_switch_for_each_port((_dp), (_ds)) \ + if (dsa_port_is_cpu((_dp))) + static inline u32 dsa_user_ports(struct dsa_switch *ds) { + struct dsa_port *dp; u32 mask = 0; - int p; - for (p = 0; p < ds->num_ports; p++) - if (dsa_is_user_port(ds, p)) - mask |= BIT(p); + dsa_switch_for_each_user_port(dp, ds) + mask |= BIT(dp->index); return mask; } @@ -645,6 +674,12 @@ struct dsa_switch_ops { int (*get_sset_count)(struct dsa_switch *ds, int port, int sset); void (*get_ethtool_phy_stats)(struct dsa_switch *ds, int port, uint64_t *data); + void (*get_eth_phy_stats)(struct dsa_switch *ds, int port, + struct ethtool_eth_phy_stats *phy_stats); + void (*get_eth_mac_stats)(struct dsa_switch *ds, int port, + struct ethtool_eth_mac_stats *mac_stats); + void (*get_eth_ctrl_stats)(struct dsa_switch *ds, int port, + struct ethtool_eth_ctrl_stats *ctrl_stats); void (*get_stats64)(struct dsa_switch *ds, int port, struct rtnl_link_stats64 *s); void (*self_test)(struct dsa_switch *ds, int port, diff --git a/include/net/gen_stats.h b/include/net/gen_stats.h index 1424e02cef90..7aa2b8e1fb29 100644 --- a/include/net/gen_stats.h +++ b/include/net/gen_stats.h @@ -7,14 +7,17 @@ #include #include -/* Note: this used to be in include/uapi/linux/gen_stats.h */ -struct gnet_stats_basic_packed { - __u64 bytes; - __u64 packets; -}; - -struct gnet_stats_basic_cpu { - struct gnet_stats_basic_packed bstats; +/* Throughput stats. + * Must be initialized beforehand with gnet_stats_basic_sync_init(). + * + * If no reads can ever occur parallel to writes (e.g. stack-allocated + * bstats), then the internal stat values can be written to and read + * from directly. Otherwise, use _bstats_set/update() for writes and + * gnet_stats_add_basic() for reads. + */ +struct gnet_stats_basic_sync { + u64_stats_t bytes; + u64_stats_t packets; struct u64_stats_sync syncp; } __aligned(2 * sizeof(u64)); @@ -34,6 +37,7 @@ struct gnet_dump { struct tc_stats tc_stats; }; +void gnet_stats_basic_sync_init(struct gnet_stats_basic_sync *b); int gnet_stats_start_copy(struct sk_buff *skb, int type, spinlock_t *lock, struct gnet_dump *d, int padattr); @@ -42,41 +46,38 @@ int gnet_stats_start_copy_compat(struct sk_buff *skb, int type, spinlock_t *lock, struct gnet_dump *d, int padattr); -int gnet_stats_copy_basic(const seqcount_t *running, - struct gnet_dump *d, - struct gnet_stats_basic_cpu __percpu *cpu, - struct gnet_stats_basic_packed *b); -void __gnet_stats_copy_basic(const seqcount_t *running, - struct gnet_stats_basic_packed *bstats, - struct gnet_stats_basic_cpu __percpu *cpu, - struct gnet_stats_basic_packed *b); -int gnet_stats_copy_basic_hw(const seqcount_t *running, - struct gnet_dump *d, - struct gnet_stats_basic_cpu __percpu *cpu, - struct gnet_stats_basic_packed *b); +int gnet_stats_copy_basic(struct gnet_dump *d, + struct gnet_stats_basic_sync __percpu *cpu, + struct gnet_stats_basic_sync *b, bool running); +void gnet_stats_add_basic(struct gnet_stats_basic_sync *bstats, + struct gnet_stats_basic_sync __percpu *cpu, + struct gnet_stats_basic_sync *b, bool running); +int gnet_stats_copy_basic_hw(struct gnet_dump *d, + struct gnet_stats_basic_sync __percpu *cpu, + struct gnet_stats_basic_sync *b, bool running); int gnet_stats_copy_rate_est(struct gnet_dump *d, struct net_rate_estimator __rcu **ptr); int gnet_stats_copy_queue(struct gnet_dump *d, struct gnet_stats_queue __percpu *cpu_q, struct gnet_stats_queue *q, __u32 qlen); -void __gnet_stats_copy_queue(struct gnet_stats_queue *qstats, - const struct gnet_stats_queue __percpu *cpu_q, - const struct gnet_stats_queue *q, __u32 qlen); +void gnet_stats_add_queue(struct gnet_stats_queue *qstats, + const struct gnet_stats_queue __percpu *cpu_q, + const struct gnet_stats_queue *q); int gnet_stats_copy_app(struct gnet_dump *d, void *st, int len); int gnet_stats_finish_copy(struct gnet_dump *d); -int gen_new_estimator(struct gnet_stats_basic_packed *bstats, - struct gnet_stats_basic_cpu __percpu *cpu_bstats, +int gen_new_estimator(struct gnet_stats_basic_sync *bstats, + struct gnet_stats_basic_sync __percpu *cpu_bstats, struct net_rate_estimator __rcu **rate_est, spinlock_t *lock, - seqcount_t *running, struct nlattr *opt); + bool running, struct nlattr *opt); void gen_kill_estimator(struct net_rate_estimator __rcu **ptr); -int gen_replace_estimator(struct gnet_stats_basic_packed *bstats, - struct gnet_stats_basic_cpu __percpu *cpu_bstats, +int gen_replace_estimator(struct gnet_stats_basic_sync *bstats, + struct gnet_stats_basic_sync __percpu *cpu_bstats, struct net_rate_estimator __rcu **ptr, spinlock_t *lock, - seqcount_t *running, struct nlattr *opt); + bool running, struct nlattr *opt); bool gen_estimator_active(struct net_rate_estimator __rcu **ptr); bool gen_estimator_read(struct net_rate_estimator __rcu **ptr, struct gnet_stats_rate_est64 *sample); diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index b06c2d02ec84..fa6a87246a7b 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -289,7 +289,7 @@ static inline void inet_csk_prepare_for_destroy_sock(struct sock *sk) { /* The below has to be done to allow calling inet_csk_destroy_sock */ sock_set_flag(sk, SOCK_DEAD); - percpu_counter_inc(sk->sk_prot->orphan_count); + this_cpu_inc(*sk->sk_prot->orphan_count); } void inet_csk_destroy_sock(struct sock *sk); diff --git a/include/net/inet_ecn.h b/include/net/inet_ecn.h index ba77f47ef61e..ea32393464a2 100644 --- a/include/net/inet_ecn.h +++ b/include/net/inet_ecn.h @@ -188,6 +188,23 @@ static inline int INET_ECN_set_ce(struct sk_buff *skb) return 0; } +static inline int skb_get_dsfield(struct sk_buff *skb) +{ + switch (skb_protocol(skb, true)) { + case cpu_to_be16(ETH_P_IP): + if (!pskb_network_may_pull(skb, sizeof(struct iphdr))) + break; + return ipv4_get_dsfield(ip_hdr(skb)); + + case cpu_to_be16(ETH_P_IPV6): + if (!pskb_network_may_pull(skb, sizeof(struct ipv6hdr))) + break; + return ipv6_get_dsfield(ipv6_hdr(skb)); + } + + return -1; +} + static inline int INET_ECN_set_ect1(struct sk_buff *skb) { switch (skb_protocol(skb, true)) { diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 7cb5a1aace40..ff1804a0c469 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -931,6 +931,7 @@ struct netns_ipvs { int sysctl_conn_reuse_mode; int sysctl_schedule_icmp; int sysctl_ignore_tunneled; + int sysctl_run_estimation; /* ip_vs_lblc */ int sysctl_lblc_expiration; @@ -1071,6 +1072,11 @@ static inline int sysctl_cache_bypass(struct netns_ipvs *ipvs) return ipvs->sysctl_cache_bypass; } +static inline int sysctl_run_estimation(struct netns_ipvs *ipvs) +{ + return ipvs->sysctl_run_estimation; +} + #else static inline int sysctl_sync_threshold(struct netns_ipvs *ipvs) @@ -1163,6 +1169,11 @@ static inline int sysctl_cache_bypass(struct netns_ipvs *ipvs) return 0; } +static inline int sysctl_run_estimation(struct netns_ipvs *ipvs) +{ + return 1; +} + #endif /* IPVS core functions diff --git a/include/net/llc.h b/include/net/llc.h index df282d9b4017..fd1f9a3fd8dd 100644 --- a/include/net/llc.h +++ b/include/net/llc.h @@ -133,7 +133,7 @@ static inline void llc_sap_put(struct llc_sap *sap) struct llc_sap *llc_sap_find(unsigned char sap_value); int llc_build_and_send_ui_pkt(struct llc_sap *sap, struct sk_buff *skb, - unsigned char *dmac, unsigned char dsap); + const unsigned char *dmac, unsigned char dsap); void llc_sap_handler(struct llc_sap *sap, struct sk_buff *skb); void llc_conn_handler(struct llc_sap *sap, struct sk_buff *skb); diff --git a/include/net/llc_if.h b/include/net/llc_if.h index 8d5c543cd620..c72570a21a4f 100644 --- a/include/net/llc_if.h +++ b/include/net/llc_if.h @@ -62,7 +62,8 @@ #define LLC_STATUS_CONFLICT 7 /* disconnect conn */ #define LLC_STATUS_RESET_DONE 8 /* */ -int llc_establish_connection(struct sock *sk, u8 *lmac, u8 *dmac, u8 dsap); +int llc_establish_connection(struct sock *sk, const u8 *lmac, u8 *dmac, + u8 dsap); int llc_build_and_send_pkt(struct sock *sk, struct sk_buff *skb); int llc_send_disc(struct sock *sk); #endif /* LLC_IF_H */ diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 618d1f427cb2..dd757f0987b0 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -632,6 +632,10 @@ struct ieee80211_fils_discovery { * @s1g: BSS is S1G BSS (affects Association Request format). * @beacon_tx_rate: The configured beacon transmit rate that needs to be passed * to driver when rate control is offloaded to firmware. + * @power_type: power type of BSS for 6 GHz + * @tx_pwr_env: transmit power envelope array of BSS. + * @tx_pwr_env_num: number of @tx_pwr_env. + * @pwr_reduction: power constraint of BSS. */ struct ieee80211_bss_conf { const u8 *bssid; @@ -702,6 +706,10 @@ struct ieee80211_bss_conf { u32 unsol_bcast_probe_resp_interval; bool s1g; struct cfg80211_bitrate_mask beacon_tx_rate; + enum ieee80211_ap_reg_power power_type; + struct ieee80211_tx_pwr_env tx_pwr_env[IEEE80211_TPE_MAX_IE_COUNT]; + u8 tx_pwr_env_num; + u8 pwr_reduction; }; /** @@ -1715,6 +1723,7 @@ enum ieee80211_offload_flags { * write-protected by sdata_lock and local->mtx so holding either is fine * for read access. * @color_change_color: the bss color that will be used after the change. + * @mbssid_tx_vif: Pointer to the transmitting interface if MBSSID is enabled. */ struct ieee80211_vif { enum nl80211_iftype type; @@ -1746,6 +1755,8 @@ struct ieee80211_vif { bool color_change_active; u8 color_change_color; + struct ieee80211_vif *mbssid_tx_vif; + /* must be last */ u8 drv_priv[] __aligned(sizeof(void *)); }; diff --git a/include/net/ndisc.h b/include/net/ndisc.h index 38e4094960ce..04341d86585d 100644 --- a/include/net/ndisc.h +++ b/include/net/ndisc.h @@ -137,7 +137,7 @@ struct ndisc_options *ndisc_parse_options(const struct net_device *dev, u8 *opt, int opt_len, struct ndisc_options *ndopts); -void __ndisc_fill_addr_option(struct sk_buff *skb, int type, void *data, +void __ndisc_fill_addr_option(struct sk_buff *skb, int type, const void *data, int data_len, int pad); #define NDISC_OPS_REDIRECT_DATA_SPACE 2 diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 22ced1381ede..e8e48be66755 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -144,17 +144,18 @@ struct neighbour { struct timer_list timer; unsigned long used; atomic_t probes; - __u8 flags; - __u8 nud_state; - __u8 type; - __u8 dead; + u8 nud_state; + u8 type; + u8 dead; u8 protocol; + u32 flags; seqlock_t ha_lock; unsigned char ha[ALIGN(MAX_ADDR_LEN, sizeof(unsigned long))] __aligned(8); struct hh_cache hh; int (*output)(struct neighbour *, struct sk_buff *); const struct neigh_ops *ops; struct list_head gc_list; + struct list_head managed_list; struct rcu_head rcu; struct net_device *dev; u8 primary_key[0]; @@ -172,7 +173,7 @@ struct pneigh_entry { struct pneigh_entry *next; possible_net_t net; struct net_device *dev; - u8 flags; + u32 flags; u8 protocol; u8 key[]; }; @@ -216,11 +217,13 @@ struct neigh_table { int gc_thresh3; unsigned long last_flush; struct delayed_work gc_work; + struct delayed_work managed_work; struct timer_list proxy_timer; struct sk_buff_head proxy_queue; atomic_t entries; atomic_t gc_entries; struct list_head gc_list; + struct list_head managed_list; rwlock_t lock; unsigned long last_rand; struct neigh_statistics __percpu *stats; @@ -250,12 +253,21 @@ static inline void *neighbour_priv(const struct neighbour *n) } /* flags for neigh_update() */ -#define NEIGH_UPDATE_F_OVERRIDE 0x00000001 -#define NEIGH_UPDATE_F_WEAK_OVERRIDE 0x00000002 -#define NEIGH_UPDATE_F_OVERRIDE_ISROUTER 0x00000004 -#define NEIGH_UPDATE_F_EXT_LEARNED 0x20000000 -#define NEIGH_UPDATE_F_ISROUTER 0x40000000 -#define NEIGH_UPDATE_F_ADMIN 0x80000000 +#define NEIGH_UPDATE_F_OVERRIDE BIT(0) +#define NEIGH_UPDATE_F_WEAK_OVERRIDE BIT(1) +#define NEIGH_UPDATE_F_OVERRIDE_ISROUTER BIT(2) +#define NEIGH_UPDATE_F_USE BIT(3) +#define NEIGH_UPDATE_F_MANAGED BIT(4) +#define NEIGH_UPDATE_F_EXT_LEARNED BIT(5) +#define NEIGH_UPDATE_F_ISROUTER BIT(6) +#define NEIGH_UPDATE_F_ADMIN BIT(7) + +/* In-kernel representation for NDA_FLAGS_EXT flags: */ +#define NTF_OLD_MASK 0xff +#define NTF_EXT_SHIFT 8 +#define NTF_EXT_MASK (NTF_EXT_MANAGED) + +#define NTF_MANAGED (NTF_EXT_MANAGED << NTF_EXT_SHIFT) extern const struct nla_policy nda_policy[]; diff --git a/include/net/netfilter/xt_rateest.h b/include/net/netfilter/xt_rateest.h index 832ab69efda5..4c3809e141f4 100644 --- a/include/net/netfilter/xt_rateest.h +++ b/include/net/netfilter/xt_rateest.h @@ -6,7 +6,7 @@ struct xt_rateest { /* keep lock and bstats on same cache line to speedup xt_rateest_tg() */ - struct gnet_stats_basic_packed bstats; + struct gnet_stats_basic_sync bstats; spinlock_t lock; diff --git a/include/net/page_pool.h b/include/net/page_pool.h index a4082406a003..3855f069627f 100644 --- a/include/net/page_pool.h +++ b/include/net/page_pool.h @@ -216,24 +216,14 @@ static inline void page_pool_recycle_direct(struct page_pool *pool, page_pool_put_full_page(pool, page, true); } -#define PAGE_POOL_DMA_USE_PP_FRAG_COUNT \ - (sizeof(dma_addr_t) > sizeof(unsigned long)) - static inline dma_addr_t page_pool_get_dma_addr(struct page *page) { - dma_addr_t ret = page->dma_addr; - - if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT) - ret |= (dma_addr_t)page->dma_addr_upper << 16 << 16; - - return ret; + return page->dma_addr; } static inline void page_pool_set_dma_addr(struct page *page, dma_addr_t addr) { page->dma_addr = addr; - if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT) - page->dma_addr_upper = upper_32_bits(addr); } static inline void page_pool_set_frag_count(struct page *page, long nr) diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 83a6d0792180..193f88ebf629 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -765,7 +765,7 @@ struct tc_cookie { }; struct tc_qopt_offload_stats { - struct gnet_stats_basic_packed *bstats; + struct gnet_stats_basic_sync *bstats; struct gnet_stats_queue *qstats; }; @@ -885,7 +885,7 @@ struct tc_gred_qopt_offload_params { }; struct tc_gred_qopt_offload_stats { - struct gnet_stats_basic_packed bstats[MAX_DPs]; + struct gnet_stats_basic_sync bstats[MAX_DPs]; struct gnet_stats_queue qstats[MAX_DPs]; struct red_stats *xstats[MAX_DPs]; }; @@ -977,6 +977,7 @@ enum tc_tbf_command { TC_TBF_REPLACE, TC_TBF_DESTROY, TC_TBF_STATS, + TC_TBF_GRAFT, }; struct tc_tbf_qopt_offload_replace_params { @@ -992,6 +993,7 @@ struct tc_tbf_qopt_offload { union { struct tc_tbf_qopt_offload_replace_params replace_params; struct tc_qopt_offload_stats stats; + u32 child_handle; }; }; diff --git a/include/net/rose.h b/include/net/rose.h index cf517d306a28..0f0a4ce0fee7 100644 --- a/include/net/rose.h +++ b/include/net/rose.h @@ -162,8 +162,8 @@ extern int sysctl_rose_link_fail_timeout; extern int sysctl_rose_maximum_vcs; extern int sysctl_rose_window_size; -int rosecmp(rose_address *, rose_address *); -int rosecmpm(rose_address *, rose_address *, unsigned short); +int rosecmp(const rose_address *, const rose_address *); +int rosecmpm(const rose_address *, const rose_address *, unsigned short); char *rose2asc(char *buf, const rose_address *); struct sock *rose_find_socket(unsigned int, struct rose_neigh *); void rose_kill_by_neigh(struct rose_neigh *); @@ -205,8 +205,8 @@ extern const struct seq_operations rose_node_seqops; extern struct seq_operations rose_route_seqops; void rose_add_loopback_neigh(void); -int __must_check rose_add_loopback_node(rose_address *); -void rose_del_loopback_node(rose_address *); +int __must_check rose_add_loopback_node(const rose_address *); +void rose_del_loopback_node(const rose_address *); void rose_rt_device_down(struct net_device *); void rose_link_device_down(struct net_device *); struct net_device *rose_dev_first(void); diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 5a011f8d394e..ada02c4a4f51 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -40,6 +40,13 @@ enum qdisc_state_t { __QDISC_STATE_DRAINING, }; +enum qdisc_state2_t { + /* Only for !TCQ_F_NOLOCK qdisc. Never access it directly. + * Use qdisc_run_begin/end() or qdisc_is_running() instead. + */ + __QDISC_STATE2_RUNNING, +}; + #define QDISC_STATE_MISSED BIT(__QDISC_STATE_MISSED) #define QDISC_STATE_DRAINING BIT(__QDISC_STATE_DRAINING) @@ -97,7 +104,7 @@ struct Qdisc { struct netdev_queue *dev_queue; struct net_rate_estimator __rcu *rate_est; - struct gnet_stats_basic_cpu __percpu *cpu_bstats; + struct gnet_stats_basic_sync __percpu *cpu_bstats; struct gnet_stats_queue __percpu *cpu_qstats; int pad; refcount_t refcnt; @@ -107,10 +114,10 @@ struct Qdisc { */ struct sk_buff_head gso_skb ____cacheline_aligned_in_smp; struct qdisc_skb_head q; - struct gnet_stats_basic_packed bstats; - seqcount_t running; + struct gnet_stats_basic_sync bstats; struct gnet_stats_queue qstats; unsigned long state; + unsigned long state2; /* must be written under qdisc spinlock */ struct Qdisc *next_sched; struct sk_buff_head skb_bad_txq; @@ -143,11 +150,15 @@ static inline struct Qdisc *qdisc_refcount_inc_nz(struct Qdisc *qdisc) return NULL; } +/* For !TCQ_F_NOLOCK qdisc: callers must either call this within a qdisc + * root_lock section, or provide their own memory barriers -- ordering + * against qdisc_run_begin/end() atomic bit operations. + */ static inline bool qdisc_is_running(struct Qdisc *qdisc) { if (qdisc->flags & TCQ_F_NOLOCK) return spin_is_locked(&qdisc->seqlock); - return (raw_read_seqcount(&qdisc->running) & 1) ? true : false; + return test_bit(__QDISC_STATE2_RUNNING, &qdisc->state2); } static inline bool nolock_qdisc_is_empty(const struct Qdisc *qdisc) @@ -167,6 +178,9 @@ static inline bool qdisc_is_empty(const struct Qdisc *qdisc) return !READ_ONCE(qdisc->q.qlen); } +/* For !TCQ_F_NOLOCK qdisc, qdisc_run_begin/end() must be invoked with + * the qdisc root lock acquired. + */ static inline bool qdisc_run_begin(struct Qdisc *qdisc) { if (qdisc->flags & TCQ_F_NOLOCK) { @@ -206,15 +220,8 @@ static inline bool qdisc_run_begin(struct Qdisc *qdisc) * after it releases the lock at the end of qdisc_run_end(). */ return spin_trylock(&qdisc->seqlock); - } else if (qdisc_is_running(qdisc)) { - return false; } - /* Variant of write_seqcount_begin() telling lockdep a trylock - * was attempted. - */ - raw_write_seqcount_begin(&qdisc->running); - seqcount_acquire(&qdisc->running.dep_map, 0, 1, _RET_IP_); - return true; + return !__test_and_set_bit(__QDISC_STATE2_RUNNING, &qdisc->state2); } static inline void qdisc_run_end(struct Qdisc *qdisc) @@ -226,7 +233,7 @@ static inline void qdisc_run_end(struct Qdisc *qdisc) &qdisc->state))) __netif_schedule(qdisc); } else { - write_seqcount_end(&qdisc->running); + __clear_bit(__QDISC_STATE2_RUNNING, &qdisc->state2); } } @@ -592,14 +599,6 @@ static inline spinlock_t *qdisc_root_sleeping_lock(const struct Qdisc *qdisc) return qdisc_lock(root); } -static inline seqcount_t *qdisc_root_sleeping_running(const struct Qdisc *qdisc) -{ - struct Qdisc *root = qdisc_root_sleeping(qdisc); - - ASSERT_RTNL(); - return &root->running; -} - static inline struct net_device *qdisc_dev(const struct Qdisc *qdisc) { return qdisc->dev_queue->dev; @@ -849,14 +848,16 @@ static inline int qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, return sch->enqueue(skb, sch, to_free); } -static inline void _bstats_update(struct gnet_stats_basic_packed *bstats, +static inline void _bstats_update(struct gnet_stats_basic_sync *bstats, __u64 bytes, __u32 packets) { - bstats->bytes += bytes; - bstats->packets += packets; + u64_stats_update_begin(&bstats->syncp); + u64_stats_add(&bstats->bytes, bytes); + u64_stats_add(&bstats->packets, packets); + u64_stats_update_end(&bstats->syncp); } -static inline void bstats_update(struct gnet_stats_basic_packed *bstats, +static inline void bstats_update(struct gnet_stats_basic_sync *bstats, const struct sk_buff *skb) { _bstats_update(bstats, @@ -864,26 +865,10 @@ static inline void bstats_update(struct gnet_stats_basic_packed *bstats, skb_is_gso(skb) ? skb_shinfo(skb)->gso_segs : 1); } -static inline void _bstats_cpu_update(struct gnet_stats_basic_cpu *bstats, - __u64 bytes, __u32 packets) -{ - u64_stats_update_begin(&bstats->syncp); - _bstats_update(&bstats->bstats, bytes, packets); - u64_stats_update_end(&bstats->syncp); -} - -static inline void bstats_cpu_update(struct gnet_stats_basic_cpu *bstats, - const struct sk_buff *skb) -{ - u64_stats_update_begin(&bstats->syncp); - bstats_update(&bstats->bstats, skb); - u64_stats_update_end(&bstats->syncp); -} - static inline void qdisc_bstats_cpu_update(struct Qdisc *sch, const struct sk_buff *skb) { - bstats_cpu_update(this_cpu_ptr(sch->cpu_bstats), skb); + bstats_update(this_cpu_ptr(sch->cpu_bstats), skb); } static inline void qdisc_bstats_update(struct Qdisc *sch, @@ -972,10 +957,9 @@ static inline void qdisc_qstats_qlen_backlog(struct Qdisc *sch, __u32 *qlen, __u32 *backlog) { struct gnet_stats_queue qstats = { 0 }; - __u32 len = qdisc_qlen_sum(sch); - __gnet_stats_copy_queue(&qstats, sch->cpu_qstats, &sch->qstats, len); - *qlen = qstats.qlen; + gnet_stats_add_queue(&qstats, sch->cpu_qstats, &sch->qstats); + *qlen = qstats.qlen + qdisc_qlen(sch); *backlog = qstats.backlog; } @@ -1316,7 +1300,7 @@ void psched_ppscfg_precompute(struct psched_pktrate *r, u64 pktrate64); struct mini_Qdisc { struct tcf_proto *filter_list; struct tcf_block *block; - struct gnet_stats_basic_cpu __percpu *cpu_bstats; + struct gnet_stats_basic_sync __percpu *cpu_bstats; struct gnet_stats_queue __percpu *cpu_qstats; struct rcu_head rcu; }; @@ -1324,7 +1308,7 @@ struct mini_Qdisc { static inline void mini_qdisc_bstats_cpu_update(struct mini_Qdisc *miniq, const struct sk_buff *skb) { - bstats_cpu_update(this_cpu_ptr(miniq->cpu_bstats), skb); + bstats_update(this_cpu_ptr(miniq->cpu_bstats), skb); } static inline void mini_qdisc_qstats_cpu_drop(struct mini_Qdisc *miniq) diff --git a/include/net/sock.h b/include/net/sock.h index afd6b4303335..9cae042c9991 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1235,7 +1235,7 @@ struct proto { unsigned int useroffset; /* Usercopy region offset */ unsigned int usersize; /* Usercopy region size */ - struct percpu_counter *orphan_count; + unsigned int __percpu *orphan_count; struct request_sock_ops *rsk_prot; struct timewait_sock_ops *twsk_prot; @@ -2836,6 +2836,10 @@ void sock_set_sndtimeo(struct sock *sk, s64 secs); int sock_bind_add(struct sock *sk, struct sockaddr *addr, int addr_len); +int sock_get_timeout(long timeo, void *optval, bool old_timeval); +int sock_copy_user_timeval(struct __kernel_sock_timeval *tv, + sockptr_t optval, int optlen, bool old_timeval); + static inline bool sk_is_readable(struct sock *sk) { if (sk->sk_prot->sock_is_readable) diff --git a/include/net/tcp.h b/include/net/tcp.h index 10f3a37eceb2..d62467a0094f 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -48,7 +48,9 @@ extern struct inet_hashinfo tcp_hashinfo; -extern struct percpu_counter tcp_orphan_count; +DECLARE_PER_CPU(unsigned int, tcp_orphan_count); +int tcp_orphan_count_sum(void); + void tcp_time_wait(struct sock *sk, int state, int timeo); #define MAX_TCP_HEADER L1_CACHE_ALIGN(128 + MAX_HEADER) @@ -290,19 +292,6 @@ static inline bool tcp_out_of_memory(struct sock *sk) void sk_forced_mem_schedule(struct sock *sk, int size); -static inline bool tcp_too_many_orphans(struct sock *sk, int shift) -{ - struct percpu_counter *ocp = sk->sk_prot->orphan_count; - int orphans = percpu_counter_read_positive(ocp); - - if (orphans << shift > sysctl_tcp_max_orphans) { - orphans = percpu_counter_sum_positive(ocp); - if (orphans << shift > sysctl_tcp_max_orphans) - return true; - } - return false; -} - bool tcp_check_oom(struct sock *sk, int shift); diff --git a/include/soc/fsl/dpaa2-io.h b/include/soc/fsl/dpaa2-io.h index c9d849924f89..4bf62de2e00e 100644 --- a/include/soc/fsl/dpaa2-io.h +++ b/include/soc/fsl/dpaa2-io.h @@ -44,6 +44,7 @@ struct device; * @regs_cinh: The cache inhibited regs * @dpio_id: The dpio index * @qman_version: The qman version + * @qman_clk: The qman clock frequency in Hz * * Describes the attributes and features of the DPIO object. */ @@ -55,6 +56,7 @@ struct dpaa2_io_desc { void __iomem *regs_cinh; int dpio_id; u32 qman_version; + u32 qman_clk; }; struct dpaa2_io *dpaa2_io_create(const struct dpaa2_io_desc *desc, @@ -129,4 +131,11 @@ int dpaa2_io_query_fq_count(struct dpaa2_io *d, u32 fqid, u32 *fcnt, u32 *bcnt); int dpaa2_io_query_bp_count(struct dpaa2_io *d, u16 bpid, u32 *num); + +int dpaa2_io_set_irq_coalescing(struct dpaa2_io *d, u32 irq_holdoff); +void dpaa2_io_get_irq_coalescing(struct dpaa2_io *d, u32 *irq_holdoff); +void dpaa2_io_set_adaptive_coalescing(struct dpaa2_io *d, + int use_adaptive_rx_coalesce); +int dpaa2_io_get_adaptive_coalescing(struct dpaa2_io *d); +void dpaa2_io_update_net_dim(struct dpaa2_io *d, __u64 frames, __u64 bytes); #endif /* __FSL_DPAA2_IO_H */ diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index d7055b41982d..9b872da0c246 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -563,9 +563,22 @@ struct ocelot_vcap_block { int pol_lpr; }; -struct ocelot_vlan { - bool valid; +struct ocelot_bridge_vlan { u16 vid; + unsigned long portmask; + unsigned long untagged; + struct list_head list; +}; + +enum ocelot_port_tag_config { + /* all VLANs are egress-untagged */ + OCELOT_PORT_TAG_DISABLED = 0, + /* all VLANs except the native VLAN and VID 0 are egress-tagged */ + OCELOT_PORT_TAG_NATIVE = 1, + /* all VLANs except VID 0 are egress-tagged */ + OCELOT_PORT_TAG_TRUNK_NO_VID0 = 2, + /* all VLANs are egress-tagged */ + OCELOT_PORT_TAG_TRUNK = 3, }; enum ocelot_sb { @@ -590,9 +603,7 @@ struct ocelot_port { bool vlan_aware; /* VLAN that untagged frames are classified to, on ingress */ - struct ocelot_vlan pvid_vlan; - /* The VLAN ID that will be transmitted as untagged, on egress */ - struct ocelot_vlan native_vlan; + const struct ocelot_bridge_vlan *pvid_vlan; unsigned int ptp_skbs_in_flight; u8 ptp_cmd; @@ -635,8 +646,7 @@ struct ocelot { u8 base_mac[ETH_ALEN]; - /* Keep track of the vlan port masks */ - u32 vlan_mask[VLAN_N_VID]; + struct list_head vlans; /* Switches like VSC9959 have flooding per traffic class */ int num_flooding_pgids; diff --git a/include/trace/events/devlink.h b/include/trace/events/devlink.h index 44d8e2981065..2814f188d98c 100644 --- a/include/trace/events/devlink.h +++ b/include/trace/events/devlink.h @@ -21,9 +21,9 @@ TRACE_EVENT(devlink_hwmsg, TP_ARGS(devlink, incoming, type, buf, len), TP_STRUCT__entry( - __string(bus_name, devlink->dev->bus->name) - __string(dev_name, dev_name(devlink->dev)) - __string(driver_name, devlink->dev->driver->name) + __string(bus_name, devlink_to_dev(devlink)->bus->name) + __string(dev_name, dev_name(devlink_to_dev(devlink))) + __string(driver_name, devlink_to_dev(devlink)->driver->name) __field(bool, incoming) __field(unsigned long, type) __dynamic_array(u8, buf, len) @@ -31,9 +31,9 @@ TRACE_EVENT(devlink_hwmsg, ), TP_fast_assign( - __assign_str(bus_name, devlink->dev->bus->name); - __assign_str(dev_name, dev_name(devlink->dev)); - __assign_str(driver_name, devlink->dev->driver->name); + __assign_str(bus_name, devlink_to_dev(devlink)->bus->name); + __assign_str(dev_name, dev_name(devlink_to_dev(devlink))); + __assign_str(driver_name, devlink_to_dev(devlink)->driver->name); __entry->incoming = incoming; __entry->type = type; memcpy(__get_dynamic_array(buf), buf, len); @@ -55,17 +55,17 @@ TRACE_EVENT(devlink_hwerr, TP_ARGS(devlink, err, msg), TP_STRUCT__entry( - __string(bus_name, devlink->dev->bus->name) - __string(dev_name, dev_name(devlink->dev)) - __string(driver_name, devlink->dev->driver->name) + __string(bus_name, devlink_to_dev(devlink)->bus->name) + __string(dev_name, dev_name(devlink_to_dev(devlink))) + __string(driver_name, devlink_to_dev(devlink)->driver->name) __field(int, err) __string(msg, msg) ), TP_fast_assign( - __assign_str(bus_name, devlink->dev->bus->name); - __assign_str(dev_name, dev_name(devlink->dev)); - __assign_str(driver_name, devlink->dev->driver->name); + __assign_str(bus_name, devlink_to_dev(devlink)->bus->name); + __assign_str(dev_name, dev_name(devlink_to_dev(devlink))); + __assign_str(driver_name, devlink_to_dev(devlink)->driver->name); __entry->err = err; __assign_str(msg, msg); ), @@ -85,17 +85,17 @@ TRACE_EVENT(devlink_health_report, TP_ARGS(devlink, reporter_name, msg), TP_STRUCT__entry( - __string(bus_name, devlink->dev->bus->name) - __string(dev_name, dev_name(devlink->dev)) - __string(driver_name, devlink->dev->driver->name) + __string(bus_name, devlink_to_dev(devlink)->bus->name) + __string(dev_name, dev_name(devlink_to_dev(devlink))) + __string(driver_name, devlink_to_dev(devlink)->driver->name) __string(reporter_name, msg) __string(msg, msg) ), TP_fast_assign( - __assign_str(bus_name, devlink->dev->bus->name); - __assign_str(dev_name, dev_name(devlink->dev)); - __assign_str(driver_name, devlink->dev->driver->name); + __assign_str(bus_name, devlink_to_dev(devlink)->bus->name); + __assign_str(dev_name, dev_name(devlink_to_dev(devlink))); + __assign_str(driver_name, devlink_to_dev(devlink)->driver->name); __assign_str(reporter_name, reporter_name); __assign_str(msg, msg); ), @@ -116,18 +116,18 @@ TRACE_EVENT(devlink_health_recover_aborted, TP_ARGS(devlink, reporter_name, health_state, time_since_last_recover), TP_STRUCT__entry( - __string(bus_name, devlink->dev->bus->name) - __string(dev_name, dev_name(devlink->dev)) - __string(driver_name, devlink->dev->driver->name) + __string(bus_name, devlink_to_dev(devlink)->bus->name) + __string(dev_name, dev_name(devlink_to_dev(devlink))) + __string(driver_name, devlink_to_dev(devlink)->driver->name) __string(reporter_name, reporter_name) __field(bool, health_state) __field(u64, time_since_last_recover) ), TP_fast_assign( - __assign_str(bus_name, devlink->dev->bus->name); - __assign_str(dev_name, dev_name(devlink->dev)); - __assign_str(driver_name, devlink->dev->driver->name); + __assign_str(bus_name, devlink_to_dev(devlink)->bus->name); + __assign_str(dev_name, dev_name(devlink_to_dev(devlink))); + __assign_str(driver_name, devlink_to_dev(devlink)->driver->name); __assign_str(reporter_name, reporter_name); __entry->health_state = health_state; __entry->time_since_last_recover = time_since_last_recover; @@ -150,17 +150,17 @@ TRACE_EVENT(devlink_health_reporter_state_update, TP_ARGS(devlink, reporter_name, new_state), TP_STRUCT__entry( - __string(bus_name, devlink->dev->bus->name) - __string(dev_name, dev_name(devlink->dev)) - __string(driver_name, devlink->dev->driver->name) + __string(bus_name, devlink_to_dev(devlink)->bus->name) + __string(dev_name, dev_name(devlink_to_dev(devlink))) + __string(driver_name, devlink_to_dev(devlink)->driver->name) __string(reporter_name, reporter_name) __field(u8, new_state) ), TP_fast_assign( - __assign_str(bus_name, devlink->dev->bus->name); - __assign_str(dev_name, dev_name(devlink->dev)); - __assign_str(driver_name, devlink->dev->driver->name); + __assign_str(bus_name, devlink_to_dev(devlink)->bus->name); + __assign_str(dev_name, dev_name(devlink_to_dev(devlink))); + __assign_str(driver_name, devlink_to_dev(devlink)->driver->name); __assign_str(reporter_name, reporter_name); __entry->new_state = new_state; ), @@ -181,9 +181,9 @@ TRACE_EVENT(devlink_trap_report, TP_ARGS(devlink, skb, metadata), TP_STRUCT__entry( - __string(bus_name, devlink->dev->bus->name) - __string(dev_name, dev_name(devlink->dev)) - __string(driver_name, devlink->dev->driver->name) + __string(bus_name, devlink_to_dev(devlink)->bus->name) + __string(dev_name, dev_name(devlink_to_dev(devlink))) + __string(driver_name, devlink_to_dev(devlink)->driver->name) __string(trap_name, metadata->trap_name) __string(trap_group_name, metadata->trap_group_name) __dynamic_array(char, input_dev_name, IFNAMSIZ) @@ -192,9 +192,9 @@ TRACE_EVENT(devlink_trap_report, TP_fast_assign( struct net_device *input_dev = metadata->input_dev; - __assign_str(bus_name, devlink->dev->bus->name); - __assign_str(dev_name, dev_name(devlink->dev)); - __assign_str(driver_name, devlink->dev->driver->name); + __assign_str(bus_name, devlink_to_dev(devlink)->bus->name); + __assign_str(dev_name, dev_name(devlink_to_dev(devlink))); + __assign_str(driver_name, devlink_to_dev(devlink)->driver->name); __assign_str(trap_name, metadata->trap_name); __assign_str(trap_group_name, metadata->trap_group_name); __assign_str(input_dev_name, diff --git a/include/uapi/linux/if_ether.h b/include/uapi/linux/if_ether.h index 5f589c7a8382..5da4ee234e0b 100644 --- a/include/uapi/linux/if_ether.h +++ b/include/uapi/linux/if_ether.h @@ -86,6 +86,7 @@ * over Ethernet */ #define ETH_P_PAE 0x888E /* Port Access Entity (IEEE 802.1X) */ +#define ETH_P_REALTEK 0x8899 /* Multiple proprietary protocols */ #define ETH_P_AOE 0x88A2 /* ATA over Ethernet */ #define ETH_P_8021AD 0x88A8 /* 802.1ad Service VLAN */ #define ETH_P_802_EX1 0x88B5 /* 802.1 Local Experimental 1. */ diff --git a/include/uapi/linux/neighbour.h b/include/uapi/linux/neighbour.h index 00a60695fa53..db05fb55055e 100644 --- a/include/uapi/linux/neighbour.h +++ b/include/uapi/linux/neighbour.h @@ -31,6 +31,7 @@ enum { NDA_PROTOCOL, /* Originator of entry */ NDA_NH_ID, NDA_FDB_EXT_ATTRS, + NDA_FLAGS_EXT, __NDA_MAX }; @@ -40,14 +41,16 @@ enum { * Neighbor Cache Entry Flags */ -#define NTF_USE 0x01 -#define NTF_SELF 0x02 -#define NTF_MASTER 0x04 -#define NTF_PROXY 0x08 /* == ATF_PUBL */ -#define NTF_EXT_LEARNED 0x10 -#define NTF_OFFLOADED 0x20 -#define NTF_STICKY 0x40 -#define NTF_ROUTER 0x80 +#define NTF_USE (1 << 0) +#define NTF_SELF (1 << 1) +#define NTF_MASTER (1 << 2) +#define NTF_PROXY (1 << 3) /* == ATF_PUBL */ +#define NTF_EXT_LEARNED (1 << 4) +#define NTF_OFFLOADED (1 << 5) +#define NTF_STICKY (1 << 6) +#define NTF_ROUTER (1 << 7) +/* Extended flags under NDA_FLAGS_EXT: */ +#define NTF_EXT_MANAGED (1 << 0) /* * Neighbor Cache Entry States. @@ -65,12 +68,22 @@ enum { #define NUD_PERMANENT 0x80 #define NUD_NONE 0x00 -/* NUD_NOARP & NUD_PERMANENT are pseudostates, they never change - * and make no address resolution or NUD. - * NUD_PERMANENT also cannot be deleted by garbage collectors. +/* NUD_NOARP & NUD_PERMANENT are pseudostates, they never change and make no + * address resolution or NUD. + * + * NUD_PERMANENT also cannot be deleted by garbage collectors. This holds true + * for dynamic entries with NTF_EXT_LEARNED flag as well. However, upon carrier + * down event, NUD_PERMANENT entries are not flushed whereas NTF_EXT_LEARNED + * flagged entries explicitly are (which is also consistent with the routing + * subsystem). + * * When NTF_EXT_LEARNED is set for a bridge fdb entry the different cache entry * states don't make sense and thus are ignored. Such entries don't age and * can roam. + * + * NTF_EXT_MANAGED flagged neigbor entries are managed by the kernel on behalf + * of a user space control plane, and automatically refreshed so that (if + * possible) they remain in NUD_REACHABLE state. */ struct nda_cacheinfo { diff --git a/include/uapi/linux/netfilter.h b/include/uapi/linux/netfilter.h index ef9a44286e23..53411ccc69db 100644 --- a/include/uapi/linux/netfilter.h +++ b/include/uapi/linux/netfilter.h @@ -51,6 +51,7 @@ enum nf_inet_hooks { enum nf_dev_hooks { NF_NETDEV_INGRESS, + NF_NETDEV_EGRESS, NF_NETDEV_NUMHOOKS }; diff --git a/include/uapi/linux/nl80211-vnd-intel.h b/include/uapi/linux/nl80211-vnd-intel.h index 0bf177b84fd9..4ed7d0b24512 100644 --- a/include/uapi/linux/nl80211-vnd-intel.h +++ b/include/uapi/linux/nl80211-vnd-intel.h @@ -13,6 +13,35 @@ * enum iwl_mvm_vendor_cmd - supported vendor commands * @IWL_MVM_VENDOR_CMD_GET_CSME_CONN_INFO: reports CSME connection info. * @IWL_MVM_VENDOR_CMD_HOST_GET_OWNERSHIP: asks for ownership on the device. + * This is useful when the CSME firmware owns the device and the kernel + * wants to use it. In case the CSME firmware has no connection active the + * kernel will manage on its own to get ownership of the device. + * When the CSME firmware has an active connection, the user space + * involvement is required. The kernel will assert the RFKILL signal with + * the "device not owned" reason so that nobody can touch the device. Then + * the user space can run the following flow to be able to get connected + * to the very same AP the CSME firmware is currently connected to: + * + * 1) The user space (NetworkManager) boots and sees that the device is + * in RFKILL because the host doesn't own the device + * 2) The user space asks the kernel what AP the CSME firmware is + * connected to (with %IWL_MVM_VENDOR_CMD_GET_CSME_CONN_INFO) + * 3) The user space checks if it has a profile that matches the reply + * from the CSME firmware + * 4) The user space installs a network to the wpa_supplicant with a + * specific BSSID and a specific frequency + * 5) The user space prevents any type of full scan + * 6) The user space asks iwlmei to request ownership on the device (with + * this command) + * 7) iwlmei requests ownership from the CSME firmware + * 8) The CSME firmware grants ownership + * 9) iwlmei tells iwlwifi to lift the RFKILL + * 10) RFKILL OFF is reported to user space + * 11) The host boots the device, loads the firwmare, and connects to a + * specific BSSID without scanning including IP as fast as it can + * 12) The host reports to the CSME firmware that there is a connection + * 13) The TCP connection is preserved and the host has connectivity + * * @IWL_MVM_VENDOR_CMD_ROAMING_FORBIDDEN_EVENT: notifies if roaming is allowed. * It contains a &IWL_MVM_VENDOR_ATTR_ROAMING_FORBIDDEN and a * &IWL_MVM_VENDOR_ATTR_VIF_ADDR attributes. diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index c2efea98e060..61cab81e920d 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -300,6 +300,29 @@ * the interface goes down. */ +/** + * DOC: FILS shared key crypto offload + * + * This feature is applicable to drivers running in AP mode. + * + * FILS shared key crypto offload can be advertised by drivers by setting + * @NL80211_EXT_FEATURE_FILS_CRYPTO_OFFLOAD flag. The drivers that support + * FILS shared key crypto offload should be able to encrypt and decrypt + * association frames for FILS shared key authentication as per IEEE 802.11ai. + * With this capability, for FILS key derivation, drivers depend on userspace. + * + * After FILS key derivation, userspace shares the FILS AAD details with the + * driver and the driver stores the same to use in decryption of association + * request and in encryption of association response. The below parameters + * should be given to the driver in %NL80211_CMD_SET_FILS_AAD. + * %NL80211_ATTR_MAC - STA MAC address, used for storing FILS AAD per STA + * %NL80211_ATTR_FILS_KEK - Used for encryption or decryption + * %NL80211_ATTR_FILS_NONCES - Used for encryption or decryption + * (STA Nonce 16 bytes followed by AP Nonce 16 bytes) + * + * Once the association is done, the driver cleans the FILS AAD data. + */ + /** * enum nl80211_commands - supported nl80211 commands * @@ -337,7 +360,10 @@ * @NL80211_CMD_DEL_INTERFACE: Virtual interface was deleted, has attributes * %NL80211_ATTR_IFINDEX and %NL80211_ATTR_WIPHY. Can also be sent from * userspace to request deletion of a virtual interface, then requires - * attribute %NL80211_ATTR_IFINDEX. + * attribute %NL80211_ATTR_IFINDEX. If multiple BSSID advertisements are + * enabled using %NL80211_ATTR_MBSSID_CONFIG, %NL80211_ATTR_MBSSID_ELEMS, + * and if this command is used for the transmitting interface, then all + * the non-transmitting interfaces are deleted as well. * * @NL80211_CMD_GET_KEY: Get sequence counter information for a key specified * by %NL80211_ATTR_KEY_IDX and/or %NL80211_ATTR_MAC. @@ -1200,6 +1226,12 @@ * @NL80211_CMD_COLOR_CHANGE_COMPLETED: Notify userland that the color change * has completed * + * @NL80211_CMD_SET_FILS_AAD: Set FILS AAD data to the driver using - + * &NL80211_ATTR_MAC - for STA MAC address + * &NL80211_ATTR_FILS_KEK - for KEK + * &NL80211_ATTR_FILS_NONCES - for FILS Nonces + * (STA Nonce 16 bytes followed by AP Nonce 16 bytes) + * * @NL80211_CMD_MAX: highest used command number * @__NL80211_CMD_AFTER_LAST: internal use */ @@ -1440,6 +1472,8 @@ enum nl80211_commands { NL80211_CMD_COLOR_CHANGE_ABORTED, NL80211_CMD_COLOR_CHANGE_COMPLETED, + NL80211_CMD_SET_FILS_AAD, + /* add new commands above here */ /* used to define NL80211_CMD_MAX below */ @@ -2593,6 +2627,18 @@ enum nl80211_commands { * @NL80211_ATTR_COLOR_CHANGE_ELEMS: Nested set of attributes containing the IE * information for the time while performing a color switch. * + * @NL80211_ATTR_MBSSID_CONFIG: Nested attribute for multiple BSSID + * advertisements (MBSSID) parameters in AP mode. + * Kernel uses this attribute to indicate the driver's support for MBSSID + * and enhanced multi-BSSID advertisements (EMA AP) to the userspace. + * Userspace should use this attribute to configure per interface MBSSID + * parameters. + * See &enum nl80211_mbssid_config_attributes for details. + * + * @NL80211_ATTR_MBSSID_ELEMS: Nested parameter to pass multiple BSSID elements. + * Mandatory parameter for the transmitting interface to enable MBSSID. + * Optional for the non-transmitting interfaces. + * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use @@ -3096,6 +3142,9 @@ enum nl80211_attrs { NL80211_ATTR_COLOR_CHANGE_COLOR, NL80211_ATTR_COLOR_CHANGE_ELEMS, + NL80211_ATTR_MBSSID_CONFIG, + NL80211_ATTR_MBSSID_ELEMS, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, @@ -4929,6 +4978,7 @@ enum nl80211_txrate_gi { * @NL80211_BAND_60GHZ: around 60 GHz band (58.32 - 69.12 GHz) * @NL80211_BAND_6GHZ: around 6 GHz band (5.9 - 7.2 GHz) * @NL80211_BAND_S1GHZ: around 900MHz, supported by S1G PHYs + * @NL80211_BAND_LC: light communication band (placeholder) * @NUM_NL80211_BANDS: number of bands, avoid using this in userspace * since newer kernel versions may support more bands */ @@ -4938,6 +4988,7 @@ enum nl80211_band { NL80211_BAND_60GHZ, NL80211_BAND_6GHZ, NL80211_BAND_S1GHZ, + NL80211_BAND_LC, NUM_NL80211_BANDS, }; @@ -5995,6 +6046,11 @@ enum nl80211_feature_flags { * @NL80211_EXT_FEATURE_BSS_COLOR: The driver supports BSS color collision * detection and change announcemnts. * + * @NL80211_EXT_FEATURE_FILS_CRYPTO_OFFLOAD: Driver running in AP mode supports + * FILS encryption and decryption for (Re)Association Request and Response + * frames. Userspace has to share FILS AAD details to the driver by using + * @NL80211_CMD_SET_FILS_AAD. + * * @NUM_NL80211_EXT_FEATURES: number of extended features. * @MAX_NL80211_EXT_FEATURES: highest extended feature index. */ @@ -6060,6 +6116,7 @@ enum nl80211_ext_feature_index { NL80211_EXT_FEATURE_SECURE_RTT, NL80211_EXT_FEATURE_PROT_RANGE_NEGO_AND_MEASURE, NL80211_EXT_FEATURE_BSS_COLOR, + NL80211_EXT_FEATURE_FILS_CRYPTO_OFFLOAD, /* add new features before the definition below */ NUM_NL80211_EXT_FEATURES, @@ -7349,4 +7406,60 @@ enum nl80211_sar_specs_attrs { NL80211_SAR_ATTR_SPECS_MAX = __NL80211_SAR_ATTR_SPECS_LAST - 1, }; +/** + * enum nl80211_mbssid_config_attributes - multiple BSSID (MBSSID) and enhanced + * multi-BSSID advertisements (EMA) in AP mode. + * Kernel uses some of these attributes to advertise driver's support for + * MBSSID and EMA. + * Remaining attributes should be used by the userspace to configure the + * features. + * + * @__NL80211_MBSSID_CONFIG_ATTR_INVALID: Invalid + * + * @NL80211_MBSSID_CONFIG_ATTR_MAX_INTERFACES: Used by the kernel to advertise + * the maximum number of MBSSID interfaces supported by the driver. + * Driver should indicate MBSSID support by setting + * wiphy->mbssid_max_interfaces to a value more than or equal to 2. + * + * @NL80211_MBSSID_CONFIG_ATTR_MAX_EMA_PROFILE_PERIODICITY: Used by the kernel + * to advertise the maximum profile periodicity supported by the driver + * if EMA is enabled. Driver should indicate EMA support to the userspace + * by setting wiphy->ema_max_profile_periodicity to + * a non-zero value. + * + * @NL80211_MBSSID_CONFIG_ATTR_INDEX: Mandatory parameter to pass the index of + * this BSS (u8) in the multiple BSSID set. + * Value must be set to 0 for the transmitting interface and non-zero for + * all non-transmitting interfaces. The userspace will be responsible + * for using unique indices for the interfaces. + * Range: 0 to wiphy->mbssid_max_interfaces-1. + * + * @NL80211_MBSSID_CONFIG_ATTR_TX_IFINDEX: Mandatory parameter for + * a non-transmitted profile which provides the interface index (u32) of + * the transmitted profile. The value must match one of the interface + * indices advertised by the kernel. Optional if the interface being set up + * is the transmitting one, however, if provided then the value must match + * the interface index of the same. + * + * @NL80211_MBSSID_CONFIG_ATTR_EMA: Flag used to enable EMA AP feature. + * Setting this flag is permitted only if the driver advertises EMA support + * by setting wiphy->ema_max_profile_periodicity to non-zero. + * + * @__NL80211_MBSSID_CONFIG_ATTR_LAST: Internal + * @NL80211_MBSSID_CONFIG_ATTR_MAX: highest attribute + */ +enum nl80211_mbssid_config_attributes { + __NL80211_MBSSID_CONFIG_ATTR_INVALID, + + NL80211_MBSSID_CONFIG_ATTR_MAX_INTERFACES, + NL80211_MBSSID_CONFIG_ATTR_MAX_EMA_PROFILE_PERIODICITY, + NL80211_MBSSID_CONFIG_ATTR_INDEX, + NL80211_MBSSID_CONFIG_ATTR_TX_IFINDEX, + NL80211_MBSSID_CONFIG_ATTR_EMA, + + /* keep last */ + __NL80211_MBSSID_CONFIG_ATTR_LAST, + NL80211_MBSSID_CONFIG_ATTR_MAX = __NL80211_MBSSID_CONFIG_ATTR_LAST - 1, +}; + #endif /* __LINUX_NL80211_H */ diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h index ec88590b3198..f292b467b27f 100644 --- a/include/uapi/linux/pkt_sched.h +++ b/include/uapi/linux/pkt_sched.h @@ -840,6 +840,8 @@ enum { TCA_FQ_CODEL_CE_THRESHOLD, TCA_FQ_CODEL_DROP_BATCH_SIZE, TCA_FQ_CODEL_MEMORY_LIMIT, + TCA_FQ_CODEL_CE_THRESHOLD_SELECTOR, + TCA_FQ_CODEL_CE_THRESHOLD_MASK, __TCA_FQ_CODEL_MAX }; diff --git a/include/uapi/linux/smc.h b/include/uapi/linux/smc.h index b175bd0165a1..20f33b27787f 100644 --- a/include/uapi/linux/smc.h +++ b/include/uapi/linux/smc.h @@ -84,17 +84,28 @@ enum { SMC_NLA_SYS_IS_ISM_V2, /* u8 */ SMC_NLA_SYS_LOCAL_HOST, /* string */ SMC_NLA_SYS_SEID, /* string */ + SMC_NLA_SYS_IS_SMCR_V2, /* u8 */ __SMC_NLA_SYS_MAX, SMC_NLA_SYS_MAX = __SMC_NLA_SYS_MAX - 1 }; -/* SMC_NLA_LGR_V2 nested attributes */ +/* SMC_NLA_LGR_D_V2_COMMON and SMC_NLA_LGR_R_V2_COMMON nested attributes */ enum { SMC_NLA_LGR_V2_VER, /* u8 */ SMC_NLA_LGR_V2_REL, /* u8 */ SMC_NLA_LGR_V2_OS, /* u8 */ SMC_NLA_LGR_V2_NEG_EID, /* string */ SMC_NLA_LGR_V2_PEER_HOST, /* string */ + __SMC_NLA_LGR_V2_MAX, + SMC_NLA_LGR_V2_MAX = __SMC_NLA_LGR_V2_MAX - 1 +}; + +/* SMC_NLA_LGR_R_V2 nested attributes */ +enum { + SMC_NLA_LGR_R_V2_UNSPEC, + SMC_NLA_LGR_R_V2_DIRECT, /* u8 */ + __SMC_NLA_LGR_R_V2_MAX, + SMC_NLA_LGR_R_V2_MAX = __SMC_NLA_LGR_R_V2_MAX - 1 }; /* SMC_GEN_LGR_SMCR attributes */ @@ -106,6 +117,8 @@ enum { SMC_NLA_LGR_R_PNETID, /* string */ SMC_NLA_LGR_R_VLAN_ID, /* u8 */ SMC_NLA_LGR_R_CONNS_NUM, /* u32 */ + SMC_NLA_LGR_R_V2_COMMON, /* nest */ + SMC_NLA_LGR_R_V2, /* nest */ __SMC_NLA_LGR_R_MAX, SMC_NLA_LGR_R_MAX = __SMC_NLA_LGR_R_MAX - 1 }; @@ -138,7 +151,7 @@ enum { SMC_NLA_LGR_D_PNETID, /* string */ SMC_NLA_LGR_D_CHID, /* u16 */ SMC_NLA_LGR_D_PAD, /* flag */ - SMC_NLA_LGR_V2, /* nest */ + SMC_NLA_LGR_D_V2_COMMON, /* nest */ __SMC_NLA_LGR_D_MAX, SMC_NLA_LGR_D_MAX = __SMC_NLA_LGR_D_MAX - 1 }; diff --git a/include/uapi/linux/vm_sockets.h b/include/uapi/linux/vm_sockets.h index 46918a1852d7..c60ca33eac59 100644 --- a/include/uapi/linux/vm_sockets.h +++ b/include/uapi/linux/vm_sockets.h @@ -64,7 +64,7 @@ * timeout for a STREAM socket. */ -#define SO_VM_SOCKETS_CONNECT_TIMEOUT 6 +#define SO_VM_SOCKETS_CONNECT_TIMEOUT_OLD 6 /* Option name for using non-blocking send/receive. Use as the option name * for setsockopt(3) or getsockopt(3) to set or get the non-blocking @@ -81,6 +81,17 @@ #define SO_VM_SOCKETS_NONBLOCK_TXRX 7 +#define SO_VM_SOCKETS_CONNECT_TIMEOUT_NEW 8 + +#if !defined(__KERNEL__) +#if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__)) +#define SO_VM_SOCKETS_CONNECT_TIMEOUT SO_VM_SOCKETS_CONNECT_TIMEOUT_OLD +#else +#define SO_VM_SOCKETS_CONNECT_TIMEOUT \ + (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_VM_SOCKETS_CONNECT_TIMEOUT_OLD : SO_VM_SOCKETS_CONNECT_TIMEOUT_NEW) +#endif +#endif + /* The vSocket equivalent of INADDR_ANY. This works for the svm_cid field of * sockaddr_vm and indicates the context ID of the current endpoint. */ diff --git a/net/802/hippi.c b/net/802/hippi.c index f80b33a8f7e0..887e73d520e4 100644 --- a/net/802/hippi.c +++ b/net/802/hippi.c @@ -121,7 +121,7 @@ int hippi_mac_addr(struct net_device *dev, void *p) struct sockaddr *addr = p; if (netif_running(dev)) return -EBUSY; - memcpy(dev->dev_addr, addr->sa_data, dev->addr_len); + dev_addr_set(dev, addr->sa_data); return 0; } EXPORT_SYMBOL(hippi_mac_addr); diff --git a/net/802/p8022.c b/net/802/p8022.c index a6585627051d..79c23173116c 100644 --- a/net/802/p8022.c +++ b/net/802/p8022.c @@ -23,7 +23,7 @@ #include static int p8022_request(struct datalink_proto *dl, struct sk_buff *skb, - unsigned char *dest) + const unsigned char *dest) { llc_build_and_send_ui_pkt(dl->sap, skb, dest, dl->sap->laddr.lsap); return 0; diff --git a/net/802/psnap.c b/net/802/psnap.c index 4492e8d7ad20..1406bfdbda13 100644 --- a/net/802/psnap.c +++ b/net/802/psnap.c @@ -79,7 +79,7 @@ drop: * Put a SNAP header on a frame and pass to 802.2 */ static int snap_request(struct datalink_proto *dl, - struct sk_buff *skb, u8 *dest) + struct sk_buff *skb, const u8 *dest) { memcpy(skb_push(skb, 5), dl->type, 5); llc_build_and_send_ui_pkt(snap_sap, skb, dest, snap_sap->laddr.lsap); diff --git a/net/atm/br2684.c b/net/atm/br2684.c index dd2a8dabed84..11854fde52db 100644 --- a/net/atm/br2684.c +++ b/net/atm/br2684.c @@ -578,7 +578,7 @@ static int br2684_regvcc(struct atm_vcc *atmvcc, void __user * arg) if (list_empty(&brdev->brvccs) && !brdev->mac_was_set) { unsigned char *esi = atmvcc->dev->esi; if (esi[0] | esi[1] | esi[2] | esi[3] | esi[4] | esi[5]) - memcpy(net_dev->dev_addr, esi, net_dev->addr_len); + dev_addr_set(net_dev, esi); else net_dev->dev_addr[2] = 1; } diff --git a/net/atm/lec.c b/net/atm/lec.c index 7226c784dbe0..8eaea4a4bbd6 100644 --- a/net/atm/lec.c +++ b/net/atm/lec.c @@ -355,8 +355,7 @@ static int lec_atm_send(struct atm_vcc *vcc, struct sk_buff *skb) pr_debug("%s: msg from zeppelin:%d\n", dev->name, mesg->type); switch (mesg->type) { case l_set_mac_addr: - for (i = 0; i < 6; i++) - dev->dev_addr[i] = mesg->content.normal.mac_addr[i]; + eth_hw_addr_set(dev, mesg->content.normal.mac_addr); break; case l_del_mac_addr: for (i = 0; i < 6; i++) diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index 2631efc6e359..2f34bbdde0e8 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -202,7 +202,7 @@ struct sock *ax25_get_socket(ax25_address *my_addr, ax25_address *dest_addr, * Find an AX.25 control block given both ends. It will only pick up * floating AX.25 control blocks or non Raw socket bound control blocks. */ -ax25_cb *ax25_find_cb(ax25_address *src_addr, ax25_address *dest_addr, +ax25_cb *ax25_find_cb(const ax25_address *src_addr, ax25_address *dest_addr, ax25_digi *digi, struct net_device *dev) { ax25_cb *s; diff --git a/net/ax25/ax25_dev.c b/net/ax25/ax25_dev.c index 4ac2e0847652..d0a043a51848 100644 --- a/net/ax25/ax25_dev.c +++ b/net/ax25/ax25_dev.c @@ -35,7 +35,7 @@ ax25_dev *ax25_addr_ax25dev(ax25_address *addr) spin_lock_bh(&ax25_dev_lock); for (ax25_dev = ax25_dev_list; ax25_dev != NULL; ax25_dev = ax25_dev->next) - if (ax25cmp(addr, (ax25_address *)ax25_dev->dev->dev_addr) == 0) { + if (ax25cmp(addr, (const ax25_address *)ax25_dev->dev->dev_addr) == 0) { res = ax25_dev; } spin_unlock_bh(&ax25_dev_lock); diff --git a/net/ax25/ax25_iface.c b/net/ax25/ax25_iface.c index b4083f30af0d..979bc4b828a0 100644 --- a/net/ax25/ax25_iface.c +++ b/net/ax25/ax25_iface.c @@ -98,7 +98,7 @@ void ax25_linkfail_release(struct ax25_linkfail *lf) EXPORT_SYMBOL(ax25_linkfail_release); -int ax25_listen_register(ax25_address *callsign, struct net_device *dev) +int ax25_listen_register(const ax25_address *callsign, struct net_device *dev) { struct listen_struct *listen; @@ -121,7 +121,7 @@ int ax25_listen_register(ax25_address *callsign, struct net_device *dev) EXPORT_SYMBOL(ax25_listen_register); -void ax25_listen_release(ax25_address *callsign, struct net_device *dev) +void ax25_listen_release(const ax25_address *callsign, struct net_device *dev) { struct listen_struct *s, *listen; @@ -171,7 +171,7 @@ int (*ax25_protocol_function(unsigned int pid))(struct sk_buff *, ax25_cb *) return res; } -int ax25_listen_mine(ax25_address *callsign, struct net_device *dev) +int ax25_listen_mine(const ax25_address *callsign, struct net_device *dev) { struct listen_struct *listen; diff --git a/net/ax25/ax25_in.c b/net/ax25/ax25_in.c index cd6afe895db9..1cac25aca637 100644 --- a/net/ax25/ax25_in.c +++ b/net/ax25/ax25_in.c @@ -181,7 +181,7 @@ static int ax25_process_rx_frame(ax25_cb *ax25, struct sk_buff *skb, int type, i } static int ax25_rcv(struct sk_buff *skb, struct net_device *dev, - ax25_address *dev_addr, struct packet_type *ptype) + const ax25_address *dev_addr, struct packet_type *ptype) { ax25_address src, dest, *next_digi = NULL; int type = 0, mine = 0, dama; @@ -447,5 +447,5 @@ int ax25_kiss_rcv(struct sk_buff *skb, struct net_device *dev, skb_pull(skb, AX25_KISS_HEADER_LEN); /* Remove the KISS byte */ - return ax25_rcv(skb, dev, (ax25_address *)dev->dev_addr, ptype); + return ax25_rcv(skb, dev, (const ax25_address *)dev->dev_addr, ptype); } diff --git a/net/ax25/ax25_out.c b/net/ax25/ax25_out.c index 22f2f66c6e0a..3db76d2470e9 100644 --- a/net/ax25/ax25_out.c +++ b/net/ax25/ax25_out.c @@ -29,7 +29,7 @@ static DEFINE_SPINLOCK(ax25_frag_lock); -ax25_cb *ax25_send_frame(struct sk_buff *skb, int paclen, ax25_address *src, ax25_address *dest, ax25_digi *digi, struct net_device *dev) +ax25_cb *ax25_send_frame(struct sk_buff *skb, int paclen, const ax25_address *src, ax25_address *dest, ax25_digi *digi, struct net_device *dev) { ax25_dev *ax25_dev; ax25_cb *ax25; diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index 17687848daec..2ed9496fc41f 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -254,7 +254,7 @@ batadv_claim_hash_find(struct batadv_priv *bat_priv, * Return: backbone gateway if found or NULL otherwise */ static struct batadv_bla_backbone_gw * -batadv_backbone_hash_find(struct batadv_priv *bat_priv, u8 *addr, +batadv_backbone_hash_find(struct batadv_priv *bat_priv, const u8 *addr, unsigned short vid) { struct batadv_hashtable *hash = bat_priv->bla.backbone_hash; @@ -336,7 +336,7 @@ batadv_bla_del_backbone_claims(struct batadv_bla_backbone_gw *backbone_gw) * @vid: the VLAN ID * @claimtype: the type of the claim (CLAIM, UNCLAIM, ANNOUNCE, ...) */ -static void batadv_bla_send_claim(struct batadv_priv *bat_priv, u8 *mac, +static void batadv_bla_send_claim(struct batadv_priv *bat_priv, const u8 *mac, unsigned short vid, int claimtype) { struct sk_buff *skb; @@ -488,7 +488,7 @@ static void batadv_bla_loopdetect_report(struct work_struct *work) * Return: the (possibly created) backbone gateway or NULL on error */ static struct batadv_bla_backbone_gw * -batadv_bla_get_backbone_gw(struct batadv_priv *bat_priv, u8 *orig, +batadv_bla_get_backbone_gw(struct batadv_priv *bat_priv, const u8 *orig, unsigned short vid, bool own_backbone) { struct batadv_bla_backbone_gw *entry; @@ -926,7 +926,7 @@ static bool batadv_handle_request(struct batadv_priv *bat_priv, */ static bool batadv_handle_unclaim(struct batadv_priv *bat_priv, struct batadv_hard_iface *primary_if, - u8 *backbone_addr, u8 *claim_addr, + const u8 *backbone_addr, const u8 *claim_addr, unsigned short vid) { struct batadv_bla_backbone_gw *backbone_gw; @@ -964,7 +964,7 @@ static bool batadv_handle_unclaim(struct batadv_priv *bat_priv, */ static bool batadv_handle_claim(struct batadv_priv *bat_priv, struct batadv_hard_iface *primary_if, - u8 *backbone_addr, u8 *claim_addr, + const u8 *backbone_addr, const u8 *claim_addr, unsigned short vid) { struct batadv_bla_backbone_gw *backbone_gw; @@ -2130,7 +2130,7 @@ batadv_bla_claim_dump_entry(struct sk_buff *msg, u32 portid, struct batadv_hard_iface *primary_if, struct batadv_bla_claim *claim) { - u8 *primary_addr = primary_if->net_dev->dev_addr; + const u8 *primary_addr = primary_if->net_dev->dev_addr; u16 backbone_crc; bool is_own; void *hdr; @@ -2298,7 +2298,7 @@ batadv_bla_backbone_dump_entry(struct sk_buff *msg, u32 portid, struct batadv_hard_iface *primary_if, struct batadv_bla_backbone_gw *backbone_gw) { - u8 *primary_addr = primary_if->net_dev->dev_addr; + const u8 *primary_addr = primary_if->net_dev->dev_addr; u16 backbone_crc; bool is_own; int msecs; diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c index a3b6658ed789..433901dcf0c3 100644 --- a/net/batman-adv/multicast.c +++ b/net/batman-adv/multicast.c @@ -89,7 +89,7 @@ static struct net_device *batadv_mcast_get_bridge(struct net_device *soft_iface) rcu_read_lock(); do { upper = netdev_master_upper_dev_get_rcu(upper); - } while (upper && !(upper->priv_flags & IFF_EBRIDGE)); + } while (upper && !netif_is_bridge_master(upper)); dev_hold(upper); rcu_read_unlock(); diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index 970d0d7ccc98..83f31494ea4d 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -747,7 +747,8 @@ batadv_reroute_unicast_packet(struct batadv_priv *bat_priv, struct sk_buff *skb, struct batadv_orig_node *orig_node = NULL; struct batadv_hard_iface *primary_if = NULL; bool ret = false; - u8 *orig_addr, orig_ttvn; + const u8 *orig_addr; + u8 orig_ttvn; if (batadv_is_my_client(bat_priv, dst_addr, vid)) { primary_if = batadv_primary_if_get_selected(bat_priv); diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 0604b0279573..7ee09337fc40 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -134,7 +134,7 @@ static int batadv_interface_set_mac_addr(struct net_device *dev, void *p) return -EADDRNOTAVAIL; ether_addr_copy(old_addr, dev->dev_addr); - ether_addr_copy(dev->dev_addr, addr->sa_data); + eth_hw_addr_set(dev, addr->sa_data); /* only modify transtable if it has been initialized before */ if (atomic_read(&bat_priv->mesh_state) != BATADV_MESH_ACTIVE) diff --git a/net/batman-adv/tp_meter.c b/net/batman-adv/tp_meter.c index 56b9fe97b3b4..fbcb15c7c29b 100644 --- a/net/batman-adv/tp_meter.c +++ b/net/batman-adv/tp_meter.c @@ -631,9 +631,9 @@ static void batadv_tp_recv_ack(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node = NULL; const struct batadv_icmp_tp_packet *icmp; struct batadv_tp_vars *tp_vars; + const unsigned char *dev_addr; size_t packet_len, mss; u32 rtt, recv_ack, cwnd; - unsigned char *dev_addr; packet_len = BATADV_TP_PLEN; mss = BATADV_TP_PLEN; diff --git a/net/batman-adv/tvlv.c b/net/batman-adv/tvlv.c index 992773376e51..0cb58eb04093 100644 --- a/net/batman-adv/tvlv.c +++ b/net/batman-adv/tvlv.c @@ -587,8 +587,8 @@ void batadv_tvlv_handler_unregister(struct batadv_priv *bat_priv, * @tvlv_value: tvlv content * @tvlv_value_len: tvlv content length */ -void batadv_tvlv_unicast_send(struct batadv_priv *bat_priv, u8 *src, - u8 *dst, u8 type, u8 version, +void batadv_tvlv_unicast_send(struct batadv_priv *bat_priv, const u8 *src, + const u8 *dst, u8 type, u8 version, void *tvlv_value, u16 tvlv_value_len) { struct batadv_unicast_tvlv_packet *unicast_tvlv_packet; diff --git a/net/batman-adv/tvlv.h b/net/batman-adv/tvlv.h index 54f2a35653d0..4cf8af00fc11 100644 --- a/net/batman-adv/tvlv.h +++ b/net/batman-adv/tvlv.h @@ -42,8 +42,8 @@ int batadv_tvlv_containers_process(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, u8 *src, u8 *dst, void *tvlv_buff, u16 tvlv_buff_len); -void batadv_tvlv_unicast_send(struct batadv_priv *bat_priv, u8 *src, - u8 *dst, u8 type, u8 version, +void batadv_tvlv_unicast_send(struct batadv_priv *bat_priv, const u8 *src, + const u8 *dst, u8 type, u8 version, void *tvlv_value, u16 tvlv_value_len); #endif /* _NET_BATMAN_ADV_TVLV_H_ */ diff --git a/net/bridge/br.c b/net/bridge/br.c index d3a32c6813e0..1fac72cc617f 100644 --- a/net/bridge/br.c +++ b/net/bridge/br.c @@ -36,7 +36,7 @@ static int br_device_event(struct notifier_block *unused, unsigned long event, v bool changed_addr; int err; - if (dev->priv_flags & IFF_EBRIDGE) { + if (netif_is_bridge_master(dev)) { err = br_vlan_bridge_event(dev, event, ptr); if (err) return notifier_from_errno(err); @@ -349,7 +349,7 @@ static void __net_exit br_net_exit(struct net *net) rtnl_lock(); for_each_netdev(net, dev) - if (dev->priv_flags & IFF_EBRIDGE) + if (netif_is_bridge_master(dev)) br_dev_delete(dev, &list); unregister_netdevice_many(&list); diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 46812b659710..a6a68e18c70a 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -825,7 +825,7 @@ int br_fdb_dump(struct sk_buff *skb, struct net_bridge_fdb_entry *f; int err = 0; - if (!(dev->priv_flags & IFF_EBRIDGE)) + if (!netif_is_bridge_master(dev)) return err; if (!filter_dev) { @@ -1076,7 +1076,7 @@ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], return -EINVAL; } - if (dev->priv_flags & IFF_EBRIDGE) { + if (netif_is_bridge_master(dev)) { br = netdev_priv(dev); vg = br_vlan_group(br); } else { @@ -1173,7 +1173,7 @@ int br_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[], struct net_bridge *br; int err; - if (dev->priv_flags & IFF_EBRIDGE) { + if (netif_is_bridge_master(dev)) { br = netdev_priv(dev); vg = br_vlan_group(br); } else { diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index 4a02f8bb278a..c11bba3e7ec0 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -471,7 +471,7 @@ int br_del_bridge(struct net *net, const char *name) if (dev == NULL) ret = -ENXIO; /* Could not find device */ - else if (!(dev->priv_flags & IFF_EBRIDGE)) { + else if (!netif_is_bridge_master(dev)) { /* Attempt to delete non bridge device! */ ret = -EPERM; } diff --git a/net/bridge/br_ioctl.c b/net/bridge/br_ioctl.c index 49c268871fc1..db4ab2c2ce18 100644 --- a/net/bridge/br_ioctl.c +++ b/net/bridge/br_ioctl.c @@ -26,7 +26,7 @@ static int get_bridge_ifindices(struct net *net, int *indices, int num) for_each_netdev_rcu(net, dev) { if (i >= num) break; - if (dev->priv_flags & IFF_EBRIDGE) + if (netif_is_bridge_master(dev)) indices[i++] = dev->ifindex; } rcu_read_unlock(); diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index 0281453f7766..61ccf46fcc21 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -422,7 +422,7 @@ static int br_mdb_dump(struct sk_buff *skb, struct netlink_callback *cb) cb->seq = net->dev_base_seq; for_each_netdev_rcu(net, dev) { - if (dev->priv_flags & IFF_EBRIDGE) { + if (netif_is_bridge_master(dev)) { struct net_bridge *br = netdev_priv(dev); struct br_port_msg *bpm; @@ -1016,7 +1016,7 @@ static int br_mdb_parse(struct sk_buff *skb, struct nlmsghdr *nlh, return -ENODEV; } - if (!(dev->priv_flags & IFF_EBRIDGE)) { + if (!netif_is_bridge_master(dev)) { NL_SET_ERR_MSG_MOD(extack, "Device is not a bridge"); return -EOPNOTSUPP; } diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 8edfb98ae1d5..b5af68c105a8 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -968,7 +968,7 @@ static int brnf_device_event(struct notifier_block *unused, unsigned long event, struct net *net; int ret; - if (event != NETDEV_REGISTER || !(dev->priv_flags & IFF_EBRIDGE)) + if (event != NETDEV_REGISTER || !netif_is_bridge_master(dev)) return NOTIFY_DONE; ASSERT_RTNL(); diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 5c6c4305ed23..0c8b5f1a15bc 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -106,7 +106,7 @@ static size_t br_get_link_af_size_filtered(const struct net_device *dev, p = br_port_get_check_rcu(dev); if (p) vg = nbp_vlan_group_rcu(p); - } else if (dev->priv_flags & IFF_EBRIDGE) { + } else if (netif_is_bridge_master(dev)) { br = netdev_priv(dev); vg = br_vlan_group_rcu(br); } @@ -1050,7 +1050,7 @@ int br_dellink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags) p = br_port_get_rtnl(dev); /* We want to accept dev as bridge itself as well */ - if (!p && !(dev->priv_flags & IFF_EBRIDGE)) + if (!p && !netif_is_bridge_master(dev)) return -EINVAL; err = br_afspec(br, p, afspec, RTM_DELLINK, &changed, NULL); diff --git a/net/bridge/netfilter/ebtable_broute.c b/net/bridge/netfilter/ebtable_broute.c index a7af4eaff17d..1a11064f9990 100644 --- a/net/bridge/netfilter/ebtable_broute.c +++ b/net/bridge/netfilter/ebtable_broute.c @@ -66,7 +66,7 @@ static unsigned int ebt_broute(void *priv, struct sk_buff *skb, NFPROTO_BRIDGE, s->in, NULL, NULL, s->net, NULL); - ret = ebt_do_table(skb, &state, priv); + ret = ebt_do_table(priv, skb, &state); if (ret != NF_DROP) return ret; diff --git a/net/bridge/netfilter/ebtable_filter.c b/net/bridge/netfilter/ebtable_filter.c index c0b121df4a9a..cb949436bc0e 100644 --- a/net/bridge/netfilter/ebtable_filter.c +++ b/net/bridge/netfilter/ebtable_filter.c @@ -58,28 +58,21 @@ static const struct ebt_table frame_filter = { .me = THIS_MODULE, }; -static unsigned int -ebt_filter_hook(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state) -{ - return ebt_do_table(skb, state, priv); -} - static const struct nf_hook_ops ebt_ops_filter[] = { { - .hook = ebt_filter_hook, + .hook = ebt_do_table, .pf = NFPROTO_BRIDGE, .hooknum = NF_BR_LOCAL_IN, .priority = NF_BR_PRI_FILTER_BRIDGED, }, { - .hook = ebt_filter_hook, + .hook = ebt_do_table, .pf = NFPROTO_BRIDGE, .hooknum = NF_BR_FORWARD, .priority = NF_BR_PRI_FILTER_BRIDGED, }, { - .hook = ebt_filter_hook, + .hook = ebt_do_table, .pf = NFPROTO_BRIDGE, .hooknum = NF_BR_LOCAL_OUT, .priority = NF_BR_PRI_FILTER_OTHER, diff --git a/net/bridge/netfilter/ebtable_nat.c b/net/bridge/netfilter/ebtable_nat.c index 4078151c224f..5ee0531ae506 100644 --- a/net/bridge/netfilter/ebtable_nat.c +++ b/net/bridge/netfilter/ebtable_nat.c @@ -58,27 +58,21 @@ static const struct ebt_table frame_nat = { .me = THIS_MODULE, }; -static unsigned int ebt_nat_hook(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state) -{ - return ebt_do_table(skb, state, priv); -} - static const struct nf_hook_ops ebt_ops_nat[] = { { - .hook = ebt_nat_hook, + .hook = ebt_do_table, .pf = NFPROTO_BRIDGE, .hooknum = NF_BR_LOCAL_OUT, .priority = NF_BR_PRI_NAT_DST_OTHER, }, { - .hook = ebt_nat_hook, + .hook = ebt_do_table, .pf = NFPROTO_BRIDGE, .hooknum = NF_BR_POST_ROUTING, .priority = NF_BR_PRI_NAT_SRC, }, { - .hook = ebt_nat_hook, + .hook = ebt_do_table, .pf = NFPROTO_BRIDGE, .hooknum = NF_BR_PRE_ROUTING, .priority = NF_BR_PRI_NAT_DST_BRIDGED, diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index ba045f35114d..460d3064dc15 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -189,10 +189,10 @@ ebt_get_target_c(const struct ebt_entry *e) } /* Do some firewalling */ -unsigned int ebt_do_table(struct sk_buff *skb, - const struct nf_hook_state *state, - struct ebt_table *table) +unsigned int ebt_do_table(void *priv, struct sk_buff *skb, + const struct nf_hook_state *state) { + struct ebt_table *table = priv; unsigned int hook = state->hook; int i, nentries; struct ebt_entry *point; diff --git a/net/core/dev.c b/net/core/dev.c index 5d6fdc93591d..cba2d0bdb7c3 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -140,7 +140,7 @@ #include #include #include -#include +#include #include #include #include @@ -304,6 +304,12 @@ static struct netdev_name_node *netdev_name_node_lookup_rcu(struct net *net, return NULL; } +bool netdev_name_in_use(struct net *net, const char *name) +{ + return netdev_name_node_lookup(net, name); +} +EXPORT_SYMBOL(netdev_name_in_use); + int netdev_name_node_alt_create(struct net_device *dev, const char *name) { struct netdev_name_node *name_node; @@ -1140,7 +1146,7 @@ static int __dev_alloc_name(struct net *net, const char *name, char *buf) } snprintf(buf, IFNAMSIZ, name, i); - if (!__dev_get_by_name(net, buf)) + if (!netdev_name_in_use(net, buf)) return i; /* It is possible to run out of possible slots @@ -1194,7 +1200,7 @@ static int dev_get_valid_name(struct net *net, struct net_device *dev, if (strchr(name, '%')) return dev_alloc_name_ns(net, dev, name); - else if (__dev_get_by_name(net, name)) + else if (netdev_name_in_use(net, name)) return -EEXIST; else if (dev->name != name) strlcpy(dev->name, name, IFNAMSIZ); @@ -1297,8 +1303,8 @@ rollback: old_assign_type = NET_NAME_RENAMED; goto rollback; } else { - pr_err("%s: name change rollback failed: %d\n", - dev->name, ret); + netdev_err(dev, "name change rollback failed: %d\n", + ret); } } @@ -2352,7 +2358,7 @@ static void netif_setup_tc(struct net_device *dev, unsigned int txq) /* If TC0 is invalidated disable TC mapping */ if (tc->offset + tc->count > txq) { - pr_warn("Number of in use tx queues changed invalidating tc mappings. Priority traffic classification disabled!\n"); + netdev_warn(dev, "Number of in use tx queues changed invalidating tc mappings. Priority traffic classification disabled!\n"); dev->num_tc = 0; return; } @@ -2363,8 +2369,8 @@ static void netif_setup_tc(struct net_device *dev, unsigned int txq) tc = &dev->tc_to_txq[q]; if (tc->offset + tc->count > txq) { - pr_warn("Number of in use tx queues changed. Priority %i to tc mapping %i is no longer valid. Setting map to 0\n", - i, q); + netdev_warn(dev, "Number of in use tx queues changed. Priority %i to tc mapping %i is no longer valid. Setting map to 0\n", + i, q); netdev_set_prio_tc_map(dev, i, 0); } } @@ -3423,7 +3429,7 @@ EXPORT_SYMBOL(__skb_gso_segment); #ifdef CONFIG_BUG static void do_netdev_rx_csum_fault(struct net_device *dev, struct sk_buff *skb) { - pr_err("%s: hw csum failure\n", dev ? dev->name : ""); + netdev_err(dev, "hw csum failure\n"); skb_dump(KERN_ERR, skb, true); dump_stack(); } @@ -3934,6 +3940,7 @@ EXPORT_SYMBOL(dev_loopback_xmit); static struct sk_buff * sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev) { +#ifdef CONFIG_NET_CLS_ACT struct mini_Qdisc *miniq = rcu_dereference_bh(dev->miniq_egress); struct tcf_result cl_res; @@ -3969,6 +3976,7 @@ sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev) default: break; } +#endif /* CONFIG_NET_CLS_ACT */ return skb; } @@ -4162,13 +4170,20 @@ static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev) qdisc_pkt_len_init(skb); #ifdef CONFIG_NET_CLS_ACT skb->tc_at_ingress = 0; -# ifdef CONFIG_NET_EGRESS +#endif +#ifdef CONFIG_NET_EGRESS if (static_branch_unlikely(&egress_needed_key)) { + if (nf_hook_egress_active()) { + skb = nf_hook_egress(skb, &rc, dev); + if (!skb) + goto out; + } + nf_skip_egress(skb, true); skb = sch_handle_egress(skb, &rc, dev); if (!skb) goto out; + nf_skip_egress(skb, false); } -# endif #endif /* If device/qdisc don't need skb->dst, release it right now while * its hot in this cpu cache. @@ -5310,6 +5325,7 @@ skip_taps: if (static_branch_unlikely(&ingress_needed_key)) { bool another = false; + nf_skip_egress(skb, true); skb = sch_handle_ingress(skb, &pt_prev, &ret, orig_dev, &another); if (another) @@ -5317,6 +5333,7 @@ skip_taps: if (!skb) goto out; + nf_skip_egress(skb, false); if (nf_ingress(skb, &pt_prev, &ret, orig_dev) < 0) goto out; } @@ -7009,8 +7026,8 @@ static int __napi_poll(struct napi_struct *n, bool *repoll) } if (unlikely(work > weight)) - pr_err_once("NAPI poll function %pS returned %d, exceeding its budget of %d.\n", - n->poll, work, weight); + netdev_err_once(n->dev, "NAPI poll function %pS returned %d, exceeding its budget of %d.\n", + n->poll, work, weight); if (likely(work < weight)) return work; @@ -8564,8 +8581,7 @@ static int __dev_set_promiscuity(struct net_device *dev, int inc, bool notify) dev->flags &= ~IFF_PROMISC; else { dev->promiscuity -= inc; - pr_warn("%s: promiscuity touches roof, set promiscuity failed. promiscuity feature of device might be broken.\n", - dev->name); + netdev_warn(dev, "promiscuity touches roof, set promiscuity failed. promiscuity feature of device might be broken.\n"); return -EOVERFLOW; } } @@ -8635,8 +8651,7 @@ static int __dev_set_allmulti(struct net_device *dev, int inc, bool notify) dev->flags &= ~IFF_ALLMULTI; else { dev->allmulti -= inc; - pr_warn("%s: allmulti touches roof, set allmulti failed. allmulti feature of device might be broken.\n", - dev->name); + netdev_warn(dev, "allmulti touches roof, set allmulti failed. allmulti feature of device might be broken.\n"); return -EOVERFLOW; } } @@ -9173,14 +9188,11 @@ int dev_get_port_parent_id(struct net_device *dev, } err = devlink_compat_switch_id_get(dev, ppid); - if (!err || err != -EOPNOTSUPP) + if (!recurse || err != -EOPNOTSUPP) return err; - if (!recurse) - return -EOPNOTSUPP; - netdev_for_each_lower_dev(dev, lower_dev, iter) { - err = dev_get_port_parent_id(lower_dev, ppid, recurse); + err = dev_get_port_parent_id(lower_dev, ppid, true); if (err) break; if (!first.id_len) @@ -10881,7 +10893,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, if (!dev->ethtool_ops) dev->ethtool_ops = &default_ethtool_ops; - nf_hook_ingress_init(dev); + nf_hook_netdev_init(dev); return dev; @@ -11167,7 +11179,7 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net, * we can use it in the destination network namespace. */ err = -EEXIST; - if (__dev_get_by_name(net, dev->name)) { + if (netdev_name_in_use(net, dev->name)) { /* We get here if we can't use the current device name */ if (!pat) goto out; @@ -11520,7 +11532,7 @@ static void __net_exit default_device_exit(struct net *net) /* Push remaining network devices to init_net */ snprintf(fb_name, IFNAMSIZ, "dev%d", dev->ifindex); - if (__dev_get_by_name(&init_net, fb_name)) + if (netdev_name_in_use(&init_net, fb_name)) snprintf(fb_name, IFNAMSIZ, "dev%%d"); err = dev_change_net_namespace(dev, &init_net, fb_name); if (err) { diff --git a/net/core/devlink.c b/net/core/devlink.c index 4917112406a0..3464854015a2 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -30,6 +30,63 @@ #define CREATE_TRACE_POINTS #include +#define DEVLINK_RELOAD_STATS_ARRAY_SIZE \ + (__DEVLINK_RELOAD_LIMIT_MAX * __DEVLINK_RELOAD_ACTION_MAX) + +struct devlink_dev_stats { + u32 reload_stats[DEVLINK_RELOAD_STATS_ARRAY_SIZE]; + u32 remote_reload_stats[DEVLINK_RELOAD_STATS_ARRAY_SIZE]; +}; + +struct devlink { + u32 index; + struct list_head port_list; + struct list_head rate_list; + struct list_head sb_list; + struct list_head dpipe_table_list; + struct list_head resource_list; + struct list_head param_list; + struct list_head region_list; + struct list_head reporter_list; + struct mutex reporters_lock; /* protects reporter_list */ + struct devlink_dpipe_headers *dpipe_headers; + struct list_head trap_list; + struct list_head trap_group_list; + struct list_head trap_policer_list; + const struct devlink_ops *ops; + u64 features; + struct xarray snapshot_ids; + struct devlink_dev_stats stats; + struct device *dev; + possible_net_t _net; + /* Serializes access to devlink instance specific objects such as + * port, sb, dpipe, resource, params, region, traps and more. + */ + struct mutex lock; + u8 reload_failed:1; + refcount_t refcount; + struct completion comp; + char priv[0] __aligned(NETDEV_ALIGN); +}; + +void *devlink_priv(struct devlink *devlink) +{ + return &devlink->priv; +} +EXPORT_SYMBOL_GPL(devlink_priv); + +struct devlink *priv_to_devlink(void *priv) +{ + return container_of(priv, struct devlink, priv); +} +EXPORT_SYMBOL_GPL(priv_to_devlink); + +struct device *devlink_to_dev(const struct devlink *devlink) +{ + return devlink->dev; +} +EXPORT_SYMBOL_GPL(devlink_to_dev); + static struct devlink_dpipe_field devlink_dpipe_fields_ethernet[] = { { .name = "destination mac", @@ -95,6 +152,22 @@ static const struct nla_policy devlink_function_nl_policy[DEVLINK_PORT_FUNCTION_ static DEFINE_XARRAY_FLAGS(devlinks, XA_FLAGS_ALLOC); #define DEVLINK_REGISTERED XA_MARK_1 +/* devlink instances are open to the access from the user space after + * devlink_register() call. Such logical barrier allows us to have certain + * expectations related to locking. + * + * Before *_register() - we are in initialization stage and no parallel + * access possible to the devlink instance. All drivers perform that phase + * by implicitly holding device_lock. + * + * After *_register() - users and driver can access devlink instance at + * the same time. + */ +#define ASSERT_DEVLINK_REGISTERED(d) \ + WARN_ON_ONCE(!xa_get_mark(&devlinks, (d)->index, DEVLINK_REGISTERED)) +#define ASSERT_DEVLINK_NOT_REGISTERED(d) \ + WARN_ON_ONCE(xa_get_mark(&devlinks, (d)->index, DEVLINK_REGISTERED)) + /* devlink_mutex * * An overall lock guarding every operation coming from userspace. @@ -3959,9 +4032,6 @@ static int devlink_reload(struct devlink *devlink, struct net *dest_net, struct net *curr_net; int err; - if (!devlink->reload_enabled) - return -EOPNOTSUPP; - memcpy(remote_reload_stats, devlink->stats.remote_reload_stats, sizeof(remote_reload_stats)); @@ -4029,7 +4099,7 @@ static int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info) u32 actions_performed; int err; - if (!devlink_reload_supported(devlink->ops)) + if (!(devlink->features & DEVLINK_F_RELOAD)) return -EOPNOTSUPP; err = devlink_resources_validate(devlink, NULL, info); @@ -8912,6 +8982,25 @@ static bool devlink_reload_actions_valid(const struct devlink_ops *ops) return true; } +/** + * devlink_set_features - Set devlink supported features + * + * @devlink: devlink + * @features: devlink support features + * + * This interface allows us to set reload ops separatelly from + * the devlink_alloc. + */ +void devlink_set_features(struct devlink *devlink, u64 features) +{ + ASSERT_DEVLINK_NOT_REGISTERED(devlink); + + WARN_ON(features & DEVLINK_F_RELOAD && + !devlink_reload_supported(devlink->ops)); + devlink->features = features; +} +EXPORT_SYMBOL_GPL(devlink_set_features); + /** * devlink_alloc_ns - Allocate new devlink instance resources * in specific namespace @@ -9056,6 +9145,9 @@ static void devlink_notify_unregister(struct devlink *devlink) */ void devlink_register(struct devlink *devlink) { + ASSERT_DEVLINK_NOT_REGISTERED(devlink); + /* Make sure that we are in .probe() routine */ + mutex_lock(&devlink_mutex); xa_set_mark(&devlinks, devlink->index, DEVLINK_REGISTERED); devlink_notify_register(devlink); @@ -9070,53 +9162,19 @@ EXPORT_SYMBOL_GPL(devlink_register); */ void devlink_unregister(struct devlink *devlink) { + ASSERT_DEVLINK_REGISTERED(devlink); + /* Make sure that we are in .remove() routine */ + devlink_put(devlink); wait_for_completion(&devlink->comp); mutex_lock(&devlink_mutex); - WARN_ON(devlink_reload_supported(devlink->ops) && - devlink->reload_enabled); devlink_notify_unregister(devlink); xa_clear_mark(&devlinks, devlink->index, DEVLINK_REGISTERED); mutex_unlock(&devlink_mutex); } EXPORT_SYMBOL_GPL(devlink_unregister); -/** - * devlink_reload_enable - Enable reload of devlink instance - * - * @devlink: devlink - * - * Should be called at end of device initialization - * process when reload operation is supported. - */ -void devlink_reload_enable(struct devlink *devlink) -{ - mutex_lock(&devlink_mutex); - devlink->reload_enabled = true; - mutex_unlock(&devlink_mutex); -} -EXPORT_SYMBOL_GPL(devlink_reload_enable); - -/** - * devlink_reload_disable - Disable reload of devlink instance - * - * @devlink: devlink - * - * Should be called at the beginning of device cleanup - * process when reload operation is supported. - */ -void devlink_reload_disable(struct devlink *devlink) -{ - mutex_lock(&devlink_mutex); - /* Mutex is taken which ensures that no reload operation is in - * progress while setting up forbidded flag. - */ - devlink->reload_enabled = false; - mutex_unlock(&devlink_mutex); -} -EXPORT_SYMBOL_GPL(devlink_reload_disable); - /** * devlink_free - Free devlink instance resources * @@ -9124,6 +9182,8 @@ EXPORT_SYMBOL_GPL(devlink_reload_disable); */ void devlink_free(struct devlink *devlink) { + ASSERT_DEVLINK_NOT_REGISTERED(devlink); + mutex_destroy(&devlink->reporters_lock); mutex_destroy(&devlink->lock); WARN_ON(!list_empty(&devlink->trap_policer_list)); @@ -11324,6 +11384,24 @@ free_msg: nlmsg_free(msg); } +static struct devlink_port *netdev_to_devlink_port(struct net_device *dev) +{ + if (!dev->netdev_ops->ndo_get_devlink_port) + return NULL; + + return dev->netdev_ops->ndo_get_devlink_port(dev); +} + +static struct devlink *netdev_to_devlink(struct net_device *dev) +{ + struct devlink_port *devlink_port = netdev_to_devlink_port(dev); + + if (!devlink_port) + return NULL; + + return devlink_port->devlink; +} + void devlink_compat_running_version(struct net_device *dev, char *buf, size_t len) { @@ -11433,7 +11511,7 @@ static void __net_exit devlink_pernet_pre_exit(struct net *net) if (!net_eq(devlink_net(devlink), net)) goto retry; - WARN_ON(!devlink_reload_supported(devlink->ops)); + WARN_ON(!(devlink->features & DEVLINK_F_RELOAD)); err = devlink_reload(devlink, &init_net, DEVLINK_RELOAD_ACTION_DRIVER_REINIT, DEVLINK_RELOAD_LIMIT_UNSPEC, diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c index 8e582e29a41e..4fcbdd71c59f 100644 --- a/net/core/gen_estimator.c +++ b/net/core/gen_estimator.c @@ -40,10 +40,10 @@ */ struct net_rate_estimator { - struct gnet_stats_basic_packed *bstats; + struct gnet_stats_basic_sync *bstats; spinlock_t *stats_lock; - seqcount_t *running; - struct gnet_stats_basic_cpu __percpu *cpu_bstats; + bool running; + struct gnet_stats_basic_sync __percpu *cpu_bstats; u8 ewma_log; u8 intvl_log; /* period : (250ms << intvl_log) */ @@ -60,13 +60,13 @@ struct net_rate_estimator { }; static void est_fetch_counters(struct net_rate_estimator *e, - struct gnet_stats_basic_packed *b) + struct gnet_stats_basic_sync *b) { - memset(b, 0, sizeof(*b)); + gnet_stats_basic_sync_init(b); if (e->stats_lock) spin_lock(e->stats_lock); - __gnet_stats_copy_basic(e->running, b, e->cpu_bstats, e->bstats); + gnet_stats_add_basic(b, e->cpu_bstats, e->bstats, e->running); if (e->stats_lock) spin_unlock(e->stats_lock); @@ -76,14 +76,18 @@ static void est_fetch_counters(struct net_rate_estimator *e, static void est_timer(struct timer_list *t) { struct net_rate_estimator *est = from_timer(est, t, timer); - struct gnet_stats_basic_packed b; + struct gnet_stats_basic_sync b; + u64 b_bytes, b_packets; u64 rate, brate; est_fetch_counters(est, &b); - brate = (b.bytes - est->last_bytes) << (10 - est->intvl_log); + b_bytes = u64_stats_read(&b.bytes); + b_packets = u64_stats_read(&b.packets); + + brate = (b_bytes - est->last_bytes) << (10 - est->intvl_log); brate = (brate >> est->ewma_log) - (est->avbps >> est->ewma_log); - rate = (b.packets - est->last_packets) << (10 - est->intvl_log); + rate = (b_packets - est->last_packets) << (10 - est->intvl_log); rate = (rate >> est->ewma_log) - (est->avpps >> est->ewma_log); write_seqcount_begin(&est->seq); @@ -91,8 +95,8 @@ static void est_timer(struct timer_list *t) est->avpps += rate; write_seqcount_end(&est->seq); - est->last_bytes = b.bytes; - est->last_packets = b.packets; + est->last_bytes = b_bytes; + est->last_packets = b_packets; est->next_jiffies += ((HZ/4) << est->intvl_log); @@ -109,7 +113,9 @@ static void est_timer(struct timer_list *t) * @cpu_bstats: bstats per cpu * @rate_est: rate estimator statistics * @lock: lock for statistics and control path - * @running: qdisc running seqcount + * @running: true if @bstats represents a running qdisc, thus @bstats' + * internal values might change during basic reads. Only used + * if @bstats_cpu is NULL * @opt: rate estimator configuration TLV * * Creates a new rate estimator with &bstats as source and &rate_est @@ -121,16 +127,16 @@ static void est_timer(struct timer_list *t) * Returns 0 on success or a negative error code. * */ -int gen_new_estimator(struct gnet_stats_basic_packed *bstats, - struct gnet_stats_basic_cpu __percpu *cpu_bstats, +int gen_new_estimator(struct gnet_stats_basic_sync *bstats, + struct gnet_stats_basic_sync __percpu *cpu_bstats, struct net_rate_estimator __rcu **rate_est, spinlock_t *lock, - seqcount_t *running, + bool running, struct nlattr *opt) { struct gnet_estimator *parm = nla_data(opt); struct net_rate_estimator *old, *est; - struct gnet_stats_basic_packed b; + struct gnet_stats_basic_sync b; int intvl_log; if (nla_len(opt) < sizeof(*parm)) @@ -164,8 +170,8 @@ int gen_new_estimator(struct gnet_stats_basic_packed *bstats, est_fetch_counters(est, &b); if (lock) local_bh_enable(); - est->last_bytes = b.bytes; - est->last_packets = b.packets; + est->last_bytes = u64_stats_read(&b.bytes); + est->last_packets = u64_stats_read(&b.packets); if (lock) spin_lock_bh(lock); @@ -214,7 +220,9 @@ EXPORT_SYMBOL(gen_kill_estimator); * @cpu_bstats: bstats per cpu * @rate_est: rate estimator statistics * @lock: lock for statistics and control path - * @running: qdisc running seqcount (might be NULL) + * @running: true if @bstats represents a running qdisc, thus @bstats' + * internal values might change during basic reads. Only used + * if @cpu_bstats is NULL * @opt: rate estimator configuration TLV * * Replaces the configuration of a rate estimator by calling @@ -222,11 +230,11 @@ EXPORT_SYMBOL(gen_kill_estimator); * * Returns 0 on success or a negative error code. */ -int gen_replace_estimator(struct gnet_stats_basic_packed *bstats, - struct gnet_stats_basic_cpu __percpu *cpu_bstats, +int gen_replace_estimator(struct gnet_stats_basic_sync *bstats, + struct gnet_stats_basic_sync __percpu *cpu_bstats, struct net_rate_estimator __rcu **rate_est, spinlock_t *lock, - seqcount_t *running, struct nlattr *opt) + bool running, struct nlattr *opt) { return gen_new_estimator(bstats, cpu_bstats, rate_est, lock, running, opt); diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c index e491b083b348..a10335b4ba2d 100644 --- a/net/core/gen_stats.c +++ b/net/core/gen_stats.c @@ -18,7 +18,7 @@ #include #include #include - +#include static inline int gnet_stats_copy(struct gnet_dump *d, int type, void *buf, int size, int padattr) @@ -114,63 +114,112 @@ gnet_stats_start_copy(struct sk_buff *skb, int type, spinlock_t *lock, } EXPORT_SYMBOL(gnet_stats_start_copy); -static void -__gnet_stats_copy_basic_cpu(struct gnet_stats_basic_packed *bstats, - struct gnet_stats_basic_cpu __percpu *cpu) +/* Must not be inlined, due to u64_stats seqcount_t lockdep key */ +void gnet_stats_basic_sync_init(struct gnet_stats_basic_sync *b) { + u64_stats_set(&b->bytes, 0); + u64_stats_set(&b->packets, 0); + u64_stats_init(&b->syncp); +} +EXPORT_SYMBOL(gnet_stats_basic_sync_init); + +static void gnet_stats_add_basic_cpu(struct gnet_stats_basic_sync *bstats, + struct gnet_stats_basic_sync __percpu *cpu) +{ + u64 t_bytes = 0, t_packets = 0; int i; for_each_possible_cpu(i) { - struct gnet_stats_basic_cpu *bcpu = per_cpu_ptr(cpu, i); + struct gnet_stats_basic_sync *bcpu = per_cpu_ptr(cpu, i); unsigned int start; u64 bytes, packets; do { start = u64_stats_fetch_begin_irq(&bcpu->syncp); - bytes = bcpu->bstats.bytes; - packets = bcpu->bstats.packets; + bytes = u64_stats_read(&bcpu->bytes); + packets = u64_stats_read(&bcpu->packets); } while (u64_stats_fetch_retry_irq(&bcpu->syncp, start)); - bstats->bytes += bytes; - bstats->packets += packets; + t_bytes += bytes; + t_packets += packets; } + _bstats_update(bstats, t_bytes, t_packets); } -void -__gnet_stats_copy_basic(const seqcount_t *running, - struct gnet_stats_basic_packed *bstats, - struct gnet_stats_basic_cpu __percpu *cpu, - struct gnet_stats_basic_packed *b) +void gnet_stats_add_basic(struct gnet_stats_basic_sync *bstats, + struct gnet_stats_basic_sync __percpu *cpu, + struct gnet_stats_basic_sync *b, bool running) { - unsigned int seq; + unsigned int start; + u64 bytes = 0; + u64 packets = 0; + + WARN_ON_ONCE((cpu || running) && in_hardirq()); if (cpu) { - __gnet_stats_copy_basic_cpu(bstats, cpu); + gnet_stats_add_basic_cpu(bstats, cpu); return; } do { if (running) - seq = read_seqcount_begin(running); - bstats->bytes = b->bytes; - bstats->packets = b->packets; - } while (running && read_seqcount_retry(running, seq)); + start = u64_stats_fetch_begin_irq(&b->syncp); + bytes = u64_stats_read(&b->bytes); + packets = u64_stats_read(&b->packets); + } while (running && u64_stats_fetch_retry_irq(&b->syncp, start)); + + _bstats_update(bstats, bytes, packets); +} +EXPORT_SYMBOL(gnet_stats_add_basic); + +static void gnet_stats_read_basic(u64 *ret_bytes, u64 *ret_packets, + struct gnet_stats_basic_sync __percpu *cpu, + struct gnet_stats_basic_sync *b, bool running) +{ + unsigned int start; + + if (cpu) { + u64 t_bytes = 0, t_packets = 0; + int i; + + for_each_possible_cpu(i) { + struct gnet_stats_basic_sync *bcpu = per_cpu_ptr(cpu, i); + unsigned int start; + u64 bytes, packets; + + do { + start = u64_stats_fetch_begin_irq(&bcpu->syncp); + bytes = u64_stats_read(&bcpu->bytes); + packets = u64_stats_read(&bcpu->packets); + } while (u64_stats_fetch_retry_irq(&bcpu->syncp, start)); + + t_bytes += bytes; + t_packets += packets; + } + *ret_bytes = t_bytes; + *ret_packets = t_packets; + return; + } + do { + if (running) + start = u64_stats_fetch_begin_irq(&b->syncp); + *ret_bytes = u64_stats_read(&b->bytes); + *ret_packets = u64_stats_read(&b->packets); + } while (running && u64_stats_fetch_retry_irq(&b->syncp, start)); } -EXPORT_SYMBOL(__gnet_stats_copy_basic); static int -___gnet_stats_copy_basic(const seqcount_t *running, - struct gnet_dump *d, - struct gnet_stats_basic_cpu __percpu *cpu, - struct gnet_stats_basic_packed *b, - int type) +___gnet_stats_copy_basic(struct gnet_dump *d, + struct gnet_stats_basic_sync __percpu *cpu, + struct gnet_stats_basic_sync *b, + int type, bool running) { - struct gnet_stats_basic_packed bstats = {0}; + u64 bstats_bytes, bstats_packets; - __gnet_stats_copy_basic(running, &bstats, cpu, b); + gnet_stats_read_basic(&bstats_bytes, &bstats_packets, cpu, b, running); if (d->compat_tc_stats && type == TCA_STATS_BASIC) { - d->tc_stats.bytes = bstats.bytes; - d->tc_stats.packets = bstats.packets; + d->tc_stats.bytes = bstats_bytes; + d->tc_stats.packets = bstats_packets; } if (d->tail) { @@ -178,24 +227,28 @@ ___gnet_stats_copy_basic(const seqcount_t *running, int res; memset(&sb, 0, sizeof(sb)); - sb.bytes = bstats.bytes; - sb.packets = bstats.packets; + sb.bytes = bstats_bytes; + sb.packets = bstats_packets; res = gnet_stats_copy(d, type, &sb, sizeof(sb), TCA_STATS_PAD); - if (res < 0 || sb.packets == bstats.packets) + if (res < 0 || sb.packets == bstats_packets) return res; /* emit 64bit stats only if needed */ - return gnet_stats_copy(d, TCA_STATS_PKT64, &bstats.packets, - sizeof(bstats.packets), TCA_STATS_PAD); + return gnet_stats_copy(d, TCA_STATS_PKT64, &bstats_packets, + sizeof(bstats_packets), TCA_STATS_PAD); } return 0; } /** * gnet_stats_copy_basic - copy basic statistics into statistic TLV - * @running: seqcount_t pointer * @d: dumping handle * @cpu: copy statistic per cpu * @b: basic statistics + * @running: true if @b represents a running qdisc, thus @b's + * internal values might change during basic reads. + * Only used if @cpu is NULL + * + * Context: task; must not be run from IRQ or BH contexts * * Appends the basic statistics to the top level TLV created by * gnet_stats_start_copy(). @@ -204,22 +257,25 @@ ___gnet_stats_copy_basic(const seqcount_t *running, * if the room in the socket buffer was not sufficient. */ int -gnet_stats_copy_basic(const seqcount_t *running, - struct gnet_dump *d, - struct gnet_stats_basic_cpu __percpu *cpu, - struct gnet_stats_basic_packed *b) +gnet_stats_copy_basic(struct gnet_dump *d, + struct gnet_stats_basic_sync __percpu *cpu, + struct gnet_stats_basic_sync *b, + bool running) { - return ___gnet_stats_copy_basic(running, d, cpu, b, - TCA_STATS_BASIC); + return ___gnet_stats_copy_basic(d, cpu, b, TCA_STATS_BASIC, running); } EXPORT_SYMBOL(gnet_stats_copy_basic); /** * gnet_stats_copy_basic_hw - copy basic hw statistics into statistic TLV - * @running: seqcount_t pointer * @d: dumping handle * @cpu: copy statistic per cpu * @b: basic statistics + * @running: true if @b represents a running qdisc, thus @b's + * internal values might change during basic reads. + * Only used if @cpu is NULL + * + * Context: task; must not be run from IRQ or BH contexts * * Appends the basic statistics to the top level TLV created by * gnet_stats_start_copy(). @@ -228,13 +284,12 @@ EXPORT_SYMBOL(gnet_stats_copy_basic); * if the room in the socket buffer was not sufficient. */ int -gnet_stats_copy_basic_hw(const seqcount_t *running, - struct gnet_dump *d, - struct gnet_stats_basic_cpu __percpu *cpu, - struct gnet_stats_basic_packed *b) +gnet_stats_copy_basic_hw(struct gnet_dump *d, + struct gnet_stats_basic_sync __percpu *cpu, + struct gnet_stats_basic_sync *b, + bool running) { - return ___gnet_stats_copy_basic(running, d, cpu, b, - TCA_STATS_BASIC_HW); + return ___gnet_stats_copy_basic(d, cpu, b, TCA_STATS_BASIC_HW, running); } EXPORT_SYMBOL(gnet_stats_copy_basic_hw); @@ -282,16 +337,15 @@ gnet_stats_copy_rate_est(struct gnet_dump *d, } EXPORT_SYMBOL(gnet_stats_copy_rate_est); -static void -__gnet_stats_copy_queue_cpu(struct gnet_stats_queue *qstats, - const struct gnet_stats_queue __percpu *q) +static void gnet_stats_add_queue_cpu(struct gnet_stats_queue *qstats, + const struct gnet_stats_queue __percpu *q) { int i; for_each_possible_cpu(i) { const struct gnet_stats_queue *qcpu = per_cpu_ptr(q, i); - qstats->qlen = 0; + qstats->qlen += qcpu->backlog; qstats->backlog += qcpu->backlog; qstats->drops += qcpu->drops; qstats->requeues += qcpu->requeues; @@ -299,24 +353,21 @@ __gnet_stats_copy_queue_cpu(struct gnet_stats_queue *qstats, } } -void __gnet_stats_copy_queue(struct gnet_stats_queue *qstats, - const struct gnet_stats_queue __percpu *cpu, - const struct gnet_stats_queue *q, - __u32 qlen) +void gnet_stats_add_queue(struct gnet_stats_queue *qstats, + const struct gnet_stats_queue __percpu *cpu, + const struct gnet_stats_queue *q) { if (cpu) { - __gnet_stats_copy_queue_cpu(qstats, cpu); + gnet_stats_add_queue_cpu(qstats, cpu); } else { - qstats->qlen = q->qlen; - qstats->backlog = q->backlog; - qstats->drops = q->drops; - qstats->requeues = q->requeues; - qstats->overlimits = q->overlimits; + qstats->qlen += q->qlen; + qstats->backlog += q->backlog; + qstats->drops += q->drops; + qstats->requeues += q->requeues; + qstats->overlimits += q->overlimits; } - - qstats->qlen = qlen; } -EXPORT_SYMBOL(__gnet_stats_copy_queue); +EXPORT_SYMBOL(gnet_stats_add_queue); /** * gnet_stats_copy_queue - copy queue statistics into statistics TLV @@ -339,7 +390,8 @@ gnet_stats_copy_queue(struct gnet_dump *d, { struct gnet_stats_queue qstats = {0}; - __gnet_stats_copy_queue(&qstats, cpu_q, q, qlen); + gnet_stats_add_queue(&qstats, cpu_q, q); + qstats.qlen = qlen; if (d->compat_tc_stats) { d->tc_stats.drops = qstats.drops; diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 2d5bc3a75fae..47931c8be04b 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -122,6 +122,8 @@ static void neigh_mark_dead(struct neighbour *n) list_del_init(&n->gc_list); atomic_dec(&n->tbl->gc_entries); } + if (!list_empty(&n->managed_list)) + list_del_init(&n->managed_list); } static void neigh_update_gc_list(struct neighbour *n) @@ -130,7 +132,6 @@ static void neigh_update_gc_list(struct neighbour *n) write_lock_bh(&n->tbl->lock); write_lock(&n->lock); - if (n->dead) goto out; @@ -149,32 +150,59 @@ static void neigh_update_gc_list(struct neighbour *n) list_add_tail(&n->gc_list, &n->tbl->gc_list); atomic_inc(&n->tbl->gc_entries); } - out: write_unlock(&n->lock); write_unlock_bh(&n->tbl->lock); } -static bool neigh_update_ext_learned(struct neighbour *neigh, u32 flags, - int *notify) +static void neigh_update_managed_list(struct neighbour *n) { - bool rc = false; - u8 ndm_flags; + bool on_managed_list, add_to_managed; + + write_lock_bh(&n->tbl->lock); + write_lock(&n->lock); + if (n->dead) + goto out; + + add_to_managed = n->flags & NTF_MANAGED; + on_managed_list = !list_empty(&n->managed_list); + + if (!add_to_managed && on_managed_list) + list_del_init(&n->managed_list); + else if (add_to_managed && !on_managed_list) + list_add_tail(&n->managed_list, &n->tbl->managed_list); +out: + write_unlock(&n->lock); + write_unlock_bh(&n->tbl->lock); +} + +static void neigh_update_flags(struct neighbour *neigh, u32 flags, int *notify, + bool *gc_update, bool *managed_update) +{ + u32 ndm_flags, old_flags = neigh->flags; if (!(flags & NEIGH_UPDATE_F_ADMIN)) - return rc; + return; - ndm_flags = (flags & NEIGH_UPDATE_F_EXT_LEARNED) ? NTF_EXT_LEARNED : 0; - if ((neigh->flags ^ ndm_flags) & NTF_EXT_LEARNED) { + ndm_flags = (flags & NEIGH_UPDATE_F_EXT_LEARNED) ? NTF_EXT_LEARNED : 0; + ndm_flags |= (flags & NEIGH_UPDATE_F_MANAGED) ? NTF_MANAGED : 0; + + if ((old_flags ^ ndm_flags) & NTF_EXT_LEARNED) { if (ndm_flags & NTF_EXT_LEARNED) neigh->flags |= NTF_EXT_LEARNED; else neigh->flags &= ~NTF_EXT_LEARNED; - rc = true; *notify = 1; + *gc_update = true; + } + if ((old_flags ^ ndm_flags) & NTF_MANAGED) { + if (ndm_flags & NTF_MANAGED) + neigh->flags |= NTF_MANAGED; + else + neigh->flags &= ~NTF_MANAGED; + *notify = 1; + *managed_update = true; } - - return rc; } static bool neigh_del(struct neighbour *n, struct neighbour __rcu **np, @@ -379,7 +407,7 @@ EXPORT_SYMBOL(neigh_ifdown); static struct neighbour *neigh_alloc(struct neigh_table *tbl, struct net_device *dev, - bool exempt_from_gc) + u32 flags, bool exempt_from_gc) { struct neighbour *n = NULL; unsigned long now = jiffies; @@ -412,6 +440,7 @@ do_alloc: n->updated = n->used = now; n->nud_state = NUD_NONE; n->output = neigh_blackhole; + n->flags = flags; seqlock_init(&n->hh.hh_lock); n->parms = neigh_parms_clone(&tbl->parms); timer_setup(&n->timer, neigh_timer_handler, 0); @@ -421,6 +450,7 @@ do_alloc: refcount_set(&n->refcnt, 1); n->dead = 1; INIT_LIST_HEAD(&n->gc_list); + INIT_LIST_HEAD(&n->managed_list); atomic_inc(&tbl->entries); out: @@ -575,19 +605,18 @@ struct neighbour *neigh_lookup_nodev(struct neigh_table *tbl, struct net *net, } EXPORT_SYMBOL(neigh_lookup_nodev); -static struct neighbour *___neigh_create(struct neigh_table *tbl, - const void *pkey, - struct net_device *dev, - bool exempt_from_gc, bool want_ref) +static struct neighbour * +___neigh_create(struct neigh_table *tbl, const void *pkey, + struct net_device *dev, u32 flags, + bool exempt_from_gc, bool want_ref) { - struct neighbour *n1, *rc, *n = neigh_alloc(tbl, dev, exempt_from_gc); - u32 hash_val; - unsigned int key_len = tbl->key_len; - int error; + u32 hash_val, key_len = tbl->key_len; + struct neighbour *n1, *rc, *n; struct neigh_hash_table *nht; + int error; + n = neigh_alloc(tbl, dev, flags, exempt_from_gc); trace_neigh_create(tbl, dev, pkey, n, exempt_from_gc); - if (!n) { rc = ERR_PTR(-ENOBUFS); goto out; @@ -650,7 +679,8 @@ static struct neighbour *___neigh_create(struct neigh_table *tbl, n->dead = 0; if (!exempt_from_gc) list_add_tail(&n->gc_list, &n->tbl->gc_list); - + if (n->flags & NTF_MANAGED) + list_add_tail(&n->managed_list, &n->tbl->managed_list); if (want_ref) neigh_hold(n); rcu_assign_pointer(n->next, @@ -674,7 +704,7 @@ out_neigh_release: struct neighbour *__neigh_create(struct neigh_table *tbl, const void *pkey, struct net_device *dev, bool want_ref) { - return ___neigh_create(tbl, pkey, dev, false, want_ref); + return ___neigh_create(tbl, pkey, dev, 0, false, want_ref); } EXPORT_SYMBOL(__neigh_create); @@ -1205,8 +1235,6 @@ static void neigh_update_hhs(struct neighbour *neigh) } } - - /* Generic update routine. -- lladdr is new lladdr or NULL, if it is not supplied. -- new is new state. @@ -1217,7 +1245,8 @@ static void neigh_update_hhs(struct neighbour *neigh) lladdr instead of overriding it if it is different. NEIGH_UPDATE_F_ADMIN means that the change is administrative. - + NEIGH_UPDATE_F_USE means that the entry is user triggered. + NEIGH_UPDATE_F_MANAGED means that the entry will be auto-refreshed. NEIGH_UPDATE_F_OVERRIDE_ISROUTER allows to override existing NTF_ROUTER flag. NEIGH_UPDATE_F_ISROUTER indicates if the neighbour is known as @@ -1225,17 +1254,15 @@ static void neigh_update_hhs(struct neighbour *neigh) Caller MUST hold reference count on the entry. */ - static int __neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, u32 flags, u32 nlmsg_pid, struct netlink_ext_ack *extack) { - bool ext_learn_change = false; - u8 old; - int err; - int notify = 0; - struct net_device *dev; + bool gc_update = false, managed_update = false; int update_isrouter = 0; + struct net_device *dev; + int err, notify = 0; + u8 old; trace_neigh_update(neigh, lladdr, new, flags, nlmsg_pid); @@ -1254,7 +1281,13 @@ static int __neigh_update(struct neighbour *neigh, const u8 *lladdr, (old & (NUD_NOARP | NUD_PERMANENT))) goto out; - ext_learn_change = neigh_update_ext_learned(neigh, flags, ¬ify); + neigh_update_flags(neigh, flags, ¬ify, &gc_update, &managed_update); + if (flags & (NEIGH_UPDATE_F_USE | NEIGH_UPDATE_F_MANAGED)) { + new = old & ~NUD_PERMANENT; + neigh->nud_state = new; + err = 0; + goto out; + } if (!(new & NUD_VALID)) { neigh_del_timer(neigh); @@ -1399,15 +1432,13 @@ out: if (update_isrouter) neigh_update_is_router(neigh, flags, ¬ify); write_unlock_bh(&neigh->lock); - - if (((new ^ old) & NUD_PERMANENT) || ext_learn_change) + if (((new ^ old) & NUD_PERMANENT) || gc_update) neigh_update_gc_list(neigh); - + if (managed_update) + neigh_update_managed_list(neigh); if (notify) neigh_update_notify(neigh, nlmsg_pid); - trace_neigh_update_done(neigh, err); - return err; } @@ -1533,6 +1564,20 @@ int neigh_direct_output(struct neighbour *neigh, struct sk_buff *skb) } EXPORT_SYMBOL(neigh_direct_output); +static void neigh_managed_work(struct work_struct *work) +{ + struct neigh_table *tbl = container_of(work, struct neigh_table, + managed_work.work); + struct neighbour *neigh; + + write_lock_bh(&tbl->lock); + list_for_each_entry(neigh, &tbl->managed_list, managed_list) + neigh_event_send(neigh, NULL); + queue_delayed_work(system_power_efficient_wq, &tbl->managed_work, + NEIGH_VAR(&tbl->parms, DELAY_PROBE_TIME)); + write_unlock_bh(&tbl->lock); +} + static void neigh_proxy_process(struct timer_list *t) { struct neigh_table *tbl = from_timer(tbl, t, proxy_timer); @@ -1679,6 +1724,8 @@ void neigh_table_init(int index, struct neigh_table *tbl) INIT_LIST_HEAD(&tbl->parms_list); INIT_LIST_HEAD(&tbl->gc_list); + INIT_LIST_HEAD(&tbl->managed_list); + list_add(&tbl->parms.list, &tbl->parms_list); write_pnet(&tbl->parms.net, &init_net); refcount_set(&tbl->parms.refcnt, 1); @@ -1710,9 +1757,13 @@ void neigh_table_init(int index, struct neigh_table *tbl) WARN_ON(tbl->entry_size % NEIGH_PRIV_ALIGN); rwlock_init(&tbl->lock); + INIT_DEFERRABLE_WORK(&tbl->gc_work, neigh_periodic_work); queue_delayed_work(system_power_efficient_wq, &tbl->gc_work, tbl->parms.reachable_time); + INIT_DEFERRABLE_WORK(&tbl->managed_work, neigh_managed_work); + queue_delayed_work(system_power_efficient_wq, &tbl->managed_work, 0); + timer_setup(&tbl->proxy_timer, neigh_proxy_process, 0); skb_queue_head_init_class(&tbl->proxy_queue, &neigh_table_proxy_queue_class); @@ -1783,6 +1834,7 @@ const struct nla_policy nda_policy[NDA_MAX+1] = { [NDA_MASTER] = { .type = NLA_U32 }, [NDA_PROTOCOL] = { .type = NLA_U8 }, [NDA_NH_ID] = { .type = NLA_U32 }, + [NDA_FLAGS_EXT] = NLA_POLICY_MASK(NLA_U32, NTF_EXT_MASK), [NDA_FDB_EXT_ATTRS] = { .type = NLA_NESTED }, }; @@ -1855,7 +1907,7 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { int flags = NEIGH_UPDATE_F_ADMIN | NEIGH_UPDATE_F_OVERRIDE | - NEIGH_UPDATE_F_OVERRIDE_ISROUTER; + NEIGH_UPDATE_F_OVERRIDE_ISROUTER; struct net *net = sock_net(skb->sk); struct ndmsg *ndm; struct nlattr *tb[NDA_MAX+1]; @@ -1864,6 +1916,7 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, struct neighbour *neigh; void *dst, *lladdr; u8 protocol = 0; + u32 ndm_flags; int err; ASSERT_RTNL(); @@ -1879,6 +1932,15 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, } ndm = nlmsg_data(nlh); + ndm_flags = ndm->ndm_flags; + if (tb[NDA_FLAGS_EXT]) { + u32 ext = nla_get_u32(tb[NDA_FLAGS_EXT]); + + BUILD_BUG_ON(sizeof(neigh->flags) * BITS_PER_BYTE < + (sizeof(ndm->ndm_flags) * BITS_PER_BYTE + + hweight32(NTF_EXT_MASK))); + ndm_flags |= (ext << NTF_EXT_SHIFT); + } if (ndm->ndm_ifindex) { dev = __dev_get_by_index(net, ndm->ndm_ifindex); if (dev == NULL) { @@ -1906,14 +1968,18 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, if (tb[NDA_PROTOCOL]) protocol = nla_get_u8(tb[NDA_PROTOCOL]); - - if (ndm->ndm_flags & NTF_PROXY) { + if (ndm_flags & NTF_PROXY) { struct pneigh_entry *pn; + if (ndm_flags & NTF_MANAGED) { + NL_SET_ERR_MSG(extack, "Invalid NTF_* flag combination"); + goto out; + } + err = -ENOBUFS; pn = pneigh_lookup(tbl, net, dst, dev, 1); if (pn) { - pn->flags = ndm->ndm_flags; + pn->flags = ndm_flags; if (protocol) pn->protocol = protocol; err = 0; @@ -1933,16 +1999,24 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, neigh = neigh_lookup(tbl, dst, dev); if (neigh == NULL) { - bool exempt_from_gc; + bool ndm_permanent = ndm->ndm_state & NUD_PERMANENT; + bool exempt_from_gc = ndm_permanent || + ndm_flags & NTF_EXT_LEARNED; if (!(nlh->nlmsg_flags & NLM_F_CREATE)) { err = -ENOENT; goto out; } + if (ndm_permanent && (ndm_flags & NTF_MANAGED)) { + NL_SET_ERR_MSG(extack, "Invalid NTF_* flag for permanent entry"); + err = -EINVAL; + goto out; + } - exempt_from_gc = ndm->ndm_state & NUD_PERMANENT || - ndm->ndm_flags & NTF_EXT_LEARNED; - neigh = ___neigh_create(tbl, dst, dev, exempt_from_gc, true); + neigh = ___neigh_create(tbl, dst, dev, + ndm_flags & + (NTF_EXT_LEARNED | NTF_MANAGED), + exempt_from_gc, true); if (IS_ERR(neigh)) { err = PTR_ERR(neigh); goto out; @@ -1961,22 +2035,22 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, if (protocol) neigh->protocol = protocol; - - if (ndm->ndm_flags & NTF_EXT_LEARNED) + if (ndm_flags & NTF_EXT_LEARNED) flags |= NEIGH_UPDATE_F_EXT_LEARNED; - - if (ndm->ndm_flags & NTF_ROUTER) + if (ndm_flags & NTF_ROUTER) flags |= NEIGH_UPDATE_F_ISROUTER; + if (ndm_flags & NTF_MANAGED) + flags |= NEIGH_UPDATE_F_MANAGED; + if (ndm_flags & NTF_USE) + flags |= NEIGH_UPDATE_F_USE; - if (ndm->ndm_flags & NTF_USE) { + err = __neigh_update(neigh, lladdr, ndm->ndm_state, flags, + NETLINK_CB(skb).portid, extack); + if (!err && ndm_flags & (NTF_USE | NTF_MANAGED)) { neigh_event_send(neigh, NULL); err = 0; - } else - err = __neigh_update(neigh, lladdr, ndm->ndm_state, flags, - NETLINK_CB(skb).portid, extack); - + } neigh_release(neigh); - out: return err; } @@ -2427,6 +2501,7 @@ out: static int neigh_fill_info(struct sk_buff *skb, struct neighbour *neigh, u32 pid, u32 seq, int type, unsigned int flags) { + u32 neigh_flags, neigh_flags_ext; unsigned long now = jiffies; struct nda_cacheinfo ci; struct nlmsghdr *nlh; @@ -2436,11 +2511,14 @@ static int neigh_fill_info(struct sk_buff *skb, struct neighbour *neigh, if (nlh == NULL) return -EMSGSIZE; + neigh_flags_ext = neigh->flags >> NTF_EXT_SHIFT; + neigh_flags = neigh->flags & NTF_OLD_MASK; + ndm = nlmsg_data(nlh); ndm->ndm_family = neigh->ops->family; ndm->ndm_pad1 = 0; ndm->ndm_pad2 = 0; - ndm->ndm_flags = neigh->flags; + ndm->ndm_flags = neigh_flags; ndm->ndm_type = neigh->type; ndm->ndm_ifindex = neigh->dev->ifindex; @@ -2471,6 +2549,8 @@ static int neigh_fill_info(struct sk_buff *skb, struct neighbour *neigh, if (neigh->protocol && nla_put_u8(skb, NDA_PROTOCOL, neigh->protocol)) goto nla_put_failure; + if (neigh_flags_ext && nla_put_u32(skb, NDA_FLAGS_EXT, neigh_flags_ext)) + goto nla_put_failure; nlmsg_end(skb, nlh); return 0; @@ -2484,6 +2564,7 @@ static int pneigh_fill_info(struct sk_buff *skb, struct pneigh_entry *pn, u32 pid, u32 seq, int type, unsigned int flags, struct neigh_table *tbl) { + u32 neigh_flags, neigh_flags_ext; struct nlmsghdr *nlh; struct ndmsg *ndm; @@ -2491,11 +2572,14 @@ static int pneigh_fill_info(struct sk_buff *skb, struct pneigh_entry *pn, if (nlh == NULL) return -EMSGSIZE; + neigh_flags_ext = pn->flags >> NTF_EXT_SHIFT; + neigh_flags = pn->flags & NTF_OLD_MASK; + ndm = nlmsg_data(nlh); ndm->ndm_family = tbl->family; ndm->ndm_pad1 = 0; ndm->ndm_pad2 = 0; - ndm->ndm_flags = pn->flags | NTF_PROXY; + ndm->ndm_flags = neigh_flags | NTF_PROXY; ndm->ndm_type = RTN_UNICAST; ndm->ndm_ifindex = pn->dev ? pn->dev->ifindex : 0; ndm->ndm_state = NUD_NONE; @@ -2505,6 +2589,8 @@ static int pneigh_fill_info(struct sk_buff *skb, struct pneigh_entry *pn, if (pn->protocol && nla_put_u8(skb, NDA_PROTOCOL, pn->protocol)) goto nla_put_failure; + if (neigh_flags_ext && nla_put_u32(skb, NDA_FLAGS_EXT, neigh_flags_ext)) + goto nla_put_failure; nlmsg_end(skb, nlh); return 0; @@ -2820,6 +2906,7 @@ static inline size_t neigh_nlmsg_size(void) + nla_total_size(MAX_ADDR_LEN) /* NDA_LLADDR */ + nla_total_size(sizeof(struct nda_cacheinfo)) + nla_total_size(4) /* NDA_PROBES */ + + nla_total_size(4) /* NDA_FLAGS_EXT */ + nla_total_size(1); /* NDA_PROTOCOL */ } @@ -2848,6 +2935,7 @@ static inline size_t pneigh_nlmsg_size(void) { return NLMSG_ALIGN(sizeof(struct ndmsg)) + nla_total_size(MAX_ADDR_LEN) /* NDA_DST */ + + nla_total_size(4) /* NDA_FLAGS_EXT */ + nla_total_size(1); /* NDA_PROTOCOL */ } diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index b32407f28746..9c01c642cf9e 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -175,6 +175,14 @@ static int change_carrier(struct net_device *dev, unsigned long new_carrier) static ssize_t carrier_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { + struct net_device *netdev = to_net_dev(dev); + + /* The check is also done in change_carrier; this helps returning early + * without hitting the trylock/restart in netdev_store. + */ + if (!netdev->netdev_ops->ndo_change_carrier) + return -EOPNOTSUPP; + return netdev_store(dev, attr, buf, len, change_carrier); } @@ -196,6 +204,12 @@ static ssize_t speed_show(struct device *dev, struct net_device *netdev = to_net_dev(dev); int ret = -EINVAL; + /* The check is also done in __ethtool_get_link_ksettings; this helps + * returning early without hitting the trylock/restart below. + */ + if (!netdev->ethtool_ops->get_link_ksettings) + return ret; + if (!rtnl_trylock()) return restart_syscall(); @@ -216,6 +230,12 @@ static ssize_t duplex_show(struct device *dev, struct net_device *netdev = to_net_dev(dev); int ret = -EINVAL; + /* The check is also done in __ethtool_get_link_ksettings; this helps + * returning early without hitting the trylock/restart below. + */ + if (!netdev->ethtool_ops->get_link_ksettings) + return ret; + if (!rtnl_trylock()) return restart_syscall(); @@ -468,6 +488,14 @@ static ssize_t proto_down_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { + struct net_device *netdev = to_net_dev(dev); + + /* The check is also done in change_proto_down; this helps returning + * early without hitting the trylock/restart in netdev_store. + */ + if (!netdev->netdev_ops->ndo_change_proto_down) + return -EOPNOTSUPP; + return netdev_store(dev, attr, buf, len, change_proto_down); } NETDEVICE_SHOW_RW(proto_down, fmt_dec); @@ -478,6 +506,12 @@ static ssize_t phys_port_id_show(struct device *dev, struct net_device *netdev = to_net_dev(dev); ssize_t ret = -EINVAL; + /* The check is also done in dev_get_phys_port_id; this helps returning + * early without hitting the trylock/restart below. + */ + if (!netdev->netdev_ops->ndo_get_phys_port_id) + return -EOPNOTSUPP; + if (!rtnl_trylock()) return restart_syscall(); @@ -500,6 +534,13 @@ static ssize_t phys_port_name_show(struct device *dev, struct net_device *netdev = to_net_dev(dev); ssize_t ret = -EINVAL; + /* The checks are also done in dev_get_phys_port_name; this helps + * returning early without hitting the trylock/restart below. + */ + if (!netdev->netdev_ops->ndo_get_phys_port_name && + !netdev->netdev_ops->ndo_get_devlink_port) + return -EOPNOTSUPP; + if (!rtnl_trylock()) return restart_syscall(); @@ -522,6 +563,14 @@ static ssize_t phys_switch_id_show(struct device *dev, struct net_device *netdev = to_net_dev(dev); ssize_t ret = -EINVAL; + /* The checks are also done in dev_get_phys_port_name; this helps + * returning early without hitting the trylock/restart below. This works + * because recurse is false when calling dev_get_port_parent_id. + */ + if (!netdev->netdev_ops->ndo_get_port_parent_id && + !netdev->netdev_ops->ndo_get_devlink_port) + return -EOPNOTSUPP; + if (!rtnl_trylock()) return restart_syscall(); @@ -1226,6 +1275,12 @@ static ssize_t tx_maxrate_store(struct netdev_queue *queue, if (!capable(CAP_NET_ADMIN)) return -EPERM; + /* The check is also done later; this helps returning early without + * hitting the trylock/restart below. + */ + if (!dev->netdev_ops->ndo_set_tx_maxrate) + return -EOPNOTSUPP; + err = kstrtou32(buf, 10, &rate); if (err < 0) return err; diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 1a6978427d6c..9b60e4301a44 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -49,6 +49,12 @@ static int page_pool_init(struct page_pool *pool, * which is the XDP_TX use-case. */ if (pool->p.flags & PP_FLAG_DMA_MAP) { + /* DMA-mapping is not supported on 32-bit systems with + * 64-bit DMA mapping. + */ + if (sizeof(dma_addr_t) > sizeof(unsigned long)) + return -EOPNOTSUPP; + if ((pool->p.dma_dir != DMA_FROM_DEVICE) && (pool->p.dma_dir != DMA_BIDIRECTIONAL)) return -EINVAL; @@ -69,10 +75,6 @@ static int page_pool_init(struct page_pool *pool, */ } - if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT && - pool->p.flags & PP_FLAG_PAGE_FRAG) - return -EINVAL; - if (ptr_ring_init(&pool->ring, ring_qsize, GFP_KERNEL) < 0) return -ENOMEM; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 2dc1b209ba91..79477dcae7c2 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -3804,9 +3804,8 @@ struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev, struct net *net = dev_net(dev); struct sk_buff *skb; int err = -ENOBUFS; - size_t if_info_size; - skb = nlmsg_new((if_info_size = if_nlmsg_size(dev, 0)), flags); + skb = nlmsg_new(if_nlmsg_size(dev, 0), flags); if (skb == NULL) goto errout; @@ -4384,7 +4383,7 @@ static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb) continue; if (br_dev != netdev_master_upper_dev_get(dev) && - !(dev->priv_flags & IFF_EBRIDGE)) + !netif_is_bridge_master(dev)) continue; cops = ops; } diff --git a/net/core/sock.c b/net/core/sock.c index beda31764df9..9862eefce21e 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -350,7 +350,7 @@ void sk_error_report(struct sock *sk) } EXPORT_SYMBOL(sk_error_report); -static int sock_get_timeout(long timeo, void *optval, bool old_timeval) +int sock_get_timeout(long timeo, void *optval, bool old_timeval) { struct __kernel_sock_timeval tv; @@ -379,12 +379,11 @@ static int sock_get_timeout(long timeo, void *optval, bool old_timeval) *(struct __kernel_sock_timeval *)optval = tv; return sizeof(tv); } +EXPORT_SYMBOL(sock_get_timeout); -static int sock_set_timeout(long *timeo_p, sockptr_t optval, int optlen, - bool old_timeval) +int sock_copy_user_timeval(struct __kernel_sock_timeval *tv, + sockptr_t optval, int optlen, bool old_timeval) { - struct __kernel_sock_timeval tv; - if (old_timeval && in_compat_syscall() && !COMPAT_USE_64BIT_TIME) { struct old_timeval32 tv32; @@ -393,8 +392,8 @@ static int sock_set_timeout(long *timeo_p, sockptr_t optval, int optlen, if (copy_from_sockptr(&tv32, optval, sizeof(tv32))) return -EFAULT; - tv.tv_sec = tv32.tv_sec; - tv.tv_usec = tv32.tv_usec; + tv->tv_sec = tv32.tv_sec; + tv->tv_usec = tv32.tv_usec; } else if (old_timeval) { struct __kernel_old_timeval old_tv; @@ -402,14 +401,28 @@ static int sock_set_timeout(long *timeo_p, sockptr_t optval, int optlen, return -EINVAL; if (copy_from_sockptr(&old_tv, optval, sizeof(old_tv))) return -EFAULT; - tv.tv_sec = old_tv.tv_sec; - tv.tv_usec = old_tv.tv_usec; + tv->tv_sec = old_tv.tv_sec; + tv->tv_usec = old_tv.tv_usec; } else { - if (optlen < sizeof(tv)) + if (optlen < sizeof(*tv)) return -EINVAL; - if (copy_from_sockptr(&tv, optval, sizeof(tv))) + if (copy_from_sockptr(tv, optval, sizeof(*tv))) return -EFAULT; } + + return 0; +} +EXPORT_SYMBOL(sock_copy_user_timeval); + +static int sock_set_timeout(long *timeo_p, sockptr_t optval, int optlen, + bool old_timeval) +{ + struct __kernel_sock_timeval tv; + int err = sock_copy_user_timeval(&tv, optval, optlen, old_timeval); + + if (err) + return err; + if (tv.tv_usec < 0 || tv.tv_usec >= USEC_PER_SEC) return -EDOM; diff --git a/net/core/stream.c b/net/core/stream.c index e09ffd410685..06b36c730ce8 100644 --- a/net/core/stream.c +++ b/net/core/stream.c @@ -195,9 +195,6 @@ void sk_stream_kill_queues(struct sock *sk) /* First the read buffer. */ __skb_queue_purge(&sk->sk_receive_queue); - /* Next, the error queue. */ - __skb_queue_purge(&sk->sk_error_queue); - /* Next, the write queue. */ WARN_ON(!skb_queue_empty(&sk->sk_write_queue)); diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h index c5c1d2b8045e..5183e627468d 100644 --- a/net/dccp/dccp.h +++ b/net/dccp/dccp.h @@ -48,7 +48,7 @@ extern bool dccp_debug; extern struct inet_hashinfo dccp_hashinfo; -extern struct percpu_counter dccp_orphan_count; +DECLARE_PER_CPU(unsigned int, dccp_orphan_count); void dccp_time_wait(struct sock *sk, int state, int timeo); diff --git a/net/dccp/proto.c b/net/dccp/proto.c index abb5c596a817..fc44dadc778b 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -42,8 +42,8 @@ DEFINE_SNMP_STAT(struct dccp_mib, dccp_statistics) __read_mostly; EXPORT_SYMBOL_GPL(dccp_statistics); -struct percpu_counter dccp_orphan_count; -EXPORT_SYMBOL_GPL(dccp_orphan_count); +DEFINE_PER_CPU(unsigned int, dccp_orphan_count); +EXPORT_PER_CPU_SYMBOL_GPL(dccp_orphan_count); struct inet_hashinfo dccp_hashinfo; EXPORT_SYMBOL_GPL(dccp_hashinfo); @@ -1055,7 +1055,7 @@ adjudge_to_death: bh_lock_sock(sk); WARN_ON(sock_owned_by_user(sk)); - percpu_counter_inc(sk->sk_prot->orphan_count); + this_cpu_inc(dccp_orphan_count); /* Have we already been destroyed by a softirq or backlog? */ if (state != DCCP_CLOSED && sk->sk_state == DCCP_CLOSED) @@ -1115,13 +1115,10 @@ static int __init dccp_init(void) BUILD_BUG_ON(sizeof(struct dccp_skb_cb) > sizeof_field(struct sk_buff, cb)); - rc = percpu_counter_init(&dccp_orphan_count, 0, GFP_KERNEL); - if (rc) - goto out_fail; inet_hashinfo_init(&dccp_hashinfo); rc = inet_hashinfo2_init_mod(&dccp_hashinfo); if (rc) - goto out_free_percpu; + goto out_fail; rc = -ENOBUFS; dccp_hashinfo.bind_bucket_cachep = kmem_cache_create("dccp_bind_bucket", @@ -1226,8 +1223,6 @@ out_free_bind_bucket_cachep: kmem_cache_destroy(dccp_hashinfo.bind_bucket_cachep); out_free_hashinfo2: inet_hashinfo2_free_mod(&dccp_hashinfo); -out_free_percpu: - percpu_counter_destroy(&dccp_orphan_count); out_fail: dccp_hashinfo.bhash = NULL; dccp_hashinfo.ehash = NULL; @@ -1250,7 +1245,6 @@ static void __exit dccp_fini(void) dccp_ackvec_exit(); dccp_sysctl_exit(); inet_hashinfo2_free_mod(&dccp_hashinfo); - percpu_counter_destroy(&dccp_orphan_count); } module_init(dccp_init); diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig index d8ee15f1c7a9..8cb87b5067ee 100644 --- a/net/dsa/Kconfig +++ b/net/dsa/Kconfig @@ -92,13 +92,6 @@ config NET_DSA_TAG_KSZ Say Y if you want to enable support for tagging frames for the Microchip 8795/9477/9893 families of switches. -config NET_DSA_TAG_RTL4_A - tristate "Tag driver for Realtek 4 byte protocol A tags" - help - Say Y or M if you want to enable support for tagging frames for the - Realtek switches with 4 byte protocol A tags, sich as found in - the Realtek RTL8366RB. - config NET_DSA_TAG_OCELOT tristate "Tag driver for Ocelot family of switches, using NPI port" select PACKING @@ -126,6 +119,19 @@ config NET_DSA_TAG_QCA Say Y or M if you want to enable support for tagging frames for the Qualcomm Atheros QCA8K switches. +config NET_DSA_TAG_RTL4_A + tristate "Tag driver for Realtek 4 byte protocol A tags" + help + Say Y or M if you want to enable support for tagging frames for the + Realtek switches with 4 byte protocol A tags, sich as found in + the Realtek RTL8366RB. + +config NET_DSA_TAG_RTL8_4 + tristate "Tag driver for Realtek 8 byte protocol 4 tags" + help + Say Y or M if you want to enable support for tagging frames for Realtek + switches with 8 byte protocol 4 tags, such as the Realtek RTL8365MB-VC. + config NET_DSA_TAG_LAN9303 tristate "Tag driver for SMSC/Microchip LAN9303 family of switches" help diff --git a/net/dsa/Makefile b/net/dsa/Makefile index 67ea009f242c..9f75820e7c98 100644 --- a/net/dsa/Makefile +++ b/net/dsa/Makefile @@ -10,12 +10,13 @@ obj-$(CONFIG_NET_DSA_TAG_DSA_COMMON) += tag_dsa.o obj-$(CONFIG_NET_DSA_TAG_GSWIP) += tag_gswip.o obj-$(CONFIG_NET_DSA_TAG_HELLCREEK) += tag_hellcreek.o obj-$(CONFIG_NET_DSA_TAG_KSZ) += tag_ksz.o -obj-$(CONFIG_NET_DSA_TAG_RTL4_A) += tag_rtl4_a.o obj-$(CONFIG_NET_DSA_TAG_LAN9303) += tag_lan9303.o obj-$(CONFIG_NET_DSA_TAG_MTK) += tag_mtk.o obj-$(CONFIG_NET_DSA_TAG_OCELOT) += tag_ocelot.o obj-$(CONFIG_NET_DSA_TAG_OCELOT_8021Q) += tag_ocelot_8021q.o obj-$(CONFIG_NET_DSA_TAG_QCA) += tag_qca.o +obj-$(CONFIG_NET_DSA_TAG_RTL4_A) += tag_rtl4_a.o +obj-$(CONFIG_NET_DSA_TAG_RTL8_4) += tag_rtl8_4.o obj-$(CONFIG_NET_DSA_TAG_SJA1105) += tag_sja1105.o obj-$(CONFIG_NET_DSA_TAG_TRAILER) += tag_trailer.o obj-$(CONFIG_NET_DSA_TAG_XRS700X) += tag_xrs700x.o diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index 41f36ad8b0ec..ea5169e671ae 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -280,23 +280,22 @@ static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev, } #ifdef CONFIG_PM_SLEEP -static bool dsa_is_port_initialized(struct dsa_switch *ds, int p) +static bool dsa_port_is_initialized(const struct dsa_port *dp) { - const struct dsa_port *dp = dsa_to_port(ds, p); - return dp->type == DSA_PORT_TYPE_USER && dp->slave; } int dsa_switch_suspend(struct dsa_switch *ds) { - int i, ret = 0; + struct dsa_port *dp; + int ret = 0; /* Suspend slave network devices */ - for (i = 0; i < ds->num_ports; i++) { - if (!dsa_is_port_initialized(ds, i)) + dsa_switch_for_each_port(dp, ds) { + if (!dsa_port_is_initialized(dp)) continue; - ret = dsa_slave_suspend(dsa_to_port(ds, i)->slave); + ret = dsa_slave_suspend(dp->slave); if (ret) return ret; } @@ -310,7 +309,8 @@ EXPORT_SYMBOL_GPL(dsa_switch_suspend); int dsa_switch_resume(struct dsa_switch *ds) { - int i, ret = 0; + struct dsa_port *dp; + int ret = 0; if (ds->ops->resume) ret = ds->ops->resume(ds); @@ -319,11 +319,11 @@ int dsa_switch_resume(struct dsa_switch *ds) return ret; /* Resume slave network devices */ - for (i = 0; i < ds->num_ports; i++) { - if (!dsa_is_port_initialized(ds, i)) + dsa_switch_for_each_port(dp, ds) { + if (!dsa_port_is_initialized(dp)) continue; - ret = dsa_slave_resume(dsa_to_port(ds, i)->slave); + ret = dsa_slave_resume(dp->slave); if (ret) return ret; } diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index 729b56c331a0..f5270114dcb8 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -399,11 +399,8 @@ static int dsa_tree_setup_cpu_ports(struct dsa_switch_tree *dst) if (!dsa_port_is_cpu(cpu_dp)) continue; - list_for_each_entry(dp, &dst->ports, list) { - /* Prefer a local CPU port */ - if (dp->ds != cpu_dp->ds) - continue; - + /* Prefer a local CPU port */ + dsa_switch_for_each_port(dp, cpu_dp->ds) { /* Prefer the first local CPU port found */ if (dp->cpu_dp) continue; @@ -802,17 +799,16 @@ static int dsa_switch_setup_tag_protocol(struct dsa_switch *ds) { const struct dsa_device_ops *tag_ops = ds->dst->tag_ops; struct dsa_switch_tree *dst = ds->dst; - int port, err; + struct dsa_port *cpu_dp; + int err; if (tag_ops->proto == dst->default_proto) return 0; - for (port = 0; port < ds->num_ports; port++) { - if (!dsa_is_cpu_port(ds, port)) - continue; - + dsa_switch_for_each_cpu_port(cpu_dp, ds) { rtnl_lock(); - err = ds->ops->change_tag_protocol(ds, port, tag_ops->proto); + err = ds->ops->change_tag_protocol(ds, cpu_dp->index, + tag_ops->proto); rtnl_unlock(); if (err) { dev_err(ds->dev, "Unable to use tag protocol \"%s\": %pe\n", @@ -853,12 +849,10 @@ static int dsa_switch_setup(struct dsa_switch *ds) /* Setup devlink port instances now, so that the switch * setup() can register regions etc, against the ports */ - list_for_each_entry(dp, &ds->dst->ports, list) { - if (dp->ds == ds) { - err = dsa_port_devlink_setup(dp); - if (err) - goto unregister_devlink_ports; - } + dsa_switch_for_each_port(dp, ds) { + err = dsa_port_devlink_setup(dp); + if (err) + goto unregister_devlink_ports; } err = dsa_switch_register_notifier(ds); @@ -902,9 +896,8 @@ teardown: unregister_notifier: dsa_switch_unregister_notifier(ds); unregister_devlink_ports: - list_for_each_entry(dp, &ds->dst->ports, list) - if (dp->ds == ds) - dsa_port_devlink_teardown(dp); + dsa_switch_for_each_port(dp, ds) + dsa_port_devlink_teardown(dp); devlink_free(ds->devlink); ds->devlink = NULL; return err; @@ -926,15 +919,14 @@ static void dsa_switch_teardown(struct dsa_switch *ds) ds->slave_mii_bus = NULL; } - dsa_switch_unregister_notifier(ds); - if (ds->ops->teardown) ds->ops->teardown(ds); + dsa_switch_unregister_notifier(ds); + if (ds->devlink) { - list_for_each_entry(dp, &ds->dst->ports, list) - if (dp->ds == ds) - dsa_port_devlink_teardown(dp); + dsa_switch_for_each_port(dp, ds) + dsa_port_devlink_teardown(dp); devlink_free(ds->devlink); ds->devlink = NULL; } @@ -1150,7 +1142,7 @@ int dsa_tree_change_tag_proto(struct dsa_switch_tree *dst, goto out_unlock; list_for_each_entry(dp, &dst->ports, list) { - if (!dsa_is_user_port(dp->ds, dp->index)) + if (!dsa_port_is_user(dp)) continue; if (dp->slave->flags & IFF_UP) @@ -1181,8 +1173,8 @@ static struct dsa_port *dsa_port_touch(struct dsa_switch *ds, int index) struct dsa_switch_tree *dst = ds->dst; struct dsa_port *dp; - list_for_each_entry(dp, &dst->ports, list) - if (dp->ds == ds && dp->index == index) + dsa_switch_for_each_port(dp, ds) + if (dp->index == index) return dp; dp = kzalloc(sizeof(*dp), GFP_KERNEL); @@ -1528,12 +1520,9 @@ static int dsa_switch_parse(struct dsa_switch *ds, struct dsa_chip_data *cd) static void dsa_switch_release_ports(struct dsa_switch *ds) { - struct dsa_switch_tree *dst = ds->dst; struct dsa_port *dp, *next; - list_for_each_entry_safe(dp, next, &dst->ports, list) { - if (dp->ds != ds) - continue; + dsa_switch_for_each_port_safe(dp, next, ds) { list_del(&dp->list); kfree(dp); } @@ -1625,13 +1614,7 @@ void dsa_switch_shutdown(struct dsa_switch *ds) mutex_lock(&dsa2_mutex); rtnl_lock(); - list_for_each_entry(dp, &ds->dst->ports, list) { - if (dp->ds != ds) - continue; - - if (!dsa_port_is_user(dp)) - continue; - + dsa_switch_for_each_user_port(dp, ds) { master = dp->cpu_dp->master; slave_dev = dp->slave; diff --git a/net/dsa/port.c b/net/dsa/port.c index 616330a16d31..bf671306b560 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -515,14 +515,15 @@ static bool dsa_port_can_apply_vlan_filtering(struct dsa_port *dp, struct netlink_ext_ack *extack) { struct dsa_switch *ds = dp->ds; - int err, i; + struct dsa_port *other_dp; + int err; /* VLAN awareness was off, so the question is "can we turn it on". * We may have had 8021q uppers, those need to go. Make sure we don't * enter an inconsistent state: deny changing the VLAN awareness state * as long as we have 8021q uppers. */ - if (vlan_filtering && dsa_is_user_port(ds, dp->index)) { + if (vlan_filtering && dsa_port_is_user(dp)) { struct net_device *upper_dev, *slave = dp->slave; struct net_device *br = dp->bridge_dev; struct list_head *iter; @@ -557,10 +558,10 @@ static bool dsa_port_can_apply_vlan_filtering(struct dsa_port *dp, * different ports of the same switch device and one of them has a * different setting than what is being requested. */ - for (i = 0; i < ds->num_ports; i++) { + dsa_switch_for_each_port(other_dp, ds) { struct net_device *other_bridge; - other_bridge = dsa_to_port(ds, i)->bridge_dev; + other_bridge = other_dp->bridge_dev; if (!other_bridge) continue; /* If it's the same bridge, it also has same @@ -607,20 +608,16 @@ int dsa_port_vlan_filtering(struct dsa_port *dp, bool vlan_filtering, return err; if (ds->vlan_filtering_is_global) { - int port; + struct dsa_port *other_dp; ds->vlan_filtering = vlan_filtering; - for (port = 0; port < ds->num_ports; port++) { - struct net_device *slave; - - if (!dsa_is_user_port(ds, port)) - continue; + dsa_switch_for_each_user_port(other_dp, ds) { + struct net_device *slave = dp->slave; /* We might be called in the unbind path, so not * all slave devices might still be registered. */ - slave = dsa_to_port(ds, port)->slave; if (!slave) continue; @@ -1041,7 +1038,7 @@ static void dsa_port_phylink_mac_link_down(struct phylink_config *config, struct phy_device *phydev = NULL; struct dsa_switch *ds = dp->ds; - if (dsa_is_user_port(ds, dp->index)) + if (dsa_port_is_user(dp)) phydev = dp->slave->phydev; if (!ds->ops->phylink_mac_link_down) { diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 11ec9e689589..9d9fef668eba 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -789,6 +789,37 @@ static int dsa_slave_get_sset_count(struct net_device *dev, int sset) return -EOPNOTSUPP; } +static void dsa_slave_get_eth_phy_stats(struct net_device *dev, + struct ethtool_eth_phy_stats *phy_stats) +{ + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = dp->ds; + + if (ds->ops->get_eth_phy_stats) + ds->ops->get_eth_phy_stats(ds, dp->index, phy_stats); +} + +static void dsa_slave_get_eth_mac_stats(struct net_device *dev, + struct ethtool_eth_mac_stats *mac_stats) +{ + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = dp->ds; + + if (ds->ops->get_eth_mac_stats) + ds->ops->get_eth_mac_stats(ds, dp->index, mac_stats); +} + +static void +dsa_slave_get_eth_ctrl_stats(struct net_device *dev, + struct ethtool_eth_ctrl_stats *ctrl_stats) +{ + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = dp->ds; + + if (ds->ops->get_eth_ctrl_stats) + ds->ops->get_eth_ctrl_stats(ds, dp->index, ctrl_stats); +} + static void dsa_slave_net_selftest(struct net_device *ndev, struct ethtool_test *etest, u64 *buf) { @@ -1695,6 +1726,9 @@ static const struct ethtool_ops dsa_slave_ethtool_ops = { .get_strings = dsa_slave_get_strings, .get_ethtool_stats = dsa_slave_get_ethtool_stats, .get_sset_count = dsa_slave_get_sset_count, + .get_eth_phy_stats = dsa_slave_get_eth_phy_stats, + .get_eth_mac_stats = dsa_slave_get_eth_mac_stats, + .get_eth_ctrl_stats = dsa_slave_get_eth_ctrl_stats, .set_wol = dsa_slave_set_wol, .get_wol = dsa_slave_get_wol, .set_eee = dsa_slave_set_eee, @@ -2334,7 +2368,7 @@ static int dsa_slave_netdevice_event(struct notifier_block *nb, dst = cpu_dp->ds->dst; list_for_each_entry(dp, &dst->ports, list) { - if (!dsa_is_user_port(dp->ds, dp->index)) + if (!dsa_port_is_user(dp)) continue; list_add(&dp->slave->close_list, &close_list); diff --git a/net/dsa/switch.c b/net/dsa/switch.c index 6466d0539af9..2b1b21bde830 100644 --- a/net/dsa/switch.c +++ b/net/dsa/switch.c @@ -17,14 +17,11 @@ static unsigned int dsa_switch_fastest_ageing_time(struct dsa_switch *ds, unsigned int ageing_time) { - int i; - - for (i = 0; i < ds->num_ports; ++i) { - struct dsa_port *dp = dsa_to_port(ds, i); + struct dsa_port *dp; + dsa_switch_for_each_port(dp, ds) if (dp->ageing_time && dp->ageing_time < ageing_time) ageing_time = dp->ageing_time; - } return ageing_time; } @@ -49,10 +46,10 @@ static int dsa_switch_ageing_time(struct dsa_switch *ds, return 0; } -static bool dsa_switch_mtu_match(struct dsa_switch *ds, int port, - struct dsa_notifier_mtu_info *info) +static bool dsa_port_mtu_match(struct dsa_port *dp, + struct dsa_notifier_mtu_info *info) { - if (ds->index == info->sw_index && port == info->port) + if (dp->ds->index == info->sw_index && dp->index == info->port) return true; /* Do not propagate to other switches in the tree if the notifier was @@ -61,7 +58,7 @@ static bool dsa_switch_mtu_match(struct dsa_switch *ds, int port, if (info->targeted_match) return false; - if (dsa_is_dsa_port(ds, port) || dsa_is_cpu_port(ds, port)) + if (dsa_port_is_dsa(dp) || dsa_port_is_cpu(dp)) return true; return false; @@ -70,14 +67,16 @@ static bool dsa_switch_mtu_match(struct dsa_switch *ds, int port, static int dsa_switch_mtu(struct dsa_switch *ds, struct dsa_notifier_mtu_info *info) { - int port, ret; + struct dsa_port *dp; + int ret; if (!ds->ops->port_change_mtu) return -EOPNOTSUPP; - for (port = 0; port < ds->num_ports; port++) { - if (dsa_switch_mtu_match(ds, port, info)) { - ret = ds->ops->port_change_mtu(ds, port, info->mtu); + dsa_switch_for_each_port(dp, ds) { + if (dsa_port_mtu_match(dp, info)) { + ret = ds->ops->port_change_mtu(ds, dp->index, + info->mtu); if (ret) return ret; } @@ -120,7 +119,8 @@ static int dsa_switch_bridge_leave(struct dsa_switch *ds, struct netlink_ext_ack extack = {0}; bool change_vlan_filtering = false; bool vlan_filtering; - int err, port; + struct dsa_port *dp; + int err; if (dst->index == info->tree_index && ds->index == info->sw_index && ds->ops->port_bridge_leave) @@ -150,10 +150,10 @@ static int dsa_switch_bridge_leave(struct dsa_switch *ds, * VLAN-aware bridge. */ if (change_vlan_filtering && ds->vlan_filtering_is_global) { - for (port = 0; port < ds->num_ports; port++) { + dsa_switch_for_each_port(dp, ds) { struct net_device *bridge_dev; - bridge_dev = dsa_to_port(ds, port)->bridge_dev; + bridge_dev = dp->bridge_dev; if (bridge_dev && br_vlan_enabled(bridge_dev)) { change_vlan_filtering = false; @@ -179,19 +179,19 @@ static int dsa_switch_bridge_leave(struct dsa_switch *ds, * DSA links) that sit between the targeted port on which the notifier was * emitted and its dedicated CPU port. */ -static bool dsa_switch_host_address_match(struct dsa_switch *ds, int port, - int info_sw_index, int info_port) +static bool dsa_port_host_address_match(struct dsa_port *dp, + int info_sw_index, int info_port) { struct dsa_port *targeted_dp, *cpu_dp; struct dsa_switch *targeted_ds; - targeted_ds = dsa_switch_find(ds->dst->index, info_sw_index); + targeted_ds = dsa_switch_find(dp->ds->dst->index, info_sw_index); targeted_dp = dsa_to_port(targeted_ds, info_port); cpu_dp = targeted_dp->cpu_dp; - if (dsa_switch_is_upstream_of(ds, targeted_ds)) - return port == dsa_towards_port(ds, cpu_dp->ds->index, - cpu_dp->index); + if (dsa_switch_is_upstream_of(dp->ds, targeted_ds)) + return dp->index == dsa_towards_port(dp->ds, cpu_dp->ds->index, + cpu_dp->index); return false; } @@ -209,11 +209,12 @@ static struct dsa_mac_addr *dsa_mac_addr_find(struct list_head *addr_list, return NULL; } -static int dsa_switch_do_mdb_add(struct dsa_switch *ds, int port, - const struct switchdev_obj_port_mdb *mdb) +static int dsa_port_do_mdb_add(struct dsa_port *dp, + const struct switchdev_obj_port_mdb *mdb) { - struct dsa_port *dp = dsa_to_port(ds, port); + struct dsa_switch *ds = dp->ds; struct dsa_mac_addr *a; + int port = dp->index; int err; /* No need to bother with refcounting for user ports */ @@ -244,11 +245,12 @@ static int dsa_switch_do_mdb_add(struct dsa_switch *ds, int port, return 0; } -static int dsa_switch_do_mdb_del(struct dsa_switch *ds, int port, - const struct switchdev_obj_port_mdb *mdb) +static int dsa_port_do_mdb_del(struct dsa_port *dp, + const struct switchdev_obj_port_mdb *mdb) { - struct dsa_port *dp = dsa_to_port(ds, port); + struct dsa_switch *ds = dp->ds; struct dsa_mac_addr *a; + int port = dp->index; int err; /* No need to bother with refcounting for user ports */ @@ -274,11 +276,12 @@ static int dsa_switch_do_mdb_del(struct dsa_switch *ds, int port, return 0; } -static int dsa_switch_do_fdb_add(struct dsa_switch *ds, int port, - const unsigned char *addr, u16 vid) +static int dsa_port_do_fdb_add(struct dsa_port *dp, const unsigned char *addr, + u16 vid) { - struct dsa_port *dp = dsa_to_port(ds, port); + struct dsa_switch *ds = dp->ds; struct dsa_mac_addr *a; + int port = dp->index; int err; /* No need to bother with refcounting for user ports */ @@ -309,11 +312,12 @@ static int dsa_switch_do_fdb_add(struct dsa_switch *ds, int port, return 0; } -static int dsa_switch_do_fdb_del(struct dsa_switch *ds, int port, - const unsigned char *addr, u16 vid) +static int dsa_port_do_fdb_del(struct dsa_port *dp, const unsigned char *addr, + u16 vid) { - struct dsa_port *dp = dsa_to_port(ds, port); + struct dsa_switch *ds = dp->ds; struct dsa_mac_addr *a; + int port = dp->index; int err; /* No need to bother with refcounting for user ports */ @@ -342,17 +346,16 @@ static int dsa_switch_do_fdb_del(struct dsa_switch *ds, int port, static int dsa_switch_host_fdb_add(struct dsa_switch *ds, struct dsa_notifier_fdb_info *info) { + struct dsa_port *dp; int err = 0; - int port; if (!ds->ops->port_fdb_add) return -EOPNOTSUPP; - for (port = 0; port < ds->num_ports; port++) { - if (dsa_switch_host_address_match(ds, port, info->sw_index, - info->port)) { - err = dsa_switch_do_fdb_add(ds, port, info->addr, - info->vid); + dsa_switch_for_each_port(dp, ds) { + if (dsa_port_host_address_match(dp, info->sw_index, + info->port)) { + err = dsa_port_do_fdb_add(dp, info->addr, info->vid); if (err) break; } @@ -364,17 +367,16 @@ static int dsa_switch_host_fdb_add(struct dsa_switch *ds, static int dsa_switch_host_fdb_del(struct dsa_switch *ds, struct dsa_notifier_fdb_info *info) { + struct dsa_port *dp; int err = 0; - int port; if (!ds->ops->port_fdb_del) return -EOPNOTSUPP; - for (port = 0; port < ds->num_ports; port++) { - if (dsa_switch_host_address_match(ds, port, info->sw_index, - info->port)) { - err = dsa_switch_do_fdb_del(ds, port, info->addr, - info->vid); + dsa_switch_for_each_port(dp, ds) { + if (dsa_port_host_address_match(dp, info->sw_index, + info->port)) { + err = dsa_port_do_fdb_del(dp, info->addr, info->vid); if (err) break; } @@ -387,22 +389,24 @@ static int dsa_switch_fdb_add(struct dsa_switch *ds, struct dsa_notifier_fdb_info *info) { int port = dsa_towards_port(ds, info->sw_index, info->port); + struct dsa_port *dp = dsa_to_port(ds, port); if (!ds->ops->port_fdb_add) return -EOPNOTSUPP; - return dsa_switch_do_fdb_add(ds, port, info->addr, info->vid); + return dsa_port_do_fdb_add(dp, info->addr, info->vid); } static int dsa_switch_fdb_del(struct dsa_switch *ds, struct dsa_notifier_fdb_info *info) { int port = dsa_towards_port(ds, info->sw_index, info->port); + struct dsa_port *dp = dsa_to_port(ds, port); if (!ds->ops->port_fdb_del) return -EOPNOTSUPP; - return dsa_switch_do_fdb_del(ds, port, info->addr, info->vid); + return dsa_port_do_fdb_del(dp, info->addr, info->vid); } static int dsa_switch_hsr_join(struct dsa_switch *ds, @@ -468,37 +472,39 @@ static int dsa_switch_mdb_add(struct dsa_switch *ds, struct dsa_notifier_mdb_info *info) { int port = dsa_towards_port(ds, info->sw_index, info->port); + struct dsa_port *dp = dsa_to_port(ds, port); if (!ds->ops->port_mdb_add) return -EOPNOTSUPP; - return dsa_switch_do_mdb_add(ds, port, info->mdb); + return dsa_port_do_mdb_add(dp, info->mdb); } static int dsa_switch_mdb_del(struct dsa_switch *ds, struct dsa_notifier_mdb_info *info) { int port = dsa_towards_port(ds, info->sw_index, info->port); + struct dsa_port *dp = dsa_to_port(ds, port); if (!ds->ops->port_mdb_del) return -EOPNOTSUPP; - return dsa_switch_do_mdb_del(ds, port, info->mdb); + return dsa_port_do_mdb_del(dp, info->mdb); } static int dsa_switch_host_mdb_add(struct dsa_switch *ds, struct dsa_notifier_mdb_info *info) { + struct dsa_port *dp; int err = 0; - int port; if (!ds->ops->port_mdb_add) return -EOPNOTSUPP; - for (port = 0; port < ds->num_ports; port++) { - if (dsa_switch_host_address_match(ds, port, info->sw_index, - info->port)) { - err = dsa_switch_do_mdb_add(ds, port, info->mdb); + dsa_switch_for_each_port(dp, ds) { + if (dsa_port_host_address_match(dp, info->sw_index, + info->port)) { + err = dsa_port_do_mdb_add(dp, info->mdb); if (err) break; } @@ -510,16 +516,16 @@ static int dsa_switch_host_mdb_add(struct dsa_switch *ds, static int dsa_switch_host_mdb_del(struct dsa_switch *ds, struct dsa_notifier_mdb_info *info) { + struct dsa_port *dp; int err = 0; - int port; if (!ds->ops->port_mdb_del) return -EOPNOTSUPP; - for (port = 0; port < ds->num_ports; port++) { - if (dsa_switch_host_address_match(ds, port, info->sw_index, - info->port)) { - err = dsa_switch_do_mdb_del(ds, port, info->mdb); + dsa_switch_for_each_port(dp, ds) { + if (dsa_port_host_address_match(dp, info->sw_index, + info->port)) { + err = dsa_port_do_mdb_del(dp, info->mdb); if (err) break; } @@ -528,13 +534,13 @@ static int dsa_switch_host_mdb_del(struct dsa_switch *ds, return err; } -static bool dsa_switch_vlan_match(struct dsa_switch *ds, int port, - struct dsa_notifier_vlan_info *info) +static bool dsa_port_vlan_match(struct dsa_port *dp, + struct dsa_notifier_vlan_info *info) { - if (ds->index == info->sw_index && port == info->port) + if (dp->ds->index == info->sw_index && dp->index == info->port) return true; - if (dsa_is_dsa_port(ds, port)) + if (dsa_port_is_dsa(dp)) return true; return false; @@ -543,14 +549,15 @@ static bool dsa_switch_vlan_match(struct dsa_switch *ds, int port, static int dsa_switch_vlan_add(struct dsa_switch *ds, struct dsa_notifier_vlan_info *info) { - int port, err; + struct dsa_port *dp; + int err; if (!ds->ops->port_vlan_add) return -EOPNOTSUPP; - for (port = 0; port < ds->num_ports; port++) { - if (dsa_switch_vlan_match(ds, port, info)) { - err = ds->ops->port_vlan_add(ds, port, info->vlan, + dsa_switch_for_each_port(dp, ds) { + if (dsa_port_vlan_match(dp, info)) { + err = ds->ops->port_vlan_add(ds, dp->index, info->vlan, info->extack); if (err) return err; @@ -579,38 +586,34 @@ static int dsa_switch_change_tag_proto(struct dsa_switch *ds, struct dsa_notifier_tag_proto_info *info) { const struct dsa_device_ops *tag_ops = info->tag_ops; - int port, err; + struct dsa_port *dp, *cpu_dp; + int err; if (!ds->ops->change_tag_protocol) return -EOPNOTSUPP; ASSERT_RTNL(); - for (port = 0; port < ds->num_ports; port++) { - if (!dsa_is_cpu_port(ds, port)) - continue; - - err = ds->ops->change_tag_protocol(ds, port, tag_ops->proto); + dsa_switch_for_each_cpu_port(cpu_dp, ds) { + err = ds->ops->change_tag_protocol(ds, cpu_dp->index, + tag_ops->proto); if (err) return err; - dsa_port_set_tag_protocol(dsa_to_port(ds, port), tag_ops); + dsa_port_set_tag_protocol(cpu_dp, tag_ops); } /* Now that changing the tag protocol can no longer fail, let's update * the remaining bits which are "duplicated for faster access", and the * bits that depend on the tagger, such as the MTU. */ - for (port = 0; port < ds->num_ports; port++) { - if (dsa_is_user_port(ds, port)) { - struct net_device *slave; + dsa_switch_for_each_user_port(dp, ds) { + struct net_device *slave = dp->slave; - slave = dsa_to_port(ds, port)->slave; - dsa_slave_setup_tagger(slave); + dsa_slave_setup_tagger(slave); - /* rtnl_mutex is held in dsa_tree_change_tag_proto */ - dsa_slave_change_mtu(slave, slave->mtu); - } + /* rtnl_mutex is held in dsa_tree_change_tag_proto */ + dsa_slave_change_mtu(slave, slave->mtu); } return 0; diff --git a/net/dsa/tag_8021q.c b/net/dsa/tag_8021q.c index 935d0264ebd8..72cac2c0af7b 100644 --- a/net/dsa/tag_8021q.c +++ b/net/dsa/tag_8021q.c @@ -77,22 +77,22 @@ EXPORT_SYMBOL_GPL(dsa_8021q_bridge_tx_fwd_offload_vid); /* Returns the VID to be inserted into the frame from xmit for switch steering * instructions on egress. Encodes switch ID and port ID. */ -u16 dsa_8021q_tx_vid(struct dsa_switch *ds, int port) +u16 dsa_tag_8021q_tx_vid(const struct dsa_port *dp) { - return DSA_8021Q_DIR_TX | DSA_8021Q_SWITCH_ID(ds->index) | - DSA_8021Q_PORT(port); + return DSA_8021Q_DIR_TX | DSA_8021Q_SWITCH_ID(dp->ds->index) | + DSA_8021Q_PORT(dp->index); } -EXPORT_SYMBOL_GPL(dsa_8021q_tx_vid); +EXPORT_SYMBOL_GPL(dsa_tag_8021q_tx_vid); /* Returns the VID that will be installed as pvid for this switch port, sent as * tagged egress towards the CPU port and decoded by the rcv function. */ -u16 dsa_8021q_rx_vid(struct dsa_switch *ds, int port) +u16 dsa_tag_8021q_rx_vid(const struct dsa_port *dp) { - return DSA_8021Q_DIR_RX | DSA_8021Q_SWITCH_ID(ds->index) | - DSA_8021Q_PORT(port); + return DSA_8021Q_DIR_RX | DSA_8021Q_SWITCH_ID(dp->ds->index) | + DSA_8021Q_PORT(dp->index); } -EXPORT_SYMBOL_GPL(dsa_8021q_rx_vid); +EXPORT_SYMBOL_GPL(dsa_tag_8021q_rx_vid); /* Returns the decoded switch ID from the RX VID. */ int dsa_8021q_rx_switch_id(u16 vid) @@ -138,12 +138,13 @@ dsa_tag_8021q_vlan_find(struct dsa_8021q_context *ctx, int port, u16 vid) return NULL; } -static int dsa_switch_do_tag_8021q_vlan_add(struct dsa_switch *ds, int port, - u16 vid, u16 flags) +static int dsa_port_do_tag_8021q_vlan_add(struct dsa_port *dp, u16 vid, + u16 flags) { - struct dsa_8021q_context *ctx = ds->tag_8021q_ctx; - struct dsa_port *dp = dsa_to_port(ds, port); + struct dsa_8021q_context *ctx = dp->ds->tag_8021q_ctx; + struct dsa_switch *ds = dp->ds; struct dsa_tag_8021q_vlan *v; + int port = dp->index; int err; /* No need to bother with refcounting for user ports */ @@ -174,12 +175,12 @@ static int dsa_switch_do_tag_8021q_vlan_add(struct dsa_switch *ds, int port, return 0; } -static int dsa_switch_do_tag_8021q_vlan_del(struct dsa_switch *ds, int port, - u16 vid) +static int dsa_port_do_tag_8021q_vlan_del(struct dsa_port *dp, u16 vid) { - struct dsa_8021q_context *ctx = ds->tag_8021q_ctx; - struct dsa_port *dp = dsa_to_port(ds, port); + struct dsa_8021q_context *ctx = dp->ds->tag_8021q_ctx; + struct dsa_switch *ds = dp->ds; struct dsa_tag_8021q_vlan *v; + int port = dp->index; int err; /* No need to bother with refcounting for user ports */ @@ -206,14 +207,16 @@ static int dsa_switch_do_tag_8021q_vlan_del(struct dsa_switch *ds, int port, } static bool -dsa_switch_tag_8021q_vlan_match(struct dsa_switch *ds, int port, - struct dsa_notifier_tag_8021q_vlan_info *info) +dsa_port_tag_8021q_vlan_match(struct dsa_port *dp, + struct dsa_notifier_tag_8021q_vlan_info *info) { - if (dsa_is_dsa_port(ds, port) || dsa_is_cpu_port(ds, port)) + struct dsa_switch *ds = dp->ds; + + if (dsa_port_is_dsa(dp) || dsa_port_is_cpu(dp)) return true; if (ds->dst->index == info->tree_index && ds->index == info->sw_index) - return port == info->port; + return dp->index == info->port; return false; } @@ -221,7 +224,8 @@ dsa_switch_tag_8021q_vlan_match(struct dsa_switch *ds, int port, int dsa_switch_tag_8021q_vlan_add(struct dsa_switch *ds, struct dsa_notifier_tag_8021q_vlan_info *info) { - int port, err; + struct dsa_port *dp; + int err; /* Since we use dsa_broadcast(), there might be other switches in other * trees which don't support tag_8021q, so don't return an error. @@ -231,21 +235,20 @@ int dsa_switch_tag_8021q_vlan_add(struct dsa_switch *ds, if (!ds->ops->tag_8021q_vlan_add || !ds->tag_8021q_ctx) return 0; - for (port = 0; port < ds->num_ports; port++) { - if (dsa_switch_tag_8021q_vlan_match(ds, port, info)) { + dsa_switch_for_each_port(dp, ds) { + if (dsa_port_tag_8021q_vlan_match(dp, info)) { u16 flags = 0; - if (dsa_is_user_port(ds, port)) + if (dsa_port_is_user(dp)) flags |= BRIDGE_VLAN_INFO_UNTAGGED; if (vid_is_dsa_8021q_rxvlan(info->vid) && dsa_8021q_rx_switch_id(info->vid) == ds->index && - dsa_8021q_rx_source_port(info->vid) == port) + dsa_8021q_rx_source_port(info->vid) == dp->index) flags |= BRIDGE_VLAN_INFO_PVID; - err = dsa_switch_do_tag_8021q_vlan_add(ds, port, - info->vid, - flags); + err = dsa_port_do_tag_8021q_vlan_add(dp, info->vid, + flags); if (err) return err; } @@ -257,15 +260,15 @@ int dsa_switch_tag_8021q_vlan_add(struct dsa_switch *ds, int dsa_switch_tag_8021q_vlan_del(struct dsa_switch *ds, struct dsa_notifier_tag_8021q_vlan_info *info) { - int port, err; + struct dsa_port *dp; + int err; if (!ds->ops->tag_8021q_vlan_del || !ds->tag_8021q_ctx) return 0; - for (port = 0; port < ds->num_ports; port++) { - if (dsa_switch_tag_8021q_vlan_match(ds, port, info)) { - err = dsa_switch_do_tag_8021q_vlan_del(ds, port, - info->vid); + dsa_switch_for_each_port(dp, ds) { + if (dsa_port_tag_8021q_vlan_match(dp, info)) { + err = dsa_port_do_tag_8021q_vlan_del(dp, info->vid); if (err) return err; } @@ -321,15 +324,14 @@ int dsa_switch_tag_8021q_vlan_del(struct dsa_switch *ds, * +-+-----+-+-----+-+-----+-+-----+-+ +-+-----+-+-----+-+-----+-+-----+-+ * swp0 swp1 swp2 swp3 swp0 swp1 swp2 swp3 */ -static bool dsa_tag_8021q_bridge_match(struct dsa_switch *ds, int port, - struct dsa_notifier_bridge_info *info) +static bool +dsa_port_tag_8021q_bridge_match(struct dsa_port *dp, + struct dsa_notifier_bridge_info *info) { - struct dsa_port *dp = dsa_to_port(ds, port); - /* Don't match on self */ - if (ds->dst->index == info->tree_index && - ds->index == info->sw_index && - port == info->port) + if (dp->ds->dst->index == info->tree_index && + dp->ds->index == info->sw_index && + dp->index == info->port) return false; if (dsa_port_is_user(dp)) @@ -343,21 +345,21 @@ int dsa_tag_8021q_bridge_join(struct dsa_switch *ds, { struct dsa_switch *targeted_ds; struct dsa_port *targeted_dp; + struct dsa_port *dp; u16 targeted_rx_vid; - int err, port; + int err; if (!ds->tag_8021q_ctx) return 0; targeted_ds = dsa_switch_find(info->tree_index, info->sw_index); targeted_dp = dsa_to_port(targeted_ds, info->port); - targeted_rx_vid = dsa_8021q_rx_vid(targeted_ds, info->port); + targeted_rx_vid = dsa_tag_8021q_rx_vid(targeted_dp); - for (port = 0; port < ds->num_ports; port++) { - struct dsa_port *dp = dsa_to_port(ds, port); - u16 rx_vid = dsa_8021q_rx_vid(ds, port); + dsa_switch_for_each_port(dp, ds) { + u16 rx_vid = dsa_tag_8021q_rx_vid(dp); - if (!dsa_tag_8021q_bridge_match(ds, port, info)) + if (!dsa_port_tag_8021q_bridge_match(dp, info)) continue; /* Install the RX VID of the targeted port in our VLAN table */ @@ -379,21 +381,20 @@ int dsa_tag_8021q_bridge_leave(struct dsa_switch *ds, { struct dsa_switch *targeted_ds; struct dsa_port *targeted_dp; + struct dsa_port *dp; u16 targeted_rx_vid; - int port; if (!ds->tag_8021q_ctx) return 0; targeted_ds = dsa_switch_find(info->tree_index, info->sw_index); targeted_dp = dsa_to_port(targeted_ds, info->port); - targeted_rx_vid = dsa_8021q_rx_vid(targeted_ds, info->port); + targeted_rx_vid = dsa_tag_8021q_rx_vid(targeted_dp); - for (port = 0; port < ds->num_ports; port++) { - struct dsa_port *dp = dsa_to_port(ds, port); - u16 rx_vid = dsa_8021q_rx_vid(ds, port); + dsa_switch_for_each_port(dp, ds) { + u16 rx_vid = dsa_tag_8021q_rx_vid(dp); - if (!dsa_tag_8021q_bridge_match(ds, port, info)) + if (!dsa_port_tag_8021q_bridge_match(dp, info)) continue; /* Remove the RX VID of the targeted port from our VLAN table */ @@ -432,8 +433,8 @@ static int dsa_tag_8021q_port_setup(struct dsa_switch *ds, int port) { struct dsa_8021q_context *ctx = ds->tag_8021q_ctx; struct dsa_port *dp = dsa_to_port(ds, port); - u16 rx_vid = dsa_8021q_rx_vid(ds, port); - u16 tx_vid = dsa_8021q_tx_vid(ds, port); + u16 rx_vid = dsa_tag_8021q_rx_vid(dp); + u16 tx_vid = dsa_tag_8021q_tx_vid(dp); struct net_device *master; int err; @@ -477,8 +478,8 @@ static void dsa_tag_8021q_port_teardown(struct dsa_switch *ds, int port) { struct dsa_8021q_context *ctx = ds->tag_8021q_ctx; struct dsa_port *dp = dsa_to_port(ds, port); - u16 rx_vid = dsa_8021q_rx_vid(ds, port); - u16 tx_vid = dsa_8021q_tx_vid(ds, port); + u16 rx_vid = dsa_tag_8021q_rx_vid(dp); + u16 tx_vid = dsa_tag_8021q_tx_vid(dp); struct net_device *master; /* The CPU port is implicitly configured by diff --git a/net/dsa/tag_ocelot_8021q.c b/net/dsa/tag_ocelot_8021q.c index 3412051981d7..a1919ea5e828 100644 --- a/net/dsa/tag_ocelot_8021q.c +++ b/net/dsa/tag_ocelot_8021q.c @@ -39,9 +39,9 @@ static struct sk_buff *ocelot_xmit(struct sk_buff *skb, struct net_device *netdev) { struct dsa_port *dp = dsa_slave_to_port(netdev); - u16 tx_vid = dsa_8021q_tx_vid(dp->ds, dp->index); u16 queue_mapping = skb_get_queue_mapping(skb); u8 pcp = netdev_txq_to_tc(netdev, queue_mapping); + u16 tx_vid = dsa_tag_8021q_tx_vid(dp); struct ethhdr *hdr = eth_hdr(skb); if (ocelot_ptp_rew_op(skb) || is_link_local_ether_addr(hdr->h_dest)) diff --git a/net/dsa/tag_rtl8_4.c b/net/dsa/tag_rtl8_4.c new file mode 100644 index 000000000000..02686ad4045d --- /dev/null +++ b/net/dsa/tag_rtl8_4.c @@ -0,0 +1,178 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Handler for Realtek 8 byte switch tags + * + * Copyright (C) 2021 Alvin Šipraga + * + * NOTE: Currently only supports protocol "4" found in the RTL8365MB, hence + * named tag_rtl8_4. + * + * This tag header has the following format: + * + * ------------------------------------------- + * | MAC DA | MAC SA | 8 byte tag | Type | ... + * ------------------------------------------- + * _______________/ \______________________________________ + * / \ + * 0 7|8 15 + * |-----------------------------------+-----------------------------------|--- + * | (16-bit) | ^ + * | Realtek EtherType [0x8899] | | + * |-----------------------------------+-----------------------------------| 8 + * | (8-bit) | (8-bit) | + * | Protocol [0x04] | REASON | b + * |-----------------------------------+-----------------------------------| y + * | (1) | (1) | (2) | (1) | (3) | (1) | (1) | (1) | (5) | t + * | FID_EN | X | FID | PRI_EN | PRI | KEEP | X | LEARN_DIS | X | e + * |-----------------------------------+-----------------------------------| s + * | (1) | (15-bit) | | + * | ALLOW | TX/RX | v + * |-----------------------------------+-----------------------------------|--- + * + * With the following field descriptions: + * + * field | description + * ------------+------------- + * Realtek | 0x8899: indicates that this is a proprietary Realtek tag; + * EtherType | note that Realtek uses the same EtherType for + * | other incompatible tag formats (e.g. tag_rtl4_a.c) + * Protocol | 0x04: indicates that this tag conforms to this format + * X | reserved + * ------------+------------- + * REASON | reason for forwarding packet to CPU + * | 0: packet was forwarded or flooded to CPU + * | 80: packet was trapped to CPU + * FID_EN | 1: packet has an FID + * | 0: no FID + * FID | FID of packet (if FID_EN=1) + * PRI_EN | 1: force priority of packet + * | 0: don't force priority + * PRI | priority of packet (if PRI_EN=1) + * KEEP | preserve packet VLAN tag format + * LEARN_DIS | don't learn the source MAC address of the packet + * ALLOW | 1: treat TX/RX field as an allowance port mask, meaning the + * | packet may only be forwarded to ports specified in the + * | mask + * | 0: no allowance port mask, TX/RX field is the forwarding + * | port mask + * TX/RX | TX (switch->CPU): port number the packet was received on + * | RX (CPU->switch): forwarding port mask (if ALLOW=0) + * | allowance port mask (if ALLOW=1) + */ + +#include +#include +#include + +#include "dsa_priv.h" + +/* Protocols supported: + * + * 0x04 = RTL8365MB DSA protocol + */ + +#define RTL8_4_TAG_LEN 8 + +#define RTL8_4_PROTOCOL GENMASK(15, 8) +#define RTL8_4_PROTOCOL_RTL8365MB 0x04 +#define RTL8_4_REASON GENMASK(7, 0) +#define RTL8_4_REASON_FORWARD 0 +#define RTL8_4_REASON_TRAP 80 + +#define RTL8_4_LEARN_DIS BIT(5) + +#define RTL8_4_TX GENMASK(3, 0) +#define RTL8_4_RX GENMASK(10, 0) + +static struct sk_buff *rtl8_4_tag_xmit(struct sk_buff *skb, + struct net_device *dev) +{ + struct dsa_port *dp = dsa_slave_to_port(dev); + __be16 *tag; + + skb_push(skb, RTL8_4_TAG_LEN); + + dsa_alloc_etype_header(skb, RTL8_4_TAG_LEN); + tag = dsa_etype_header_pos_tx(skb); + + /* Set Realtek EtherType */ + tag[0] = htons(ETH_P_REALTEK); + + /* Set Protocol; zero REASON */ + tag[1] = htons(FIELD_PREP(RTL8_4_PROTOCOL, RTL8_4_PROTOCOL_RTL8365MB)); + + /* Zero FID_EN, FID, PRI_EN, PRI, KEEP; set LEARN_DIS */ + tag[2] = htons(FIELD_PREP(RTL8_4_LEARN_DIS, 1)); + + /* Zero ALLOW; set RX (CPU->switch) forwarding port mask */ + tag[3] = htons(FIELD_PREP(RTL8_4_RX, BIT(dp->index))); + + return skb; +} + +static struct sk_buff *rtl8_4_tag_rcv(struct sk_buff *skb, + struct net_device *dev) +{ + __be16 *tag; + u16 etype; + u8 reason; + u8 proto; + u8 port; + + if (unlikely(!pskb_may_pull(skb, RTL8_4_TAG_LEN))) + return NULL; + + tag = dsa_etype_header_pos_rx(skb); + + /* Parse Realtek EtherType */ + etype = ntohs(tag[0]); + if (unlikely(etype != ETH_P_REALTEK)) { + dev_warn_ratelimited(&dev->dev, + "non-realtek ethertype 0x%04x\n", etype); + return NULL; + } + + /* Parse Protocol */ + proto = FIELD_GET(RTL8_4_PROTOCOL, ntohs(tag[1])); + if (unlikely(proto != RTL8_4_PROTOCOL_RTL8365MB)) { + dev_warn_ratelimited(&dev->dev, + "unknown realtek protocol 0x%02x\n", + proto); + return NULL; + } + + /* Parse REASON */ + reason = FIELD_GET(RTL8_4_REASON, ntohs(tag[1])); + + /* Parse TX (switch->CPU) */ + port = FIELD_GET(RTL8_4_TX, ntohs(tag[3])); + skb->dev = dsa_master_find_slave(dev, 0, port); + if (!skb->dev) { + dev_warn_ratelimited(&dev->dev, + "could not find slave for port %d\n", + port); + return NULL; + } + + /* Remove tag and recalculate checksum */ + skb_pull_rcsum(skb, RTL8_4_TAG_LEN); + + dsa_strip_etype_header(skb, RTL8_4_TAG_LEN); + + if (reason != RTL8_4_REASON_TRAP) + dsa_default_offload_fwd_mark(skb); + + return skb; +} + +static const struct dsa_device_ops rtl8_4_netdev_ops = { + .name = "rtl8_4", + .proto = DSA_TAG_PROTO_RTL8_4, + .xmit = rtl8_4_tag_xmit, + .rcv = rtl8_4_tag_rcv, + .needed_headroom = RTL8_4_TAG_LEN, +}; +module_dsa_tag_driver(rtl8_4_netdev_ops); + +MODULE_LICENSE("GPL"); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_RTL8_4); diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c index 2edede9ddac9..262c8833a910 100644 --- a/net/dsa/tag_sja1105.c +++ b/net/dsa/tag_sja1105.c @@ -158,10 +158,7 @@ static u16 sja1105_xmit_tpid(struct dsa_port *dp) * we're sure about that). It may not be on this port though, so we * need to find it. */ - list_for_each_entry(other_dp, &ds->dst->ports, list) { - if (other_dp->ds != ds) - continue; - + dsa_switch_for_each_port(other_dp, ds) { if (!other_dp->bridge_dev) continue; @@ -238,9 +235,9 @@ static struct sk_buff *sja1105_xmit(struct sk_buff *skb, struct net_device *netdev) { struct dsa_port *dp = dsa_slave_to_port(netdev); - u16 tx_vid = dsa_8021q_tx_vid(dp->ds, dp->index); u16 queue_mapping = skb_get_queue_mapping(skb); u8 pcp = netdev_txq_to_tc(netdev, queue_mapping); + u16 tx_vid = dsa_tag_8021q_tx_vid(dp); if (skb->offload_fwd_mark) return sja1105_imprecise_xmit(skb, netdev); @@ -266,9 +263,9 @@ static struct sk_buff *sja1110_xmit(struct sk_buff *skb, { struct sk_buff *clone = SJA1105_SKB_CB(skb)->clone; struct dsa_port *dp = dsa_slave_to_port(netdev); - u16 tx_vid = dsa_8021q_tx_vid(dp->ds, dp->index); u16 queue_mapping = skb_get_queue_mapping(skb); u8 pcp = netdev_txq_to_tc(netdev, queue_mapping); + u16 tx_vid = dsa_tag_8021q_tx_vid(dp); __be32 *tx_trailer; __be16 *tx_header; int trailer_pos; diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index d7b8fa10fabb..c7d9e08107cb 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -523,6 +523,26 @@ int eth_platform_get_mac_address(struct device *dev, u8 *mac_addr) } EXPORT_SYMBOL(eth_platform_get_mac_address); +/** + * platform_get_ethdev_address - Set netdev's MAC address from a given device + * @dev: Pointer to the device + * @netdev: Pointer to netdev to write the address to + * + * Wrapper around eth_platform_get_mac_address() which writes the address + * directly to netdev->dev_addr. + */ +int platform_get_ethdev_address(struct device *dev, struct net_device *netdev) +{ + u8 addr[ETH_ALEN] __aligned(2); + int ret; + + ret = eth_platform_get_mac_address(dev, addr); + if (!ret) + eth_hw_addr_set(netdev, addr); + return ret; +} +EXPORT_SYMBOL(platform_get_ethdev_address); + /** * nvmem_get_mac_address - Obtain the MAC address from an nvmem cell named * 'mac-address' associated with given device. @@ -558,7 +578,6 @@ int nvmem_get_mac_address(struct device *dev, void *addrbuf) return 0; } -EXPORT_SYMBOL(nvmem_get_mac_address); static int fwnode_get_mac_addr(struct fwnode_handle *fwnode, const char *name, char *addr) diff --git a/net/ieee802154/6lowpan/core.c b/net/ieee802154/6lowpan/core.c index 3297e7fa9945..2cf62718a282 100644 --- a/net/ieee802154/6lowpan/core.c +++ b/net/ieee802154/6lowpan/core.c @@ -157,7 +157,7 @@ static int lowpan_newlink(struct net *src_net, struct net_device *ldev, lowpan_802154_dev(ldev)->wdev = wdev; /* Set the lowpan hardware address to the wpan hardware address. */ - memcpy(ldev->dev_addr, wdev->dev_addr, IEEE802154_ADDR_LEN); + __dev_addr_set(ldev, wdev->dev_addr, IEEE802154_ADDR_LEN); /* We need headroom for possible wpan_dev_hard_header call and tailroom * for encryption/fcs handling. The lowpan interface will replace * the IPv6 header with 6LoWPAN header. At worst case the 6LoWPAN diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index f25d02ad4a8a..f7fea3a7c5e6 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -1015,7 +1015,7 @@ void inet_csk_destroy_sock(struct sock *sk) sk_refcnt_debug_release(sk); - percpu_counter_dec(sk->sk_prot->orphan_count); + this_cpu_dec(*sk->sk_prot->orphan_count); sock_put(sk); } @@ -1074,7 +1074,7 @@ static void inet_child_forget(struct sock *sk, struct request_sock *req, sock_orphan(child); - percpu_counter_inc(sk->sk_prot->orphan_count); + this_cpu_inc(*sk->sk_prot->orphan_count); if (sk->sk_protocol == IPPROTO_TCP && tcp_rsk(req)->tfo_listener) { BUG_ON(rcu_access_pointer(tcp_sk(child)->fastopen_rsk) != req); diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index bfb522e51346..75737267746f 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -598,7 +598,7 @@ bool inet_ehash_nolisten(struct sock *sk, struct sock *osk, bool *found_dup_sk) if (ok) { sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); } else { - percpu_counter_inc(sk->sk_prot->orphan_count); + this_cpu_inc(*sk->sk_prot->orphan_count); inet_sk_set_state(sk, TCP_CLOSE); sock_set_flag(sk, SOCK_DEAD); inet_csk_destroy_sock(sk); diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 0fe6c936dc54..2ac2b95c5694 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -986,7 +986,7 @@ static int ipgre_tunnel_init(struct net_device *dev) __gre_tunnel_init(dev); - memcpy(dev->dev_addr, &iph->saddr, 4); + __dev_addr_set(dev, &iph->saddr, 4); memcpy(dev->broadcast, &iph->daddr, 4); dev->flags = IFF_NOARP; diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index fe9101d3d69e..5a473319d3a5 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -834,7 +834,7 @@ static void ip_tunnel_update(struct ip_tunnel_net *itn, t->parms.i_key = p->i_key; t->parms.o_key = p->o_key; if (dev->type != ARPHRD_ETHER) { - memcpy(dev->dev_addr, &p->iph.saddr, 4); + __dev_addr_set(dev, &p->iph.saddr, 4); memcpy(dev->broadcast, &p->iph.daddr, 4); } ip_tunnel_add(itn, t); diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index efe25a0172e6..8c2bd1d9ddce 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -425,7 +425,7 @@ static int vti_tunnel_init(struct net_device *dev) struct ip_tunnel *tunnel = netdev_priv(dev); struct iphdr *iph = &tunnel->parms.iph; - memcpy(dev->dev_addr, &iph->saddr, 4); + __dev_addr_set(dev, &iph->saddr, 4); memcpy(dev->broadcast, &iph->daddr, 4); dev->flags = IFF_NOARP; diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 3aa78ccbec3e..123ea63a04cb 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -380,7 +380,7 @@ static int ipip_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); - memcpy(dev->dev_addr, &tunnel->parms.iph.saddr, 4); + __dev_addr_set(dev, &tunnel->parms.iph.saddr, 4); memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4); tunnel->tun_hlen = 0; diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index c53f14b94356..ffc0cab7cf18 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -179,10 +179,11 @@ struct arpt_entry *arpt_next_entry(const struct arpt_entry *entry) return (void *)entry + entry->next_offset; } -unsigned int arpt_do_table(struct sk_buff *skb, - const struct nf_hook_state *state, - struct xt_table *table) +unsigned int arpt_do_table(void *priv, + struct sk_buff *skb, + const struct nf_hook_state *state) { + const struct xt_table *table = priv; unsigned int hook = state->hook; static const char nulldevname[IFNAMSIZ] __attribute__((aligned(sizeof(long)))); unsigned int verdict = NF_DROP; diff --git a/net/ipv4/netfilter/arptable_filter.c b/net/ipv4/netfilter/arptable_filter.c index 3de78416ec76..78cd5ee24448 100644 --- a/net/ipv4/netfilter/arptable_filter.c +++ b/net/ipv4/netfilter/arptable_filter.c @@ -26,14 +26,6 @@ static const struct xt_table packet_filter = { .priority = NF_IP_PRI_FILTER, }; -/* The work comes in here from netfilter.c */ -static unsigned int -arptable_filter_hook(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state) -{ - return arpt_do_table(skb, state, priv); -} - static struct nf_hook_ops *arpfilter_ops __read_mostly; static int arptable_filter_table_init(struct net *net) @@ -72,7 +64,7 @@ static int __init arptable_filter_init(void) if (ret < 0) return ret; - arpfilter_ops = xt_hook_ops_alloc(&packet_filter, arptable_filter_hook); + arpfilter_ops = xt_hook_ops_alloc(&packet_filter, arpt_do_table); if (IS_ERR(arpfilter_ops)) { xt_unregister_template(&packet_filter); return PTR_ERR(arpfilter_ops); diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 13acb687c19a..2ed7c58b471a 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -222,10 +222,11 @@ struct ipt_entry *ipt_next_entry(const struct ipt_entry *entry) /* Returns one of the generic firewall policies, like NF_ACCEPT. */ unsigned int -ipt_do_table(struct sk_buff *skb, - const struct nf_hook_state *state, - struct xt_table *table) +ipt_do_table(void *priv, + struct sk_buff *skb, + const struct nf_hook_state *state) { + const struct xt_table *table = priv; unsigned int hook = state->hook; static const char nulldevname[IFNAMSIZ] __attribute__((aligned(sizeof(long)))); const struct iphdr *ip; diff --git a/net/ipv4/netfilter/iptable_filter.c b/net/ipv4/netfilter/iptable_filter.c index 0eb0e2ab9bfc..b9062f4552ac 100644 --- a/net/ipv4/netfilter/iptable_filter.c +++ b/net/ipv4/netfilter/iptable_filter.c @@ -28,13 +28,6 @@ static const struct xt_table packet_filter = { .priority = NF_IP_PRI_FILTER, }; -static unsigned int -iptable_filter_hook(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state) -{ - return ipt_do_table(skb, state, priv); -} - static struct nf_hook_ops *filter_ops __read_mostly; /* Default to forward because I got too much mail already. */ @@ -90,7 +83,7 @@ static int __init iptable_filter_init(void) if (ret < 0) return ret; - filter_ops = xt_hook_ops_alloc(&packet_filter, iptable_filter_hook); + filter_ops = xt_hook_ops_alloc(&packet_filter, ipt_do_table); if (IS_ERR(filter_ops)) { xt_unregister_template(&packet_filter); return PTR_ERR(filter_ops); diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c index 40417a3f930b..3abb430af9e6 100644 --- a/net/ipv4/netfilter/iptable_mangle.c +++ b/net/ipv4/netfilter/iptable_mangle.c @@ -34,7 +34,7 @@ static const struct xt_table packet_mangler = { }; static unsigned int -ipt_mangle_out(struct sk_buff *skb, const struct nf_hook_state *state, void *priv) +ipt_mangle_out(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { unsigned int ret; const struct iphdr *iph; @@ -50,7 +50,7 @@ ipt_mangle_out(struct sk_buff *skb, const struct nf_hook_state *state, void *pri daddr = iph->daddr; tos = iph->tos; - ret = ipt_do_table(skb, state, priv); + ret = ipt_do_table(priv, skb, state); /* Reroute for ANY change. */ if (ret != NF_DROP && ret != NF_STOLEN) { iph = ip_hdr(skb); @@ -75,8 +75,8 @@ iptable_mangle_hook(void *priv, const struct nf_hook_state *state) { if (state->hook == NF_INET_LOCAL_OUT) - return ipt_mangle_out(skb, state, priv); - return ipt_do_table(skb, state, priv); + return ipt_mangle_out(priv, skb, state); + return ipt_do_table(priv, skb, state); } static struct nf_hook_ops *mangle_ops __read_mostly; diff --git a/net/ipv4/netfilter/iptable_nat.c b/net/ipv4/netfilter/iptable_nat.c index 45d7e072e6a5..56f6ecc43451 100644 --- a/net/ipv4/netfilter/iptable_nat.c +++ b/net/ipv4/netfilter/iptable_nat.c @@ -29,34 +29,27 @@ static const struct xt_table nf_nat_ipv4_table = { .af = NFPROTO_IPV4, }; -static unsigned int iptable_nat_do_chain(void *priv, - struct sk_buff *skb, - const struct nf_hook_state *state) -{ - return ipt_do_table(skb, state, priv); -} - static const struct nf_hook_ops nf_nat_ipv4_ops[] = { { - .hook = iptable_nat_do_chain, + .hook = ipt_do_table, .pf = NFPROTO_IPV4, .hooknum = NF_INET_PRE_ROUTING, .priority = NF_IP_PRI_NAT_DST, }, { - .hook = iptable_nat_do_chain, + .hook = ipt_do_table, .pf = NFPROTO_IPV4, .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP_PRI_NAT_SRC, }, { - .hook = iptable_nat_do_chain, + .hook = ipt_do_table, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP_PRI_NAT_DST, }, { - .hook = iptable_nat_do_chain, + .hook = ipt_do_table, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP_PRI_NAT_SRC, diff --git a/net/ipv4/netfilter/iptable_raw.c b/net/ipv4/netfilter/iptable_raw.c index 8265c6765705..ca5e5b21587c 100644 --- a/net/ipv4/netfilter/iptable_raw.c +++ b/net/ipv4/netfilter/iptable_raw.c @@ -32,14 +32,6 @@ static const struct xt_table packet_raw_before_defrag = { .priority = NF_IP_PRI_RAW_BEFORE_DEFRAG, }; -/* The work comes in here from netfilter.c. */ -static unsigned int -iptable_raw_hook(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state) -{ - return ipt_do_table(skb, state, priv); -} - static struct nf_hook_ops *rawtable_ops __read_mostly; static int iptable_raw_table_init(struct net *net) @@ -90,7 +82,7 @@ static int __init iptable_raw_init(void) if (ret < 0) return ret; - rawtable_ops = xt_hook_ops_alloc(table, iptable_raw_hook); + rawtable_ops = xt_hook_ops_alloc(table, ipt_do_table); if (IS_ERR(rawtable_ops)) { xt_unregister_template(table); return PTR_ERR(rawtable_ops); diff --git a/net/ipv4/netfilter/iptable_security.c b/net/ipv4/netfilter/iptable_security.c index f519162a2fa5..d885443cb267 100644 --- a/net/ipv4/netfilter/iptable_security.c +++ b/net/ipv4/netfilter/iptable_security.c @@ -33,13 +33,6 @@ static const struct xt_table security_table = { .priority = NF_IP_PRI_SECURITY, }; -static unsigned int -iptable_security_hook(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state) -{ - return ipt_do_table(skb, state, priv); -} - static struct nf_hook_ops *sectbl_ops __read_mostly; static int iptable_security_table_init(struct net *net) @@ -78,7 +71,7 @@ static int __init iptable_security_init(void) if (ret < 0) return ret; - sectbl_ops = xt_hook_ops_alloc(&security_table, iptable_security_hook); + sectbl_ops = xt_hook_ops_alloc(&security_table, ipt_do_table); if (IS_ERR(sectbl_ops)) { xt_unregister_template(&security_table); return PTR_ERR(sectbl_ops); diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index b0d3a09dc84e..f30273afb539 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -53,7 +53,7 @@ static int sockstat_seq_show(struct seq_file *seq, void *v) struct net *net = seq->private; int orphans, sockets; - orphans = percpu_counter_sum_positive(&tcp_orphan_count); + orphans = tcp_orphan_count_sum(); sockets = proto_sockets_allocated_sum_positive(&tcp_prot); socket_seq_show(seq); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index e35d2c65d57f..bf22a4c11515 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -287,8 +287,8 @@ enum { TCP_CMSG_TS = 2 }; -struct percpu_counter tcp_orphan_count; -EXPORT_SYMBOL_GPL(tcp_orphan_count); +DEFINE_PER_CPU(unsigned int, tcp_orphan_count); +EXPORT_PER_CPU_SYMBOL_GPL(tcp_orphan_count); long sysctl_tcp_mem[3] __read_mostly; EXPORT_SYMBOL(sysctl_tcp_mem); @@ -2670,11 +2670,36 @@ void tcp_shutdown(struct sock *sk, int how) } EXPORT_SYMBOL(tcp_shutdown); +int tcp_orphan_count_sum(void) +{ + int i, total = 0; + + for_each_possible_cpu(i) + total += per_cpu(tcp_orphan_count, i); + + return max(total, 0); +} + +static int tcp_orphan_cache; +static struct timer_list tcp_orphan_timer; +#define TCP_ORPHAN_TIMER_PERIOD msecs_to_jiffies(100) + +static void tcp_orphan_update(struct timer_list *unused) +{ + WRITE_ONCE(tcp_orphan_cache, tcp_orphan_count_sum()); + mod_timer(&tcp_orphan_timer, jiffies + TCP_ORPHAN_TIMER_PERIOD); +} + +static bool tcp_too_many_orphans(int shift) +{ + return READ_ONCE(tcp_orphan_cache) << shift > sysctl_tcp_max_orphans; +} + bool tcp_check_oom(struct sock *sk, int shift) { bool too_many_orphans, out_of_socket_memory; - too_many_orphans = tcp_too_many_orphans(sk, shift); + too_many_orphans = tcp_too_many_orphans(shift); out_of_socket_memory = tcp_out_of_memory(sk); if (too_many_orphans) @@ -2783,7 +2808,7 @@ adjudge_to_death: /* remove backlog if any, without releasing ownership. */ __release_sock(sk); - percpu_counter_inc(sk->sk_prot->orphan_count); + this_cpu_inc(tcp_orphan_count); /* Have we already been destroyed by a softirq or backlog? */ if (state != TCP_CLOSE && sk->sk_state == TCP_CLOSE) @@ -4476,7 +4501,10 @@ void __init tcp_init(void) sizeof_field(struct sk_buff, cb)); percpu_counter_init(&tcp_sockets_allocated, 0, GFP_KERNEL); - percpu_counter_init(&tcp_orphan_count, 0, GFP_KERNEL); + + timer_setup(&tcp_orphan_timer, tcp_orphan_update, TIMER_DEFERRABLE); + mod_timer(&tcp_orphan_timer, jiffies + TCP_ORPHAN_TIMER_PERIOD); + inet_hashinfo_init(&tcp_hashinfo); inet_hashinfo2_init(&tcp_hashinfo, "tcp_listen_portaddr_hash", thash_entries, 21, /* one slot per 2 MB*/ diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 26ca9dc132ae..6ecf921c2112 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -2239,12 +2239,12 @@ static int addrconf_ifid_6lowpan(u8 *eui, struct net_device *dev) static int addrconf_ifid_ieee1394(u8 *eui, struct net_device *dev) { - union fwnet_hwaddr *ha; + const union fwnet_hwaddr *ha; if (dev->addr_len != FWNET_ALEN) return -1; - ha = (union fwnet_hwaddr *)dev->dev_addr; + ha = (const union fwnet_hwaddr *)dev->dev_addr; memcpy(eui, &ha->uc.uniq_id, sizeof(ha->uc.uniq_id)); eui[0] ^= 2; diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 3ad201d372d8..d831d2439693 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1088,7 +1088,7 @@ static void ip6gre_tnl_link_config_common(struct ip6_tnl *t) struct flowi6 *fl6 = &t->fl.u.ip6; if (dev->type != ARPHRD_ETHER) { - memcpy(dev->dev_addr, &p->laddr, sizeof(struct in6_addr)); + __dev_addr_set(dev, &p->laddr, sizeof(struct in6_addr)); memcpy(dev->broadcast, &p->raddr, sizeof(struct in6_addr)); } @@ -1521,7 +1521,7 @@ static int ip6gre_tunnel_init(struct net_device *dev) if (tunnel->parms.collect_md) return 0; - memcpy(dev->dev_addr, &tunnel->parms.laddr, sizeof(struct in6_addr)); + __dev_addr_set(dev, &tunnel->parms.laddr, sizeof(struct in6_addr)); memcpy(dev->broadcast, &tunnel->parms.raddr, sizeof(struct in6_addr)); if (ipv6_addr_any(&tunnel->parms.raddr)) diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 20a67efda47f..484aca492cc0 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1449,7 +1449,7 @@ static void ip6_tnl_link_config(struct ip6_tnl *t) unsigned int mtu; int t_hlen; - memcpy(dev->dev_addr, &p->laddr, sizeof(struct in6_addr)); + __dev_addr_set(dev, &p->laddr, sizeof(struct in6_addr)); memcpy(dev->broadcast, &p->raddr, sizeof(struct in6_addr)); /* Set up flowi template */ diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index 1d8e3ffa225d..527e9ead7449 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -660,7 +660,7 @@ static void vti6_link_config(struct ip6_tnl *t, bool keep_mtu) struct net_device *tdev = NULL; int mtu; - memcpy(dev->dev_addr, &p->laddr, sizeof(struct in6_addr)); + __dev_addr_set(dev, &p->laddr, sizeof(struct in6_addr)); memcpy(dev->broadcast, &p->raddr, sizeof(struct in6_addr)); p->flags &= ~(IP6_TNL_F_CAP_XMIT | IP6_TNL_F_CAP_RCV | diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 4b098521a44c..184190b9ea25 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -142,7 +142,7 @@ struct neigh_table nd_tbl = { }; EXPORT_SYMBOL_GPL(nd_tbl); -void __ndisc_fill_addr_option(struct sk_buff *skb, int type, void *data, +void __ndisc_fill_addr_option(struct sk_buff *skb, int type, const void *data, int data_len, int pad) { int space = __ndisc_opt_addr_space(data_len, pad); @@ -165,7 +165,7 @@ void __ndisc_fill_addr_option(struct sk_buff *skb, int type, void *data, EXPORT_SYMBOL_GPL(__ndisc_fill_addr_option); static inline void ndisc_fill_addr_option(struct sk_buff *skb, int type, - void *data, u8 icmp6_type) + const void *data, u8 icmp6_type) { __ndisc_fill_addr_option(skb, type, data, skb->dev->addr_len, ndisc_addr_option_pad(skb->dev->type)); diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index a579ea14a69b..2d816277f2c5 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -247,10 +247,10 @@ ip6t_next_entry(const struct ip6t_entry *entry) /* Returns one of the generic firewall policies, like NF_ACCEPT. */ unsigned int -ip6t_do_table(struct sk_buff *skb, - const struct nf_hook_state *state, - struct xt_table *table) +ip6t_do_table(void *priv, struct sk_buff *skb, + const struct nf_hook_state *state) { + const struct xt_table *table = priv; unsigned int hook = state->hook; static const char nulldevname[IFNAMSIZ] __attribute__((aligned(sizeof(long)))); /* Initializing verdict to NF_DROP keeps gcc happy. */ diff --git a/net/ipv6/netfilter/ip6table_filter.c b/net/ipv6/netfilter/ip6table_filter.c index 727ee8097012..df785ebda0ca 100644 --- a/net/ipv6/netfilter/ip6table_filter.c +++ b/net/ipv6/netfilter/ip6table_filter.c @@ -27,14 +27,6 @@ static const struct xt_table packet_filter = { .priority = NF_IP6_PRI_FILTER, }; -/* The work comes in here from netfilter.c. */ -static unsigned int -ip6table_filter_hook(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state) -{ - return ip6t_do_table(skb, state, priv); -} - static struct nf_hook_ops *filter_ops __read_mostly; /* Default to forward because I got too much mail already. */ @@ -90,7 +82,7 @@ static int __init ip6table_filter_init(void) if (ret < 0) return ret; - filter_ops = xt_hook_ops_alloc(&packet_filter, ip6table_filter_hook); + filter_ops = xt_hook_ops_alloc(&packet_filter, ip6t_do_table); if (IS_ERR(filter_ops)) { xt_unregister_template(&packet_filter); return PTR_ERR(filter_ops); diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c index 9b518ce37d6a..a88b2ce4a3cb 100644 --- a/net/ipv6/netfilter/ip6table_mangle.c +++ b/net/ipv6/netfilter/ip6table_mangle.c @@ -29,7 +29,7 @@ static const struct xt_table packet_mangler = { }; static unsigned int -ip6t_mangle_out(struct sk_buff *skb, const struct nf_hook_state *state, void *priv) +ip6t_mangle_out(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { unsigned int ret; struct in6_addr saddr, daddr; @@ -46,7 +46,7 @@ ip6t_mangle_out(struct sk_buff *skb, const struct nf_hook_state *state, void *pr /* flowlabel and prio (includes version, which shouldn't change either */ flowlabel = *((u_int32_t *)ipv6_hdr(skb)); - ret = ip6t_do_table(skb, state, priv); + ret = ip6t_do_table(priv, skb, state); if (ret != NF_DROP && ret != NF_STOLEN && (!ipv6_addr_equal(&ipv6_hdr(skb)->saddr, &saddr) || @@ -68,8 +68,8 @@ ip6table_mangle_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { if (state->hook == NF_INET_LOCAL_OUT) - return ip6t_mangle_out(skb, state, priv); - return ip6t_do_table(skb, state, priv); + return ip6t_mangle_out(priv, skb, state); + return ip6t_do_table(priv, skb, state); } static struct nf_hook_ops *mangle_ops __read_mostly; diff --git a/net/ipv6/netfilter/ip6table_nat.c b/net/ipv6/netfilter/ip6table_nat.c index 921c1723a01e..bf3cb3a13600 100644 --- a/net/ipv6/netfilter/ip6table_nat.c +++ b/net/ipv6/netfilter/ip6table_nat.c @@ -31,34 +31,27 @@ static const struct xt_table nf_nat_ipv6_table = { .af = NFPROTO_IPV6, }; -static unsigned int ip6table_nat_do_chain(void *priv, - struct sk_buff *skb, - const struct nf_hook_state *state) -{ - return ip6t_do_table(skb, state, priv); -} - static const struct nf_hook_ops nf_nat_ipv6_ops[] = { { - .hook = ip6table_nat_do_chain, + .hook = ip6t_do_table, .pf = NFPROTO_IPV6, .hooknum = NF_INET_PRE_ROUTING, .priority = NF_IP6_PRI_NAT_DST, }, { - .hook = ip6table_nat_do_chain, + .hook = ip6t_do_table, .pf = NFPROTO_IPV6, .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP6_PRI_NAT_SRC, }, { - .hook = ip6table_nat_do_chain, + .hook = ip6t_do_table, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP6_PRI_NAT_DST, }, { - .hook = ip6table_nat_do_chain, + .hook = ip6t_do_table, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP6_PRI_NAT_SRC, diff --git a/net/ipv6/netfilter/ip6table_raw.c b/net/ipv6/netfilter/ip6table_raw.c index 4f2a04af71d3..08861d5d1f4d 100644 --- a/net/ipv6/netfilter/ip6table_raw.c +++ b/net/ipv6/netfilter/ip6table_raw.c @@ -31,14 +31,6 @@ static const struct xt_table packet_raw_before_defrag = { .priority = NF_IP6_PRI_RAW_BEFORE_DEFRAG, }; -/* The work comes in here from netfilter.c. */ -static unsigned int -ip6table_raw_hook(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state) -{ - return ip6t_do_table(skb, state, priv); -} - static struct nf_hook_ops *rawtable_ops __read_mostly; static int ip6table_raw_table_init(struct net *net) @@ -88,7 +80,7 @@ static int __init ip6table_raw_init(void) return ret; /* Register hooks */ - rawtable_ops = xt_hook_ops_alloc(table, ip6table_raw_hook); + rawtable_ops = xt_hook_ops_alloc(table, ip6t_do_table); if (IS_ERR(rawtable_ops)) { xt_unregister_template(table); return PTR_ERR(rawtable_ops); diff --git a/net/ipv6/netfilter/ip6table_security.c b/net/ipv6/netfilter/ip6table_security.c index 931674034d8b..4df14a9bae78 100644 --- a/net/ipv6/netfilter/ip6table_security.c +++ b/net/ipv6/netfilter/ip6table_security.c @@ -32,13 +32,6 @@ static const struct xt_table security_table = { .priority = NF_IP6_PRI_SECURITY, }; -static unsigned int -ip6table_security_hook(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state) -{ - return ip6t_do_table(skb, state, priv); -} - static struct nf_hook_ops *sectbl_ops __read_mostly; static int ip6table_security_table_init(struct net *net) @@ -77,7 +70,7 @@ static int __init ip6table_security_init(void) if (ret < 0) return ret; - sectbl_ops = xt_hook_ops_alloc(&security_table, ip6table_security_hook); + sectbl_ops = xt_hook_ops_alloc(&security_table, ip6t_do_table); if (IS_ERR(sectbl_ops)) { xt_unregister_template(&security_table); return PTR_ERR(sectbl_ops); diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index ef0c7a7c18e2..1b57ee36d668 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -204,7 +204,7 @@ static int ipip6_tunnel_create(struct net_device *dev) struct sit_net *sitn = net_generic(net, sit_net_id); int err; - memcpy(dev->dev_addr, &t->parms.iph.saddr, 4); + __dev_addr_set(dev, &t->parms.iph.saddr, 4); memcpy(dev->broadcast, &t->parms.iph.daddr, 4); if ((__force u16)t->parms.i_flags & SIT_ISATAP) @@ -1149,7 +1149,7 @@ static void ipip6_tunnel_update(struct ip_tunnel *t, struct ip_tunnel_parm *p, synchronize_net(); t->parms.iph.saddr = p->iph.saddr; t->parms.iph.daddr = p->iph.daddr; - memcpy(t->dev->dev_addr, &p->iph.saddr, 4); + __dev_addr_set(t->dev, &p->iph.saddr, 4); memcpy(t->dev->broadcast, &p->iph.daddr, 4); ipip6_tunnel_link(sitn, t); t->parms.iph.ttl = p->iph.ttl; diff --git a/net/llc/llc_c_ac.c b/net/llc/llc_c_ac.c index 647c0554d04c..40ca3c1e42a2 100644 --- a/net/llc/llc_c_ac.c +++ b/net/llc/llc_c_ac.c @@ -781,7 +781,7 @@ int llc_conn_ac_send_sabme_cmd_p_set_x(struct sock *sk, struct sk_buff *skb) if (nskb) { struct llc_sap *sap = llc->sap; - u8 *dmac = llc->daddr.mac; + const u8 *dmac = llc->daddr.mac; if (llc->dev->flags & IFF_LOOPBACK) dmac = llc->dev->dev_addr; diff --git a/net/llc/llc_if.c b/net/llc/llc_if.c index ad6547736c21..dde9bf08a593 100644 --- a/net/llc/llc_if.c +++ b/net/llc/llc_if.c @@ -80,7 +80,7 @@ out_free: * establishment will inform to upper layer via calling it's confirm * function and passing proper information. */ -int llc_establish_connection(struct sock *sk, u8 *lmac, u8 *dmac, u8 dsap) +int llc_establish_connection(struct sock *sk, const u8 *lmac, u8 *dmac, u8 dsap) { int rc = -EISCONN; struct llc_addr laddr, daddr; diff --git a/net/llc/llc_output.c b/net/llc/llc_output.c index b9ad087bcbd7..5a6466fc626a 100644 --- a/net/llc/llc_output.c +++ b/net/llc/llc_output.c @@ -56,7 +56,7 @@ int llc_mac_hdr_init(struct sk_buff *skb, * package primitive as an event and send to SAP event handler */ int llc_build_and_send_ui_pkt(struct llc_sap *sap, struct sk_buff *skb, - unsigned char *dmac, unsigned char dsap) + const unsigned char *dmac, unsigned char dsap) { int rc; llc_pdu_header_init(skb, LLC_PDU_TYPE_U, sap->laddr.lsap, diff --git a/net/llc/llc_proc.c b/net/llc/llc_proc.c index a4eccb98220a..0ff490a73fae 100644 --- a/net/llc/llc_proc.c +++ b/net/llc/llc_proc.c @@ -26,7 +26,7 @@ #include #include -static void llc_ui_format_mac(struct seq_file *seq, u8 *addr) +static void llc_ui_format_mac(struct seq_file *seq, const u8 *addr) { seq_printf(seq, "%pM", addr); } diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c index cce28e3b2232..470ff0ce3dc7 100644 --- a/net/mac80211/agg-rx.c +++ b/net/mac80211/agg-rx.c @@ -477,7 +477,7 @@ void ieee80211_process_addba_request(struct ieee80211_local *local, size_t len) { u16 capab, tid, timeout, ba_policy, buf_size, start_seq_num; - struct ieee802_11_elems elems = { }; + struct ieee802_11_elems *elems = NULL; u8 dialog_token; int ies_len; @@ -495,16 +495,18 @@ void ieee80211_process_addba_request(struct ieee80211_local *local, ies_len = len - offsetof(struct ieee80211_mgmt, u.action.u.addba_req.variable); if (ies_len) { - ieee802_11_parse_elems(mgmt->u.action.u.addba_req.variable, - ies_len, true, &elems, mgmt->bssid, NULL); - if (elems.parse_error) - return; + elems = ieee802_11_parse_elems(mgmt->u.action.u.addba_req.variable, + ies_len, true, mgmt->bssid, NULL); + if (!elems || elems->parse_error) + goto free; } __ieee80211_start_rx_ba_session(sta, dialog_token, timeout, start_seq_num, ba_policy, tid, buf_size, true, false, - elems.addba_ext_ie); + elems ? elems->addba_ext_ie : NULL); +free: + kfree(elems); } void ieee80211_manage_rx_ba_offl(struct ieee80211_vif *vif, diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index d69b31c20fe2..e2b791c37591 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -111,6 +111,36 @@ static int ieee80211_set_mon_options(struct ieee80211_sub_if_data *sdata, return 0; } +static int ieee80211_set_ap_mbssid_options(struct ieee80211_sub_if_data *sdata, + struct cfg80211_mbssid_config params) +{ + struct ieee80211_sub_if_data *tx_sdata; + + sdata->vif.mbssid_tx_vif = NULL; + sdata->vif.bss_conf.bssid_index = 0; + sdata->vif.bss_conf.nontransmitted = false; + sdata->vif.bss_conf.ema_ap = false; + + if (sdata->vif.type != NL80211_IFTYPE_AP || !params.tx_wdev) + return -EINVAL; + + tx_sdata = IEEE80211_WDEV_TO_SUB_IF(params.tx_wdev); + if (!tx_sdata) + return -EINVAL; + + if (tx_sdata == sdata) { + sdata->vif.mbssid_tx_vif = &sdata->vif; + } else { + sdata->vif.mbssid_tx_vif = &tx_sdata->vif; + sdata->vif.bss_conf.nontransmitted = true; + sdata->vif.bss_conf.bssid_index = params.index; + } + if (params.ema) + sdata->vif.bss_conf.ema_ap = true; + + return 0; +} + static struct wireless_dev *ieee80211_add_iface(struct wiphy *wiphy, const char *name, unsigned char name_assign_type, @@ -1105,6 +1135,14 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, changed |= BSS_CHANGED_HE_BSS_COLOR; } + if (sdata->vif.type == NL80211_IFTYPE_AP && + params->mbssid_config.tx_wdev) { + err = ieee80211_set_ap_mbssid_options(sdata, + params->mbssid_config); + if (err) + return err; + } + mutex_lock(&local->mtx); err = ieee80211_vif_use_channel(sdata, ¶ms->chandef, IEEE80211_CHANCTX_SHARED); diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c index 8be28cfd6f64..481f01b0f65c 100644 --- a/net/mac80211/debugfs_sta.c +++ b/net/mac80211/debugfs_sta.c @@ -5,7 +5,7 @@ * Copyright 2007 Johannes Berg * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright(c) 2016 Intel Deutschland GmbH - * Copyright (C) 2018 - 2020 Intel Corporation + * Copyright (C) 2018 - 2021 Intel Corporation */ #include @@ -153,20 +153,20 @@ static ssize_t sta_aqm_read(struct file *file, char __user *userbuf, rcu_read_lock(); p += scnprintf(p, - bufsz+buf-p, + bufsz + buf - p, "target %uus interval %uus ecn %s\n", codel_time_to_us(sta->cparams.target), codel_time_to_us(sta->cparams.interval), sta->cparams.ecn ? "yes" : "no"); p += scnprintf(p, - bufsz+buf-p, + bufsz + buf - p, "tid ac backlog-bytes backlog-packets new-flows drops marks overlimit collisions tx-bytes tx-packets flags\n"); for (i = 0; i < ARRAY_SIZE(sta->sta.txq); i++) { if (!sta->sta.txq[i]) continue; txqi = to_txq_info(sta->sta.txq[i]); - p += scnprintf(p, bufsz+buf-p, + p += scnprintf(p, bufsz + buf - p, "%d %d %u %u %u %u %u %u %u %u %u 0x%lx(%s%s%s)\n", txqi->txq.tid, txqi->txq.ac, @@ -314,17 +314,24 @@ STA_OPS_RW(aql); static ssize_t sta_agg_status_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) { - char buf[71 + IEEE80211_NUM_TIDS * 40], *p = buf; + char *buf, *p; + ssize_t bufsz = 71 + IEEE80211_NUM_TIDS * 40; int i; struct sta_info *sta = file->private_data; struct tid_ampdu_rx *tid_rx; struct tid_ampdu_tx *tid_tx; + ssize_t ret; + + buf = kzalloc(bufsz, GFP_KERNEL); + if (!buf) + return -ENOMEM; + p = buf; rcu_read_lock(); - p += scnprintf(p, sizeof(buf) + buf - p, "next dialog_token: %#02x\n", + p += scnprintf(p, bufsz + buf - p, "next dialog_token: %#02x\n", sta->ampdu_mlme.dialog_token_allocator + 1); - p += scnprintf(p, sizeof(buf) + buf - p, + p += scnprintf(p, bufsz + buf - p, "TID\t\tRX\tDTKN\tSSN\t\tTX\tDTKN\tpending\n"); for (i = 0; i < IEEE80211_NUM_TIDS; i++) { @@ -334,25 +341,27 @@ static ssize_t sta_agg_status_read(struct file *file, char __user *userbuf, tid_tx = rcu_dereference(sta->ampdu_mlme.tid_tx[i]); tid_rx_valid = test_bit(i, sta->ampdu_mlme.agg_session_valid); - p += scnprintf(p, sizeof(buf) + buf - p, "%02d", i); - p += scnprintf(p, sizeof(buf) + buf - p, "\t\t%x", + p += scnprintf(p, bufsz + buf - p, "%02d", i); + p += scnprintf(p, bufsz + buf - p, "\t\t%x", tid_rx_valid); - p += scnprintf(p, sizeof(buf) + buf - p, "\t%#.2x", + p += scnprintf(p, bufsz + buf - p, "\t%#.2x", tid_rx_valid ? sta->ampdu_mlme.tid_rx_token[i] : 0); - p += scnprintf(p, sizeof(buf) + buf - p, "\t%#.3x", + p += scnprintf(p, bufsz + buf - p, "\t%#.3x", tid_rx ? tid_rx->ssn : 0); - p += scnprintf(p, sizeof(buf) + buf - p, "\t\t%x", !!tid_tx); - p += scnprintf(p, sizeof(buf) + buf - p, "\t%#.2x", + p += scnprintf(p, bufsz + buf - p, "\t\t%x", !!tid_tx); + p += scnprintf(p, bufsz + buf - p, "\t%#.2x", tid_tx ? tid_tx->dialog_token : 0); - p += scnprintf(p, sizeof(buf) + buf - p, "\t%03d", + p += scnprintf(p, bufsz + buf - p, "\t%03d", tid_tx ? skb_queue_len(&tid_tx->pending) : 0); - p += scnprintf(p, sizeof(buf) + buf - p, "\n"); + p += scnprintf(p, bufsz + buf - p, "\n"); } rcu_read_unlock(); - return simple_read_from_buffer(userbuf, count, ppos, buf, p - buf); + ret = simple_read_from_buffer(userbuf, count, ppos, buf, p - buf); + kfree(buf); + return ret; } static ssize_t sta_agg_status_write(struct file *file, const char __user *userbuf, @@ -434,15 +443,22 @@ static ssize_t sta_ht_capa_read(struct file *file, char __user *userbuf, if (_cond) \ p += scnprintf(p, sizeof(buf)+buf-p, "\t" _str "\n"); \ } while (0) - char buf[512], *p = buf; + char *buf, *p; int i; + ssize_t bufsz = 512; struct sta_info *sta = file->private_data; struct ieee80211_sta_ht_cap *htc = &sta->sta.ht_cap; + ssize_t ret; - p += scnprintf(p, sizeof(buf) + buf - p, "ht %ssupported\n", + buf = kzalloc(bufsz, GFP_KERNEL); + if (!buf) + return -ENOMEM; + p = buf; + + p += scnprintf(p, bufsz + buf - p, "ht %ssupported\n", htc->ht_supported ? "" : "not "); if (htc->ht_supported) { - p += scnprintf(p, sizeof(buf)+buf-p, "cap: %#.4x\n", htc->cap); + p += scnprintf(p, bufsz + buf - p, "cap: %#.4x\n", htc->cap); PRINT_HT_CAP((htc->cap & BIT(0)), "RX LDPC"); PRINT_HT_CAP((htc->cap & BIT(1)), "HT20/HT40"); @@ -484,81 +500,90 @@ static ssize_t sta_ht_capa_read(struct file *file, char __user *userbuf, PRINT_HT_CAP((htc->cap & BIT(15)), "L-SIG TXOP protection"); - p += scnprintf(p, sizeof(buf)+buf-p, "ampdu factor/density: %d/%d\n", + p += scnprintf(p, bufsz + buf - p, "ampdu factor/density: %d/%d\n", htc->ampdu_factor, htc->ampdu_density); - p += scnprintf(p, sizeof(buf)+buf-p, "MCS mask:"); + p += scnprintf(p, bufsz + buf - p, "MCS mask:"); for (i = 0; i < IEEE80211_HT_MCS_MASK_LEN; i++) - p += scnprintf(p, sizeof(buf)+buf-p, " %.2x", + p += scnprintf(p, bufsz + buf - p, " %.2x", htc->mcs.rx_mask[i]); - p += scnprintf(p, sizeof(buf)+buf-p, "\n"); + p += scnprintf(p, bufsz + buf - p, "\n"); /* If not set this is meaningless */ if (le16_to_cpu(htc->mcs.rx_highest)) { - p += scnprintf(p, sizeof(buf)+buf-p, + p += scnprintf(p, bufsz + buf - p, "MCS rx highest: %d Mbps\n", le16_to_cpu(htc->mcs.rx_highest)); } - p += scnprintf(p, sizeof(buf)+buf-p, "MCS tx params: %x\n", + p += scnprintf(p, bufsz + buf - p, "MCS tx params: %x\n", htc->mcs.tx_params); } - return simple_read_from_buffer(userbuf, count, ppos, buf, p - buf); + ret = simple_read_from_buffer(userbuf, count, ppos, buf, p - buf); + kfree(buf); + return ret; } STA_OPS(ht_capa); static ssize_t sta_vht_capa_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) { - char buf[512], *p = buf; + char *buf, *p; struct sta_info *sta = file->private_data; struct ieee80211_sta_vht_cap *vhtc = &sta->sta.vht_cap; + ssize_t ret; + ssize_t bufsz = 512; - p += scnprintf(p, sizeof(buf) + buf - p, "VHT %ssupported\n", + buf = kzalloc(bufsz, GFP_KERNEL); + if (!buf) + return -ENOMEM; + p = buf; + + p += scnprintf(p, bufsz + buf - p, "VHT %ssupported\n", vhtc->vht_supported ? "" : "not "); if (vhtc->vht_supported) { - p += scnprintf(p, sizeof(buf) + buf - p, "cap: %#.8x\n", + p += scnprintf(p, bufsz + buf - p, "cap: %#.8x\n", vhtc->cap); #define PFLAG(a, b) \ do { \ if (vhtc->cap & IEEE80211_VHT_CAP_ ## a) \ - p += scnprintf(p, sizeof(buf) + buf - p, \ + p += scnprintf(p, bufsz + buf - p, \ "\t\t%s\n", b); \ } while (0) switch (vhtc->cap & 0x3) { case IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_3895: - p += scnprintf(p, sizeof(buf) + buf - p, + p += scnprintf(p, bufsz + buf - p, "\t\tMAX-MPDU-3895\n"); break; case IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_7991: - p += scnprintf(p, sizeof(buf) + buf - p, + p += scnprintf(p, bufsz + buf - p, "\t\tMAX-MPDU-7991\n"); break; case IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_11454: - p += scnprintf(p, sizeof(buf) + buf - p, + p += scnprintf(p, bufsz + buf - p, "\t\tMAX-MPDU-11454\n"); break; default: - p += scnprintf(p, sizeof(buf) + buf - p, + p += scnprintf(p, bufsz + buf - p, "\t\tMAX-MPDU-UNKNOWN\n"); } switch (vhtc->cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK) { case 0: - p += scnprintf(p, sizeof(buf) + buf - p, + p += scnprintf(p, bufsz + buf - p, "\t\t80Mhz\n"); break; case IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ: - p += scnprintf(p, sizeof(buf) + buf - p, + p += scnprintf(p, bufsz + buf - p, "\t\t160Mhz\n"); break; case IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ: - p += scnprintf(p, sizeof(buf) + buf - p, + p += scnprintf(p, bufsz + buf - p, "\t\t80+80Mhz\n"); break; default: - p += scnprintf(p, sizeof(buf) + buf - p, + p += scnprintf(p, bufsz + buf - p, "\t\tUNKNOWN-MHZ: 0x%x\n", (vhtc->cap >> 2) & 0x3); } @@ -566,15 +591,15 @@ static ssize_t sta_vht_capa_read(struct file *file, char __user *userbuf, PFLAG(SHORT_GI_80, "SHORT-GI-80"); PFLAG(SHORT_GI_160, "SHORT-GI-160"); PFLAG(TXSTBC, "TXSTBC"); - p += scnprintf(p, sizeof(buf) + buf - p, + p += scnprintf(p, bufsz + buf - p, "\t\tRXSTBC_%d\n", (vhtc->cap >> 8) & 0x7); PFLAG(SU_BEAMFORMER_CAPABLE, "SU-BEAMFORMER-CAPABLE"); PFLAG(SU_BEAMFORMEE_CAPABLE, "SU-BEAMFORMEE-CAPABLE"); - p += scnprintf(p, sizeof(buf) + buf - p, + p += scnprintf(p, bufsz + buf - p, "\t\tBEAMFORMEE-STS: 0x%x\n", (vhtc->cap & IEEE80211_VHT_CAP_BEAMFORMEE_STS_MASK) >> IEEE80211_VHT_CAP_BEAMFORMEE_STS_SHIFT); - p += scnprintf(p, sizeof(buf) + buf - p, + p += scnprintf(p, bufsz + buf - p, "\t\tSOUNDING-DIMENSIONS: 0x%x\n", (vhtc->cap & IEEE80211_VHT_CAP_SOUNDING_DIMENSIONS_MASK) >> IEEE80211_VHT_CAP_SOUNDING_DIMENSIONS_SHIFT); @@ -582,34 +607,36 @@ static ssize_t sta_vht_capa_read(struct file *file, char __user *userbuf, PFLAG(MU_BEAMFORMEE_CAPABLE, "MU-BEAMFORMEE-CAPABLE"); PFLAG(VHT_TXOP_PS, "TXOP-PS"); PFLAG(HTC_VHT, "HTC-VHT"); - p += scnprintf(p, sizeof(buf) + buf - p, + p += scnprintf(p, bufsz + buf - p, "\t\tMPDU-LENGTH-EXPONENT: 0x%x\n", (vhtc->cap & IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_MASK) >> IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_SHIFT); PFLAG(VHT_LINK_ADAPTATION_VHT_UNSOL_MFB, "LINK-ADAPTATION-VHT-UNSOL-MFB"); - p += scnprintf(p, sizeof(buf) + buf - p, + p += scnprintf(p, bufsz + buf - p, "\t\tLINK-ADAPTATION-VHT-MRQ-MFB: 0x%x\n", (vhtc->cap & IEEE80211_VHT_CAP_VHT_LINK_ADAPTATION_VHT_MRQ_MFB) >> 26); PFLAG(RX_ANTENNA_PATTERN, "RX-ANTENNA-PATTERN"); PFLAG(TX_ANTENNA_PATTERN, "TX-ANTENNA-PATTERN"); - p += scnprintf(p, sizeof(buf)+buf-p, "RX MCS: %.4x\n", + p += scnprintf(p, bufsz + buf - p, "RX MCS: %.4x\n", le16_to_cpu(vhtc->vht_mcs.rx_mcs_map)); if (vhtc->vht_mcs.rx_highest) - p += scnprintf(p, sizeof(buf)+buf-p, + p += scnprintf(p, bufsz + buf - p, "MCS RX highest: %d Mbps\n", le16_to_cpu(vhtc->vht_mcs.rx_highest)); - p += scnprintf(p, sizeof(buf)+buf-p, "TX MCS: %.4x\n", + p += scnprintf(p, bufsz + buf - p, "TX MCS: %.4x\n", le16_to_cpu(vhtc->vht_mcs.tx_mcs_map)); if (vhtc->vht_mcs.tx_highest) - p += scnprintf(p, sizeof(buf)+buf-p, + p += scnprintf(p, bufsz + buf - p, "MCS TX highest: %d Mbps\n", le16_to_cpu(vhtc->vht_mcs.tx_highest)); #undef PFLAG } - return simple_read_from_buffer(userbuf, count, ppos, buf, p - buf); + ret = simple_read_from_buffer(userbuf, count, ppos, buf, p - buf); + kfree(buf); + return ret; } STA_OPS(vht_capa); diff --git a/net/mac80211/fils_aead.c b/net/mac80211/fils_aead.c index a13ae148937e..e1d4cfd99128 100644 --- a/net/mac80211/fils_aead.c +++ b/net/mac80211/fils_aead.c @@ -219,7 +219,8 @@ int fils_encrypt_assoc_req(struct sk_buff *skb, { struct ieee80211_mgmt *mgmt = (void *)skb->data; u8 *capab, *ies, *encr; - const u8 *addr[5 + 1], *session; + const u8 *addr[5 + 1]; + const struct element *session; size_t len[5 + 1]; size_t crypt_len; @@ -231,12 +232,12 @@ int fils_encrypt_assoc_req(struct sk_buff *skb, ies = mgmt->u.assoc_req.variable; } - session = cfg80211_find_ext_ie(WLAN_EID_EXT_FILS_SESSION, - ies, skb->data + skb->len - ies); - if (!session || session[1] != 1 + 8) + session = cfg80211_find_ext_elem(WLAN_EID_EXT_FILS_SESSION, + ies, skb->data + skb->len - ies); + if (!session || session->datalen != 1 + 8) return -EINVAL; /* encrypt after FILS Session element */ - encr = (u8 *)session + 2 + 1 + 8; + encr = (u8 *)session->data + 1 + 8; /* AES-SIV AAD vectors */ @@ -270,7 +271,8 @@ int fils_decrypt_assoc_resp(struct ieee80211_sub_if_data *sdata, { struct ieee80211_mgmt *mgmt = (void *)frame; u8 *capab, *ies, *encr; - const u8 *addr[5 + 1], *session; + const u8 *addr[5 + 1]; + const struct element *session; size_t len[5 + 1]; int res; size_t crypt_len; @@ -280,16 +282,16 @@ int fils_decrypt_assoc_resp(struct ieee80211_sub_if_data *sdata, capab = (u8 *)&mgmt->u.assoc_resp.capab_info; ies = mgmt->u.assoc_resp.variable; - session = cfg80211_find_ext_ie(WLAN_EID_EXT_FILS_SESSION, - ies, frame + *frame_len - ies); - if (!session || session[1] != 1 + 8) { + session = cfg80211_find_ext_elem(WLAN_EID_EXT_FILS_SESSION, + ies, frame + *frame_len - ies); + if (!session || session->datalen != 1 + 8) { mlme_dbg(sdata, "No (valid) FILS Session element in (Re)Association Response frame from %pM", mgmt->sa); return -EINVAL; } /* decrypt after FILS Session element */ - encr = (u8 *)session + 2 + 1 + 8; + encr = (u8 *)session->data + 1 + 8; /* AES-SIV AAD vectors */ diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c index 5d6ca4c3e698..0416c4d22292 100644 --- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -9,7 +9,7 @@ * Copyright 2009, Johannes Berg * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright(c) 2016 Intel Deutschland GmbH - * Copyright(c) 2018-2020 Intel Corporation + * Copyright(c) 2018-2021 Intel Corporation */ #include @@ -1589,7 +1589,7 @@ void ieee80211_rx_mgmt_probe_beacon(struct ieee80211_sub_if_data *sdata, struct ieee80211_rx_status *rx_status) { size_t baselen; - struct ieee802_11_elems elems; + struct ieee802_11_elems *elems; BUILD_BUG_ON(offsetof(typeof(mgmt->u.probe_resp), variable) != offsetof(typeof(mgmt->u.beacon), variable)); @@ -1602,10 +1602,14 @@ void ieee80211_rx_mgmt_probe_beacon(struct ieee80211_sub_if_data *sdata, if (baselen > len) return; - ieee802_11_parse_elems(mgmt->u.probe_resp.variable, len - baselen, - false, &elems, mgmt->bssid, NULL); + elems = ieee802_11_parse_elems(mgmt->u.probe_resp.variable, + len - baselen, false, + mgmt->bssid, NULL); - ieee80211_rx_bss_info(sdata, mgmt, len, rx_status, &elems); + if (elems) { + ieee80211_rx_bss_info(sdata, mgmt, len, rx_status, elems); + kfree(elems); + } } void ieee80211_ibss_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata, @@ -1614,7 +1618,7 @@ void ieee80211_ibss_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata, struct ieee80211_rx_status *rx_status; struct ieee80211_mgmt *mgmt; u16 fc; - struct ieee802_11_elems elems; + struct ieee802_11_elems *elems; int ies_len; rx_status = IEEE80211_SKB_RXCB(skb); @@ -1651,15 +1655,16 @@ void ieee80211_ibss_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata, if (ies_len < 0) break; - ieee802_11_parse_elems( + elems = ieee802_11_parse_elems( mgmt->u.action.u.chan_switch.variable, - ies_len, true, &elems, mgmt->bssid, NULL); + ies_len, true, mgmt->bssid, NULL); - if (elems.parse_error) - break; - - ieee80211_rx_mgmt_spectrum_mgmt(sdata, mgmt, skb->len, - rx_status, &elems); + if (elems && !elems->parse_error) + ieee80211_rx_mgmt_spectrum_mgmt(sdata, mgmt, + skb->len, + rx_status, + elems); + kfree(elems); break; } } diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 159af6c3ffb0..5666bbb8860b 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -631,10 +631,9 @@ struct ieee80211_if_ocb { */ struct ieee802_11_elems; struct ieee80211_mesh_sync_ops { - void (*rx_bcn_presp)(struct ieee80211_sub_if_data *sdata, - u16 stype, - struct ieee80211_mgmt *mgmt, - struct ieee802_11_elems *elems, + void (*rx_bcn_presp)(struct ieee80211_sub_if_data *sdata, u16 stype, + struct ieee80211_mgmt *mgmt, unsigned int len, + const struct ieee80211_meshconf_ie *mesh_cfg, struct ieee80211_rx_status *rx_status); /* should be called with beacon_data under RCU read lock */ @@ -1242,6 +1241,9 @@ struct ieee80211_local { */ bool suspended; + /* suspending is true during the whole suspend process */ + bool suspending; + /* * Resuming is true while suspended, but when we're reprogramming the * hardware -- at that time it's allowed to use ieee80211_queue_work() @@ -1508,6 +1510,7 @@ struct ieee80211_csa_ie { struct ieee802_11_elems { const u8 *ie_start; size_t total_len; + u32 crc; /* pointers to IEs */ const struct ieee80211_tdls_lnkie *lnk_id; @@ -1517,7 +1520,6 @@ struct ieee802_11_elems { const u8 *supp_rates; const u8 *ds_params; const struct ieee80211_tim_ie *tim; - const u8 *challenge; const u8 *rsn; const u8 *rsnx; const u8 *erp_info; @@ -1571,7 +1573,6 @@ struct ieee802_11_elems { u8 ssid_len; u8 supp_rates_len; u8 tim_len; - u8 challenge_len; u8 rsn_len; u8 rsnx_len; u8 ext_supp_rates_len; @@ -2194,18 +2195,18 @@ static inline void ieee80211_tx_skb(struct ieee80211_sub_if_data *sdata, ieee80211_tx_skb_tid(sdata, skb, 7); } -u32 ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action, - struct ieee802_11_elems *elems, - u64 filter, u32 crc, u8 *transmitter_bssid, - u8 *bss_bssid); -static inline void ieee802_11_parse_elems(const u8 *start, size_t len, - bool action, - struct ieee802_11_elems *elems, - u8 *transmitter_bssid, - u8 *bss_bssid) +struct ieee802_11_elems *ieee802_11_parse_elems_crc(const u8 *start, size_t len, + bool action, + u64 filter, u32 crc, + const u8 *transmitter_bssid, + const u8 *bss_bssid); +static inline struct ieee802_11_elems * +ieee802_11_parse_elems(const u8 *start, size_t len, bool action, + const u8 *transmitter_bssid, + const u8 *bss_bssid) { - ieee802_11_parse_elems_crc(start, len, action, elems, 0, 0, - transmitter_bssid, bss_bssid); + return ieee802_11_parse_elems_crc(start, len, action, 0, 0, + transmitter_bssid, bss_bssid); } diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 62c95597704b..9a2145c8192b 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -632,17 +632,46 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, bool going_do ieee80211_add_virtual_monitor(local); } +static void ieee80211_stop_mbssid(struct ieee80211_sub_if_data *sdata) +{ + struct ieee80211_sub_if_data *tx_sdata, *non_tx_sdata, *tmp_sdata; + struct ieee80211_vif *tx_vif = sdata->vif.mbssid_tx_vif; + + if (!tx_vif) + return; + + tx_sdata = vif_to_sdata(tx_vif); + sdata->vif.mbssid_tx_vif = NULL; + + list_for_each_entry_safe(non_tx_sdata, tmp_sdata, + &tx_sdata->local->interfaces, list) { + if (non_tx_sdata != sdata && non_tx_sdata != tx_sdata && + non_tx_sdata->vif.mbssid_tx_vif == tx_vif && + ieee80211_sdata_running(non_tx_sdata)) { + non_tx_sdata->vif.mbssid_tx_vif = NULL; + dev_close(non_tx_sdata->wdev.netdev); + } + } + + if (sdata != tx_sdata && ieee80211_sdata_running(tx_sdata)) { + tx_sdata->vif.mbssid_tx_vif = NULL; + dev_close(tx_sdata->wdev.netdev); + } +} + static int ieee80211_stop(struct net_device *dev) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); - /* close all dependent VLAN interfaces before locking wiphy */ + /* close dependent VLAN and MBSSID interfaces before locking wiphy */ if (sdata->vif.type == NL80211_IFTYPE_AP) { struct ieee80211_sub_if_data *vlan, *tmpsdata; list_for_each_entry_safe(vlan, tmpsdata, &sdata->u.ap.vlans, u.vlan.list) dev_close(vlan->dev); + + ieee80211_stop_mbssid(sdata); } wiphy_lock(sdata->local->hw.wiphy); @@ -1108,9 +1137,7 @@ int ieee80211_do_open(struct wireless_dev *wdev, bool coming_up) * this interface, if it has the special null one. */ if (dev && is_zero_ether_addr(dev->dev_addr)) { - memcpy(dev->dev_addr, - local->hw.wiphy->perm_addr, - ETH_ALEN); + eth_hw_addr_set(dev, local->hw.wiphy->perm_addr); memcpy(dev->perm_addr, dev->dev_addr, ETH_ALEN); if (!is_valid_ether_addr(dev->dev_addr)) { @@ -1964,9 +1991,9 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name, ieee80211_assign_perm_addr(local, ndev->perm_addr, type); if (is_valid_ether_addr(params->macaddr)) - memcpy(ndev->dev_addr, params->macaddr, ETH_ALEN); + eth_hw_addr_set(ndev, params->macaddr); else - memcpy(ndev->dev_addr, ndev->perm_addr, ETH_ALEN); + eth_hw_addr_set(ndev, ndev->perm_addr); SET_NETDEV_DEV(ndev, wiphy_dev(local->hw.wiphy)); /* don't use IEEE80211_DEV_TO_SUB_IF -- it checks too much */ diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index 5dcfd53a4ab6..15ac08d111ea 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -1247,7 +1247,7 @@ ieee80211_mesh_rx_probe_req(struct ieee80211_sub_if_data *sdata, struct sk_buff *presp; struct beacon_data *bcn; struct ieee80211_mgmt *hdr; - struct ieee802_11_elems elems; + struct ieee802_11_elems *elems; size_t baselen; u8 *pos; @@ -1256,22 +1256,24 @@ ieee80211_mesh_rx_probe_req(struct ieee80211_sub_if_data *sdata, if (baselen > len) return; - ieee802_11_parse_elems(pos, len - baselen, false, &elems, mgmt->bssid, - NULL); - - if (!elems.mesh_id) + elems = ieee802_11_parse_elems(pos, len - baselen, false, mgmt->bssid, + NULL); + if (!elems) return; + if (!elems->mesh_id) + goto free; + /* 802.11-2012 10.1.4.3.2 */ if ((!ether_addr_equal(mgmt->da, sdata->vif.addr) && !is_broadcast_ether_addr(mgmt->da)) || - elems.ssid_len != 0) - return; + elems->ssid_len != 0) + goto free; - if (elems.mesh_id_len != 0 && - (elems.mesh_id_len != ifmsh->mesh_id_len || - memcmp(elems.mesh_id, ifmsh->mesh_id, ifmsh->mesh_id_len))) - return; + if (elems->mesh_id_len != 0 && + (elems->mesh_id_len != ifmsh->mesh_id_len || + memcmp(elems->mesh_id, ifmsh->mesh_id, ifmsh->mesh_id_len))) + goto free; rcu_read_lock(); bcn = rcu_dereference(ifmsh->beacon); @@ -1295,6 +1297,8 @@ ieee80211_mesh_rx_probe_req(struct ieee80211_sub_if_data *sdata, ieee80211_tx_skb(sdata, presp); out: rcu_read_unlock(); +free: + kfree(elems); } static void ieee80211_mesh_rx_bcn_presp(struct ieee80211_sub_if_data *sdata, @@ -1305,7 +1309,7 @@ static void ieee80211_mesh_rx_bcn_presp(struct ieee80211_sub_if_data *sdata, { struct ieee80211_local *local = sdata->local; struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; - struct ieee802_11_elems elems; + struct ieee802_11_elems *elems; struct ieee80211_channel *channel; size_t baselen; int freq; @@ -1320,42 +1324,47 @@ static void ieee80211_mesh_rx_bcn_presp(struct ieee80211_sub_if_data *sdata, if (baselen > len) return; - ieee802_11_parse_elems(mgmt->u.probe_resp.variable, len - baselen, - false, &elems, mgmt->bssid, NULL); - - /* ignore non-mesh or secure / unsecure mismatch */ - if ((!elems.mesh_id || !elems.mesh_config) || - (elems.rsn && sdata->u.mesh.security == IEEE80211_MESH_SEC_NONE) || - (!elems.rsn && sdata->u.mesh.security != IEEE80211_MESH_SEC_NONE)) + elems = ieee802_11_parse_elems(mgmt->u.probe_resp.variable, + len - baselen, + false, mgmt->bssid, NULL); + if (!elems) return; - if (elems.ds_params) - freq = ieee80211_channel_to_frequency(elems.ds_params[0], band); + /* ignore non-mesh or secure / unsecure mismatch */ + if ((!elems->mesh_id || !elems->mesh_config) || + (elems->rsn && sdata->u.mesh.security == IEEE80211_MESH_SEC_NONE) || + (!elems->rsn && sdata->u.mesh.security != IEEE80211_MESH_SEC_NONE)) + goto free; + + if (elems->ds_params) + freq = ieee80211_channel_to_frequency(elems->ds_params[0], band); else freq = rx_status->freq; channel = ieee80211_get_channel(local->hw.wiphy, freq); if (!channel || channel->flags & IEEE80211_CHAN_DISABLED) - return; + goto free; - if (mesh_matches_local(sdata, &elems)) { + if (mesh_matches_local(sdata, elems)) { mpl_dbg(sdata, "rssi_threshold=%d,rx_status->signal=%d\n", sdata->u.mesh.mshcfg.rssi_threshold, rx_status->signal); if (!sdata->u.mesh.user_mpm || sdata->u.mesh.mshcfg.rssi_threshold == 0 || sdata->u.mesh.mshcfg.rssi_threshold < rx_status->signal) - mesh_neighbour_update(sdata, mgmt->sa, &elems, + mesh_neighbour_update(sdata, mgmt->sa, elems, rx_status); if (ifmsh->csa_role != IEEE80211_MESH_CSA_ROLE_INIT && !sdata->vif.csa_active) - ieee80211_mesh_process_chnswitch(sdata, &elems, true); + ieee80211_mesh_process_chnswitch(sdata, elems, true); } if (ifmsh->sync_ops) - ifmsh->sync_ops->rx_bcn_presp(sdata, - stype, mgmt, &elems, rx_status); + ifmsh->sync_ops->rx_bcn_presp(sdata, stype, mgmt, len, + elems->mesh_config, rx_status); +free: + kfree(elems); } int ieee80211_mesh_finish_csa(struct ieee80211_sub_if_data *sdata) @@ -1447,7 +1456,7 @@ static void mesh_rx_csa_frame(struct ieee80211_sub_if_data *sdata, struct ieee80211_mgmt *mgmt, size_t len) { struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; - struct ieee802_11_elems elems; + struct ieee802_11_elems *elems; u16 pre_value; bool fwd_csa = true; size_t baselen; @@ -1460,33 +1469,37 @@ static void mesh_rx_csa_frame(struct ieee80211_sub_if_data *sdata, pos = mgmt->u.action.u.chan_switch.variable; baselen = offsetof(struct ieee80211_mgmt, u.action.u.chan_switch.variable); - ieee802_11_parse_elems(pos, len - baselen, true, &elems, - mgmt->bssid, NULL); - - if (!mesh_matches_local(sdata, &elems)) + elems = ieee802_11_parse_elems(pos, len - baselen, true, + mgmt->bssid, NULL); + if (!elems) return; - ifmsh->chsw_ttl = elems.mesh_chansw_params_ie->mesh_ttl; + if (!mesh_matches_local(sdata, elems)) + goto free; + + ifmsh->chsw_ttl = elems->mesh_chansw_params_ie->mesh_ttl; if (!--ifmsh->chsw_ttl) fwd_csa = false; - pre_value = le16_to_cpu(elems.mesh_chansw_params_ie->mesh_pre_value); + pre_value = le16_to_cpu(elems->mesh_chansw_params_ie->mesh_pre_value); if (ifmsh->pre_value >= pre_value) - return; + goto free; ifmsh->pre_value = pre_value; if (!sdata->vif.csa_active && - !ieee80211_mesh_process_chnswitch(sdata, &elems, false)) { + !ieee80211_mesh_process_chnswitch(sdata, elems, false)) { mcsa_dbg(sdata, "Failed to process CSA action frame"); - return; + goto free; } /* forward or re-broadcast the CSA frame */ if (fwd_csa) { - if (mesh_fwd_csa_frame(sdata, mgmt, len, &elems) < 0) + if (mesh_fwd_csa_frame(sdata, mgmt, len, elems) < 0) mcsa_dbg(sdata, "Failed to forward the CSA frame"); } +free: + kfree(elems); } static void ieee80211_mesh_rx_mgmt_action(struct ieee80211_sub_if_data *sdata, diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c index a05b615deb51..44a6fdb6efbd 100644 --- a/net/mac80211/mesh_hwmp.c +++ b/net/mac80211/mesh_hwmp.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2008, 2009 open80211s Ltd. - * Copyright (C) 2019 Intel Corporation + * Copyright (C) 2019, 2021 Intel Corporation * Author: Luis Carlos Cobo */ @@ -908,7 +908,7 @@ static void hwmp_rann_frame_process(struct ieee80211_sub_if_data *sdata, void mesh_rx_path_sel_frame(struct ieee80211_sub_if_data *sdata, struct ieee80211_mgmt *mgmt, size_t len) { - struct ieee802_11_elems elems; + struct ieee802_11_elems *elems; size_t baselen; u32 path_metric; struct sta_info *sta; @@ -926,37 +926,41 @@ void mesh_rx_path_sel_frame(struct ieee80211_sub_if_data *sdata, rcu_read_unlock(); baselen = (u8 *) mgmt->u.action.u.mesh_action.variable - (u8 *) mgmt; - ieee802_11_parse_elems(mgmt->u.action.u.mesh_action.variable, - len - baselen, false, &elems, mgmt->bssid, NULL); + elems = ieee802_11_parse_elems(mgmt->u.action.u.mesh_action.variable, + len - baselen, false, mgmt->bssid, NULL); + if (!elems) + return; - if (elems.preq) { - if (elems.preq_len != 37) + if (elems->preq) { + if (elems->preq_len != 37) /* Right now we support just 1 destination and no AE */ - return; - path_metric = hwmp_route_info_get(sdata, mgmt, elems.preq, + goto free; + path_metric = hwmp_route_info_get(sdata, mgmt, elems->preq, MPATH_PREQ); if (path_metric) - hwmp_preq_frame_process(sdata, mgmt, elems.preq, + hwmp_preq_frame_process(sdata, mgmt, elems->preq, path_metric); } - if (elems.prep) { - if (elems.prep_len != 31) + if (elems->prep) { + if (elems->prep_len != 31) /* Right now we support no AE */ - return; - path_metric = hwmp_route_info_get(sdata, mgmt, elems.prep, + goto free; + path_metric = hwmp_route_info_get(sdata, mgmt, elems->prep, MPATH_PREP); if (path_metric) - hwmp_prep_frame_process(sdata, mgmt, elems.prep, + hwmp_prep_frame_process(sdata, mgmt, elems->prep, path_metric); } - if (elems.perr) { - if (elems.perr_len != 15) + if (elems->perr) { + if (elems->perr_len != 15) /* Right now we support only one destination per PERR */ - return; - hwmp_perr_frame_process(sdata, mgmt, elems.perr); + goto free; + hwmp_perr_frame_process(sdata, mgmt, elems->perr); } - if (elems.rann) - hwmp_rann_frame_process(sdata, mgmt, elems.rann); + if (elems->rann) + hwmp_rann_frame_process(sdata, mgmt, elems->rann); +free: + kfree(elems); } /** diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c index a6915847d78a..a829470dd59e 100644 --- a/net/mac80211/mesh_plink.c +++ b/net/mac80211/mesh_plink.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2008, 2009 open80211s Ltd. - * Copyright (C) 2019 Intel Corporation + * Copyright (C) 2019, 2021 Intel Corporation * Author: Luis Carlos Cobo */ #include @@ -1200,7 +1200,7 @@ void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata, struct ieee80211_mgmt *mgmt, size_t len, struct ieee80211_rx_status *rx_status) { - struct ieee802_11_elems elems; + struct ieee802_11_elems *elems; size_t baselen; u8 *baseaddr; @@ -1228,7 +1228,8 @@ void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata, if (baselen > len) return; } - ieee802_11_parse_elems(baseaddr, len - baselen, true, &elems, - mgmt->bssid, NULL); - mesh_process_plink_frame(sdata, mgmt, &elems, rx_status); + elems = ieee802_11_parse_elems(baseaddr, len - baselen, true, + mgmt->bssid, NULL); + mesh_process_plink_frame(sdata, mgmt, elems, rx_status); + kfree(elems); } diff --git a/net/mac80211/mesh_sync.c b/net/mac80211/mesh_sync.c index fde93de2b80a..9e342cc2504c 100644 --- a/net/mac80211/mesh_sync.c +++ b/net/mac80211/mesh_sync.c @@ -3,6 +3,7 @@ * Copyright 2011-2012, Pavel Zubarev * Copyright 2011-2012, Marco Porsch * Copyright 2011-2012, cozybit Inc. + * Copyright (C) 2021 Intel Corporation */ #include "ieee80211_i.h" @@ -35,12 +36,12 @@ struct sync_method { /** * mesh_peer_tbtt_adjusting - check if an mp is currently adjusting its TBTT * - * @ie: information elements of a management frame from the mesh peer + * @cfg: mesh config element from the mesh peer (or %NULL) */ -static bool mesh_peer_tbtt_adjusting(struct ieee802_11_elems *ie) +static bool mesh_peer_tbtt_adjusting(const struct ieee80211_meshconf_ie *cfg) { - return (ie->mesh_config->meshconf_cap & - IEEE80211_MESHCONF_CAPAB_TBTT_ADJUSTING) != 0; + return cfg && + (cfg->meshconf_cap & IEEE80211_MESHCONF_CAPAB_TBTT_ADJUSTING); } void mesh_sync_adjust_tsf(struct ieee80211_sub_if_data *sdata) @@ -76,11 +77,11 @@ void mesh_sync_adjust_tsf(struct ieee80211_sub_if_data *sdata) } } -static void mesh_sync_offset_rx_bcn_presp(struct ieee80211_sub_if_data *sdata, - u16 stype, - struct ieee80211_mgmt *mgmt, - struct ieee802_11_elems *elems, - struct ieee80211_rx_status *rx_status) +static void +mesh_sync_offset_rx_bcn_presp(struct ieee80211_sub_if_data *sdata, u16 stype, + struct ieee80211_mgmt *mgmt, unsigned int len, + const struct ieee80211_meshconf_ie *mesh_cfg, + struct ieee80211_rx_status *rx_status) { struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; struct ieee80211_local *local = sdata->local; @@ -101,10 +102,7 @@ static void mesh_sync_offset_rx_bcn_presp(struct ieee80211_sub_if_data *sdata, */ if (ieee80211_have_rx_timestamp(rx_status)) t_r = ieee80211_calculate_rx_timestamp(local, rx_status, - 24 + 12 + - elems->total_len + - FCS_LEN, - 24); + len + FCS_LEN, 24); else t_r = drv_get_tsf(local, sdata); @@ -119,7 +117,7 @@ static void mesh_sync_offset_rx_bcn_presp(struct ieee80211_sub_if_data *sdata, * dot11MeshNbrOffsetMaxNeighbor non-peer non-MBSS neighbors */ - if (elems->mesh_config && mesh_peer_tbtt_adjusting(elems)) { + if (mesh_peer_tbtt_adjusting(mesh_cfg)) { msync_dbg(sdata, "STA %pM : is adjusting TBTT\n", sta->sta.addr); goto no_sync; diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index c0ea3b1aa9e1..54ab0e1ef6ca 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -1490,6 +1490,7 @@ ieee80211_find_80211h_pwr_constr(struct ieee80211_sub_if_data *sdata, fallthrough; case NL80211_BAND_2GHZ: case NL80211_BAND_60GHZ: + case NL80211_BAND_LC: chan_increment = 1; break; case NL80211_BAND_5GHZ: @@ -2258,6 +2259,7 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, { struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; struct ieee80211_local *local = sdata->local; + struct ieee80211_bss_conf *bss_conf = &sdata->vif.bss_conf; u32 changed = 0; struct ieee80211_prep_tx_info info = { .subtype = stype, @@ -2407,6 +2409,10 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, cancel_delayed_work_sync(&ifmgd->tx_tspec_wk); sdata->encrypt_headroom = IEEE80211_ENCRYPT_HEADROOM; + + bss_conf->pwr_reduction = 0; + bss_conf->tx_pwr_env_num = 0; + memset(bss_conf->tx_pwr_env, 0, sizeof(bss_conf->tx_pwr_env)); } static void ieee80211_reset_ap_probe(struct ieee80211_sub_if_data *sdata) @@ -2509,7 +2515,7 @@ static void ieee80211_mlme_send_probe_req(struct ieee80211_sub_if_data *sdata, static void ieee80211_mgd_probe_ap_send(struct ieee80211_sub_if_data *sdata) { struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; - const u8 *ssid; + const struct element *ssid; u8 *dst = ifmgd->associated->bssid; u8 unicast_limit = max(1, max_probe_tries - 3); struct sta_info *sta; @@ -2546,14 +2552,14 @@ static void ieee80211_mgd_probe_ap_send(struct ieee80211_sub_if_data *sdata) int ssid_len; rcu_read_lock(); - ssid = ieee80211_bss_get_ie(ifmgd->associated, WLAN_EID_SSID); + ssid = ieee80211_bss_get_elem(ifmgd->associated, WLAN_EID_SSID); if (WARN_ON_ONCE(ssid == NULL)) ssid_len = 0; else - ssid_len = ssid[1]; + ssid_len = ssid->datalen; ieee80211_mlme_send_probe_req(sdata, sdata->vif.addr, dst, - ssid + 2, ssid_len, + ssid->data, ssid_len, ifmgd->associated->channel); rcu_read_unlock(); } @@ -2583,6 +2589,13 @@ static void ieee80211_mgd_probe_ap(struct ieee80211_sub_if_data *sdata, goto out; } + if (sdata->local->suspending) { + /* reschedule after resume */ + mutex_unlock(&sdata->local->mtx); + ieee80211_reset_ap_probe(sdata); + goto out; + } + if (beacon) { mlme_dbg_ratelimited(sdata, "detected beacon loss from AP (missed %d beacons) - probing\n", @@ -2629,7 +2642,7 @@ struct sk_buff *ieee80211_ap_probereq_get(struct ieee80211_hw *hw, struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; struct cfg80211_bss *cbss; struct sk_buff *skb; - const u8 *ssid; + const struct element *ssid; int ssid_len; if (WARN_ON(sdata->vif.type != NL80211_IFTYPE_STATION)) @@ -2647,16 +2660,17 @@ struct sk_buff *ieee80211_ap_probereq_get(struct ieee80211_hw *hw, return NULL; rcu_read_lock(); - ssid = ieee80211_bss_get_ie(cbss, WLAN_EID_SSID); - if (WARN_ONCE(!ssid || ssid[1] > IEEE80211_MAX_SSID_LEN, - "invalid SSID element (len=%d)", ssid ? ssid[1] : -1)) + ssid = ieee80211_bss_get_elem(cbss, WLAN_EID_SSID); + if (WARN_ONCE(!ssid || ssid->datalen > IEEE80211_MAX_SSID_LEN, + "invalid SSID element (len=%d)", + ssid ? ssid->datalen : -1)) ssid_len = 0; else - ssid_len = ssid[1]; + ssid_len = ssid->datalen; skb = ieee80211_build_probe_req(sdata, sdata->vif.addr, cbss->bssid, (u32) -1, cbss->channel, - ssid + 2, ssid_len, + ssid->data, ssid_len, NULL, 0, IEEE80211_PROBE_FLAG_DIRECTED); rcu_read_unlock(); @@ -2870,17 +2884,17 @@ static void ieee80211_auth_challenge(struct ieee80211_sub_if_data *sdata, { struct ieee80211_local *local = sdata->local; struct ieee80211_mgd_auth_data *auth_data = sdata->u.mgd.auth_data; + const struct element *challenge; u8 *pos; - struct ieee802_11_elems elems; u32 tx_flags = 0; struct ieee80211_prep_tx_info info = { .subtype = IEEE80211_STYPE_AUTH, }; pos = mgmt->u.auth.variable; - ieee802_11_parse_elems(pos, len - (pos - (u8 *)mgmt), false, &elems, - mgmt->bssid, auth_data->bss->bssid); - if (!elems.challenge) + challenge = cfg80211_find_elem(WLAN_EID_CHALLENGE, pos, + len - (pos - (u8 *)mgmt)); + if (!challenge) return; auth_data->expected_transaction = 4; drv_mgd_prepare_tx(sdata->local, sdata, &info); @@ -2888,7 +2902,8 @@ static void ieee80211_auth_challenge(struct ieee80211_sub_if_data *sdata, tx_flags = IEEE80211_TX_CTL_REQ_TX_STATUS | IEEE80211_TX_INTFL_MLME_CONN_TX; ieee80211_send_auth(sdata, 3, auth_data->algorithm, 0, - elems.challenge - 2, elems.challenge_len + 2, + (void *)challenge, + challenge->datalen + sizeof(*challenge), auth_data->bss->bssid, auth_data->bss->bssid, auth_data->key, auth_data->key_len, auth_data->key_idx, tx_flags); @@ -3290,8 +3305,11 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, aid = 0; /* TODO */ } capab_info = le16_to_cpu(mgmt->u.assoc_resp.capab_info); - ieee802_11_parse_elems(pos, len - (pos - (u8 *)mgmt), false, elems, - mgmt->bssid, assoc_data->bss->bssid); + elems = ieee802_11_parse_elems(pos, len - (pos - (u8 *)mgmt), false, + mgmt->bssid, assoc_data->bss->bssid); + + if (!elems) + return false; if (elems->aid_resp) aid = le16_to_cpu(elems->aid_resp->aid); @@ -3313,7 +3331,8 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, if (!is_s1g && !elems->supp_rates) { sdata_info(sdata, "no SuppRates element in AssocResp\n"); - return false; + ret = false; + goto out; } sdata->vif.bss_conf.aid = aid; @@ -3335,7 +3354,7 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, (!(ifmgd->flags & IEEE80211_STA_DISABLE_VHT) && (!elems->vht_cap_elem || !elems->vht_operation)))) { const struct cfg80211_bss_ies *ies; - struct ieee802_11_elems bss_elems; + struct ieee802_11_elems *bss_elems; rcu_read_lock(); ies = rcu_dereference(cbss->ies); @@ -3343,16 +3362,22 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, bss_ies = kmemdup(ies, sizeof(*ies) + ies->len, GFP_ATOMIC); rcu_read_unlock(); - if (!bss_ies) - return false; + if (!bss_ies) { + ret = false; + goto out; + } + + bss_elems = ieee802_11_parse_elems(bss_ies->data, bss_ies->len, + false, mgmt->bssid, + assoc_data->bss->bssid); + if (!bss_elems) { + ret = false; + goto out; + } - ieee802_11_parse_elems(bss_ies->data, bss_ies->len, - false, &bss_elems, - mgmt->bssid, - assoc_data->bss->bssid); if (assoc_data->wmm && - !elems->wmm_param && bss_elems.wmm_param) { - elems->wmm_param = bss_elems.wmm_param; + !elems->wmm_param && bss_elems->wmm_param) { + elems->wmm_param = bss_elems->wmm_param; sdata_info(sdata, "AP bug: WMM param missing from AssocResp\n"); } @@ -3361,30 +3386,32 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, * Also check if we requested HT/VHT, otherwise the AP doesn't * have to include the IEs in the (re)association response. */ - if (!elems->ht_cap_elem && bss_elems.ht_cap_elem && + if (!elems->ht_cap_elem && bss_elems->ht_cap_elem && !(ifmgd->flags & IEEE80211_STA_DISABLE_HT)) { - elems->ht_cap_elem = bss_elems.ht_cap_elem; + elems->ht_cap_elem = bss_elems->ht_cap_elem; sdata_info(sdata, "AP bug: HT capability missing from AssocResp\n"); } - if (!elems->ht_operation && bss_elems.ht_operation && + if (!elems->ht_operation && bss_elems->ht_operation && !(ifmgd->flags & IEEE80211_STA_DISABLE_HT)) { - elems->ht_operation = bss_elems.ht_operation; + elems->ht_operation = bss_elems->ht_operation; sdata_info(sdata, "AP bug: HT operation missing from AssocResp\n"); } - if (!elems->vht_cap_elem && bss_elems.vht_cap_elem && + if (!elems->vht_cap_elem && bss_elems->vht_cap_elem && !(ifmgd->flags & IEEE80211_STA_DISABLE_VHT)) { - elems->vht_cap_elem = bss_elems.vht_cap_elem; + elems->vht_cap_elem = bss_elems->vht_cap_elem; sdata_info(sdata, "AP bug: VHT capa missing from AssocResp\n"); } - if (!elems->vht_operation && bss_elems.vht_operation && + if (!elems->vht_operation && bss_elems->vht_operation && !(ifmgd->flags & IEEE80211_STA_DISABLE_VHT)) { - elems->vht_operation = bss_elems.vht_operation; + elems->vht_operation = bss_elems->vht_operation; sdata_info(sdata, "AP bug: VHT operation missing from AssocResp\n"); } + + kfree(bss_elems); } /* @@ -3629,6 +3656,7 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, ret = true; out: + kfree(elems); kfree(bss_ies); return ret; } @@ -3640,7 +3668,7 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; struct ieee80211_mgd_assoc_data *assoc_data = ifmgd->assoc_data; u16 capab_info, status_code, aid; - struct ieee802_11_elems elems; + struct ieee802_11_elems *elems; int ac, uapsd_queues = -1; u8 *pos; bool reassoc; @@ -3697,14 +3725,16 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, fils_decrypt_assoc_resp(sdata, (u8 *)mgmt, &len, assoc_data) < 0) return; - ieee802_11_parse_elems(pos, len - (pos - (u8 *)mgmt), false, &elems, - mgmt->bssid, assoc_data->bss->bssid); + elems = ieee802_11_parse_elems(pos, len - (pos - (u8 *)mgmt), false, + mgmt->bssid, assoc_data->bss->bssid); + if (!elems) + goto notify_driver; if (status_code == WLAN_STATUS_ASSOC_REJECTED_TEMPORARILY && - elems.timeout_int && - elems.timeout_int->type == WLAN_TIMEOUT_ASSOC_COMEBACK) { + elems->timeout_int && + elems->timeout_int->type == WLAN_TIMEOUT_ASSOC_COMEBACK) { u32 tu, ms; - tu = le32_to_cpu(elems.timeout_int->value); + tu = le32_to_cpu(elems->timeout_int->value); ms = tu * 1024 / 1000; sdata_info(sdata, "%pM rejected association temporarily; comeback duration %u TU (%u ms)\n", @@ -3724,7 +3754,7 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, event.u.mlme.reason = status_code; drv_event_callback(sdata->local, sdata, &event); } else { - if (!ieee80211_assoc_success(sdata, cbss, mgmt, len, &elems)) { + if (!ieee80211_assoc_success(sdata, cbss, mgmt, len, elems)) { /* oops -- internal error -- send timeout for now */ ieee80211_destroy_assoc_data(sdata, false, false); cfg80211_assoc_timeout(sdata->dev, cbss); @@ -3754,6 +3784,7 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, ifmgd->assoc_req_ies, ifmgd->assoc_req_ies_len); notify_driver: drv_mgd_complete_tx(sdata->local, sdata, &info); + kfree(elems); } static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata, @@ -3958,7 +3989,7 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, struct ieee80211_bss_conf *bss_conf = &sdata->vif.bss_conf; struct ieee80211_mgmt *mgmt = (void *) hdr; size_t baselen; - struct ieee802_11_elems elems; + struct ieee802_11_elems *elems; struct ieee80211_local *local = sdata->local; struct ieee80211_chanctx_conf *chanctx_conf; struct ieee80211_channel *chan; @@ -4004,15 +4035,16 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, if (ifmgd->assoc_data && ifmgd->assoc_data->need_beacon && ieee80211_rx_our_beacon(bssid, ifmgd->assoc_data->bss)) { - ieee802_11_parse_elems(variable, - len - baselen, false, &elems, - bssid, - ifmgd->assoc_data->bss->bssid); + elems = ieee802_11_parse_elems(variable, len - baselen, false, + bssid, + ifmgd->assoc_data->bss->bssid); + if (!elems) + return; ieee80211_rx_bss_info(sdata, mgmt, len, rx_status); - if (elems.dtim_period) - ifmgd->dtim_period = elems.dtim_period; + if (elems->dtim_period) + ifmgd->dtim_period = elems->dtim_period; ifmgd->have_beacon = true; ifmgd->assoc_data->need_beacon = false; if (ieee80211_hw_check(&local->hw, TIMING_BEACON_ONLY)) { @@ -4020,17 +4052,17 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, le64_to_cpu(mgmt->u.beacon.timestamp); sdata->vif.bss_conf.sync_device_ts = rx_status->device_timestamp; - sdata->vif.bss_conf.sync_dtim_count = elems.dtim_count; + sdata->vif.bss_conf.sync_dtim_count = elems->dtim_count; } - if (elems.mbssid_config_ie) + if (elems->mbssid_config_ie) bss_conf->profile_periodicity = - elems.mbssid_config_ie->profile_periodicity; + elems->mbssid_config_ie->profile_periodicity; else bss_conf->profile_periodicity = 0; - if (elems.ext_capab_len >= 11 && - (elems.ext_capab[10] & WLAN_EXT_CAPA11_EMA_SUPPORT)) + if (elems->ext_capab_len >= 11 && + (elems->ext_capab[10] & WLAN_EXT_CAPA11_EMA_SUPPORT)) bss_conf->ema_ap = true; else bss_conf->ema_ap = false; @@ -4039,6 +4071,7 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, ifmgd->assoc_data->timeout = jiffies; ifmgd->assoc_data->timeout_started = true; run_again(sdata, ifmgd->assoc_data->timeout); + kfree(elems); return; } @@ -4070,13 +4103,15 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, */ if (!ieee80211_is_s1g_beacon(hdr->frame_control)) ncrc = crc32_be(0, (void *)&mgmt->u.beacon.beacon_int, 4); - ncrc = ieee802_11_parse_elems_crc(variable, - len - baselen, false, &elems, - care_about_ies, ncrc, - mgmt->bssid, bssid); + elems = ieee802_11_parse_elems_crc(variable, len - baselen, + false, care_about_ies, ncrc, + mgmt->bssid, bssid); + if (!elems) + return; + ncrc = elems->crc; if (ieee80211_hw_check(&local->hw, PS_NULLFUNC_STACK) && - ieee80211_check_tim(elems.tim, elems.tim_len, bss_conf->aid)) { + ieee80211_check_tim(elems->tim, elems->tim_len, bss_conf->aid)) { if (local->hw.conf.dynamic_ps_timeout > 0) { if (local->hw.conf.flags & IEEE80211_CONF_PS) { local->hw.conf.flags &= ~IEEE80211_CONF_PS; @@ -4146,12 +4181,12 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, le64_to_cpu(mgmt->u.beacon.timestamp); sdata->vif.bss_conf.sync_device_ts = rx_status->device_timestamp; - sdata->vif.bss_conf.sync_dtim_count = elems.dtim_count; + sdata->vif.bss_conf.sync_dtim_count = elems->dtim_count; } if ((ncrc == ifmgd->beacon_crc && ifmgd->beacon_crc_valid) || ieee80211_is_s1g_short_beacon(mgmt->frame_control)) - return; + goto free; ifmgd->beacon_crc = ncrc; ifmgd->beacon_crc_valid = true; @@ -4159,12 +4194,12 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, ieee80211_sta_process_chanswitch(sdata, rx_status->mactime, rx_status->device_timestamp, - &elems, true); + elems, true); if (!(ifmgd->flags & IEEE80211_STA_DISABLE_WMM) && - ieee80211_sta_wmm_params(local, sdata, elems.wmm_param, - elems.wmm_param_len, - elems.mu_edca_param_set)) + ieee80211_sta_wmm_params(local, sdata, elems->wmm_param, + elems->wmm_param_len, + elems->mu_edca_param_set)) changed |= BSS_CHANGED_QOS; /* @@ -4173,7 +4208,7 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, */ if (!ifmgd->have_beacon) { /* a few bogus AP send dtim_period = 0 or no TIM IE */ - bss_conf->dtim_period = elems.dtim_period ?: 1; + bss_conf->dtim_period = elems->dtim_period ?: 1; changed |= BSS_CHANGED_BEACON_INFO; ifmgd->have_beacon = true; @@ -4185,9 +4220,9 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, ieee80211_recalc_ps_vif(sdata); } - if (elems.erp_info) { + if (elems->erp_info) { erp_valid = true; - erp_value = elems.erp_info[0]; + erp_value = elems->erp_info[0]; } else { erp_valid = false; } @@ -4200,12 +4235,12 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, mutex_lock(&local->sta_mtx); sta = sta_info_get(sdata, bssid); - changed |= ieee80211_recalc_twt_req(sdata, sta, &elems); + changed |= ieee80211_recalc_twt_req(sdata, sta, elems); - if (ieee80211_config_bw(sdata, sta, elems.ht_cap_elem, - elems.vht_cap_elem, elems.ht_operation, - elems.vht_operation, elems.he_operation, - elems.s1g_oper, bssid, &changed)) { + if (ieee80211_config_bw(sdata, sta, elems->ht_cap_elem, + elems->vht_cap_elem, elems->ht_operation, + elems->vht_operation, elems->he_operation, + elems->s1g_oper, bssid, &changed)) { mutex_unlock(&local->sta_mtx); sdata_info(sdata, "failed to follow AP %pM bandwidth change, disconnect\n", @@ -4217,21 +4252,23 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, sizeof(deauth_buf), true, WLAN_REASON_DEAUTH_LEAVING, false); - return; + goto free; } - if (sta && elems.opmode_notif) - ieee80211_vht_handle_opmode(sdata, sta, *elems.opmode_notif, + if (sta && elems->opmode_notif) + ieee80211_vht_handle_opmode(sdata, sta, *elems->opmode_notif, rx_status->band); mutex_unlock(&local->sta_mtx); changed |= ieee80211_handle_pwr_constr(sdata, chan, mgmt, - elems.country_elem, - elems.country_elem_len, - elems.pwr_constr_elem, - elems.cisco_dtpc_elem); + elems->country_elem, + elems->country_elem_len, + elems->pwr_constr_elem, + elems->cisco_dtpc_elem); ieee80211_bss_info_change_notify(sdata, changed); +free: + kfree(elems); } void ieee80211_sta_rx_queued_ext(struct ieee80211_sub_if_data *sdata, @@ -4260,7 +4297,6 @@ void ieee80211_sta_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata, struct ieee80211_rx_status *rx_status; struct ieee80211_mgmt *mgmt; u16 fc; - struct ieee802_11_elems elems; int ies_len; rx_status = (struct ieee80211_rx_status *) skb->cb; @@ -4292,6 +4328,8 @@ void ieee80211_sta_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata, break; case IEEE80211_STYPE_ACTION: if (mgmt->u.action.category == WLAN_CATEGORY_SPECTRUM_MGMT) { + struct ieee802_11_elems *elems; + ies_len = skb->len - offsetof(struct ieee80211_mgmt, u.action.u.chan_switch.variable); @@ -4300,18 +4338,19 @@ void ieee80211_sta_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata, break; /* CSA IE cannot be overridden, no need for BSSID */ - ieee802_11_parse_elems( - mgmt->u.action.u.chan_switch.variable, - ies_len, true, &elems, mgmt->bssid, NULL); + elems = ieee802_11_parse_elems( + mgmt->u.action.u.chan_switch.variable, + ies_len, true, mgmt->bssid, NULL); - if (elems.parse_error) - break; - - ieee80211_sta_process_chanswitch(sdata, - rx_status->mactime, - rx_status->device_timestamp, - &elems, false); + if (elems && !elems->parse_error) + ieee80211_sta_process_chanswitch(sdata, + rx_status->mactime, + rx_status->device_timestamp, + elems, false); + kfree(elems); } else if (mgmt->u.action.category == WLAN_CATEGORY_PUBLIC) { + struct ieee802_11_elems *elems; + ies_len = skb->len - offsetof(struct ieee80211_mgmt, u.action.u.ext_chan_switch.variable); @@ -4323,21 +4362,22 @@ void ieee80211_sta_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata, * extended CSA IE can't be overridden, no need for * BSSID */ - ieee802_11_parse_elems( - mgmt->u.action.u.ext_chan_switch.variable, - ies_len, true, &elems, mgmt->bssid, NULL); + elems = ieee802_11_parse_elems( + mgmt->u.action.u.ext_chan_switch.variable, + ies_len, true, mgmt->bssid, NULL); - if (elems.parse_error) - break; + if (elems && !elems->parse_error) { + /* for the handling code pretend it was an IE */ + elems->ext_chansw_ie = + &mgmt->u.action.u.ext_chan_switch.data; - /* for the handling code pretend this was also an IE */ - elems.ext_chansw_ie = - &mgmt->u.action.u.ext_chan_switch.data; + ieee80211_sta_process_chanswitch(sdata, + rx_status->mactime, + rx_status->device_timestamp, + elems, false); + } - ieee80211_sta_process_chanswitch(sdata, - rx_status->mactime, - rx_status->device_timestamp, - &elems, false); + kfree(elems); } break; } @@ -4972,10 +5012,22 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata, bool is_6ghz = cbss->channel->band == NL80211_BAND_6GHZ; bool is_5ghz = cbss->channel->band == NL80211_BAND_5GHZ; struct ieee80211_bss *bss = (void *)cbss->priv; + struct ieee802_11_elems *elems; + const struct cfg80211_bss_ies *ies; int ret; u32 i; bool have_80mhz; + rcu_read_lock(); + + ies = rcu_dereference(cbss->ies); + elems = ieee802_11_parse_elems(ies->data, ies->len, false, + NULL, NULL); + if (!elems) { + rcu_read_unlock(); + return -ENOMEM; + } + sband = local->hw.wiphy->bands[cbss->channel->band]; ifmgd->flags &= ~(IEEE80211_STA_DISABLE_40MHZ | @@ -4998,18 +5050,9 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata, ieee80211_vif_type_p2p(&sdata->vif))) ifmgd->flags |= IEEE80211_STA_DISABLE_HE; - rcu_read_lock(); - if (!(ifmgd->flags & IEEE80211_STA_DISABLE_HT) && !is_6ghz) { - const u8 *ht_oper_ie, *ht_cap_ie; - - ht_oper_ie = ieee80211_bss_get_ie(cbss, WLAN_EID_HT_OPERATION); - if (ht_oper_ie && ht_oper_ie[1] >= sizeof(*ht_oper)) - ht_oper = (void *)(ht_oper_ie + 2); - - ht_cap_ie = ieee80211_bss_get_ie(cbss, WLAN_EID_HT_CAPABILITY); - if (ht_cap_ie && ht_cap_ie[1] >= sizeof(*ht_cap)) - ht_cap = (void *)(ht_cap_ie + 2); + ht_oper = elems->ht_operation; + ht_cap = elems->ht_cap_elem; if (!ht_cap) { ifmgd->flags |= IEEE80211_STA_DISABLE_HT; @@ -5018,12 +5061,7 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata, } if (!(ifmgd->flags & IEEE80211_STA_DISABLE_VHT) && !is_6ghz) { - const u8 *vht_oper_ie, *vht_cap; - - vht_oper_ie = ieee80211_bss_get_ie(cbss, - WLAN_EID_VHT_OPERATION); - if (vht_oper_ie && vht_oper_ie[1] >= sizeof(*vht_oper)) - vht_oper = (void *)(vht_oper_ie + 2); + vht_oper = elems->vht_operation; if (vht_oper && !ht_oper) { vht_oper = NULL; sdata_info(sdata, @@ -5033,25 +5071,38 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata, ifmgd->flags |= IEEE80211_STA_DISABLE_HE; } - vht_cap = ieee80211_bss_get_ie(cbss, WLAN_EID_VHT_CAPABILITY); - if (!vht_cap || vht_cap[1] < sizeof(struct ieee80211_vht_cap)) { + if (!elems->vht_cap_elem) { ifmgd->flags |= IEEE80211_STA_DISABLE_VHT; vht_oper = NULL; } } if (!(ifmgd->flags & IEEE80211_STA_DISABLE_HE)) { - const struct cfg80211_bss_ies *ies; - const u8 *he_oper_ie; + he_oper = elems->he_operation; - ies = rcu_dereference(cbss->ies); - he_oper_ie = cfg80211_find_ext_ie(WLAN_EID_EXT_HE_OPERATION, - ies->data, ies->len); - if (he_oper_ie && - he_oper_ie[1] >= ieee80211_he_oper_size(&he_oper_ie[3])) - he_oper = (void *)(he_oper_ie + 3); - else - he_oper = NULL; + if (is_6ghz) { + struct ieee80211_bss_conf *bss_conf; + u8 i, j = 0; + + bss_conf = &sdata->vif.bss_conf; + + if (elems->pwr_constr_elem) + bss_conf->pwr_reduction = *elems->pwr_constr_elem; + + BUILD_BUG_ON(ARRAY_SIZE(bss_conf->tx_pwr_env) != + ARRAY_SIZE(elems->tx_pwr_env)); + + for (i = 0; i < elems->tx_pwr_env_num; i++) { + if (elems->tx_pwr_env_len[i] > + sizeof(bss_conf->tx_pwr_env[j])) + continue; + + bss_conf->tx_pwr_env_num++; + memcpy(&bss_conf->tx_pwr_env[j], elems->tx_pwr_env[i], + elems->tx_pwr_env_len[i]); + j++; + } + } if (!ieee80211_verify_sta_he_mcs_support(sdata, sband, he_oper)) ifmgd->flags |= IEEE80211_STA_DISABLE_HE; @@ -5072,13 +5123,8 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata, ifmgd->flags |= IEEE80211_STA_DISABLE_VHT; if (sband->band == NL80211_BAND_S1GHZ) { - const u8 *s1g_oper_ie; - - s1g_oper_ie = ieee80211_bss_get_ie(cbss, - WLAN_EID_S1G_OPERATION); - if (s1g_oper_ie && s1g_oper_ie[1] >= sizeof(*s1g_oper)) - s1g_oper = (void *)(s1g_oper_ie + 2); - else + s1g_oper = elems->s1g_oper; + if (!s1g_oper) sdata_info(sdata, "AP missing S1G operation element?\n"); } @@ -5094,6 +5140,9 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata, local->rx_chains); rcu_read_unlock(); + /* the element data was RCU protected so no longer valid anyway */ + kfree(elems); + elems = NULL; if (ifmgd->flags & IEEE80211_STA_DISABLE_HE && is_6ghz) { sdata_info(sdata, "Rejecting non-HE 6/7 GHz connection"); @@ -5498,7 +5547,7 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, const struct cfg80211_bss_ies *beacon_ies; struct ieee80211_supported_band *sband; struct ieee80211_bss_conf *bss_conf = &sdata->vif.bss_conf; - const u8 *ssidie, *ht_ie, *vht_ie; + const struct element *ssid_elem, *ht_elem, *vht_elem; int i, err; bool override = false; @@ -5507,14 +5556,14 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, return -ENOMEM; rcu_read_lock(); - ssidie = ieee80211_bss_get_ie(req->bss, WLAN_EID_SSID); - if (!ssidie || ssidie[1] > sizeof(assoc_data->ssid)) { + ssid_elem = ieee80211_bss_get_elem(req->bss, WLAN_EID_SSID); + if (!ssid_elem || ssid_elem->datalen > sizeof(assoc_data->ssid)) { rcu_read_unlock(); kfree(assoc_data); return -EINVAL; } - memcpy(assoc_data->ssid, ssidie + 2, ssidie[1]); - assoc_data->ssid_len = ssidie[1]; + memcpy(assoc_data->ssid, ssid_elem->data, ssid_elem->datalen); + assoc_data->ssid_len = ssid_elem->datalen; memcpy(bss_conf->ssid, assoc_data->ssid, assoc_data->ssid_len); bss_conf->ssid_len = assoc_data->ssid_len; rcu_read_unlock(); @@ -5628,15 +5677,15 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, assoc_data->supp_rates_len = bss->supp_rates_len; rcu_read_lock(); - ht_ie = ieee80211_bss_get_ie(req->bss, WLAN_EID_HT_OPERATION); - if (ht_ie && ht_ie[1] >= sizeof(struct ieee80211_ht_operation)) + ht_elem = ieee80211_bss_get_elem(req->bss, WLAN_EID_HT_OPERATION); + if (ht_elem && ht_elem->datalen >= sizeof(struct ieee80211_ht_operation)) assoc_data->ap_ht_param = - ((struct ieee80211_ht_operation *)(ht_ie + 2))->ht_param; + ((struct ieee80211_ht_operation *)(ht_elem->data))->ht_param; else if (!is_6ghz) ifmgd->flags |= IEEE80211_STA_DISABLE_HT; - vht_ie = ieee80211_bss_get_ie(req->bss, WLAN_EID_VHT_CAPABILITY); - if (vht_ie && vht_ie[1] >= sizeof(struct ieee80211_vht_cap)) - memcpy(&assoc_data->ap_vht_cap, vht_ie + 2, + vht_elem = ieee80211_bss_get_elem(req->bss, WLAN_EID_VHT_CAPABILITY); + if (vht_elem && vht_elem->datalen >= sizeof(struct ieee80211_vht_cap)) + memcpy(&assoc_data->ap_vht_cap, vht_elem->data, sizeof(struct ieee80211_vht_cap)); else if (is_5ghz) ifmgd->flags |= IEEE80211_STA_DISABLE_VHT | diff --git a/net/mac80211/pm.c b/net/mac80211/pm.c index 7809a906d7fe..0ccb5701c7f3 100644 --- a/net/mac80211/pm.c +++ b/net/mac80211/pm.c @@ -27,6 +27,9 @@ int __ieee80211_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan) if (!local->open_count) goto suspend; + local->suspending = true; + mb(); /* make suspending visible before any cancellation */ + ieee80211_scan_cancel(local); ieee80211_dfs_cac_cancel(local); @@ -176,6 +179,7 @@ int __ieee80211_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan) /* need suspended to be visible before quiescing is false */ barrier(); local->quiescing = false; + local->suspending = false; return 0; } diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index c4071b015c18..fc5c608d02e2 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -3216,10 +3216,7 @@ static bool ieee80211_process_rx_twt_action(struct ieee80211_rx_data *rx) { struct ieee80211_mgmt *mgmt = (struct ieee80211_mgmt *)rx->skb->data; - struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(rx->skb); struct ieee80211_sub_if_data *sdata = rx->sdata; - const struct ieee80211_sta_he_cap *hecap; - struct ieee80211_supported_band *sband; /* TWT actions are only supported in AP for the moment */ if (sdata->vif.type != NL80211_IFTYPE_AP) @@ -3228,14 +3225,7 @@ ieee80211_process_rx_twt_action(struct ieee80211_rx_data *rx) if (!rx->local->ops->add_twt_setup) return false; - sband = rx->local->hw.wiphy->bands[status->band]; - hecap = ieee80211_get_he_iftype_cap(sband, - ieee80211_vif_type_p2p(&sdata->vif)); - if (!hecap) - return false; - - if (!(hecap->he_cap_elem.mac_cap_info[0] & - IEEE80211_HE_MAC_CAP0_TWT_RES)) + if (!sdata->vif.bss_conf.twt_responder) return false; if (!rx->sta) diff --git a/net/mac80211/s1g.c b/net/mac80211/s1g.c index 7e35ab5b6166..4141bc80cdfd 100644 --- a/net/mac80211/s1g.c +++ b/net/mac80211/s1g.c @@ -104,9 +104,11 @@ ieee80211_s1g_rx_twt_setup(struct ieee80211_sub_if_data *sdata, /* broadcast TWT not supported yet */ if (twt->control & IEEE80211_TWT_CONTROL_NEG_TYPE_BROADCAST) { - le16p_replace_bits(&twt_agrt->req_type, - TWT_SETUP_CMD_REJECT, - IEEE80211_TWT_REQTYPE_SETUP_CMD); + twt_agrt->req_type &= + ~cpu_to_le16(IEEE80211_TWT_REQTYPE_SETUP_CMD); + twt_agrt->req_type |= + le16_encode_bits(TWT_SETUP_CMD_REJECT, + IEEE80211_TWT_REQTYPE_SETUP_CMD); goto out; } diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index 6b50cb5e0e3c..5e6b275afc9e 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -9,7 +9,7 @@ * Copyright 2007, Michael Wu * Copyright 2013-2015 Intel Mobile Communications GmbH * Copyright 2016-2017 Intel Deutschland GmbH - * Copyright (C) 2018-2020 Intel Corporation + * Copyright (C) 2018-2021 Intel Corporation */ #include @@ -155,7 +155,7 @@ ieee80211_bss_info_update(struct ieee80211_local *local, }; bool signal_valid; struct ieee80211_sub_if_data *scan_sdata; - struct ieee802_11_elems elems; + struct ieee802_11_elems *elems; size_t baselen; u8 *elements; @@ -209,8 +209,10 @@ ieee80211_bss_info_update(struct ieee80211_local *local, if (baselen > len) return NULL; - ieee802_11_parse_elems(elements, len - baselen, false, &elems, - mgmt->bssid, cbss->bssid); + elems = ieee802_11_parse_elems(elements, len - baselen, false, + mgmt->bssid, cbss->bssid); + if (!elems) + return NULL; /* In case the signal is invalid update the status */ signal_valid = channel == cbss->channel; @@ -218,15 +220,17 @@ ieee80211_bss_info_update(struct ieee80211_local *local, rx_status->flag |= RX_FLAG_NO_SIGNAL_VAL; bss = (void *)cbss->priv; - ieee80211_update_bss_from_elems(local, bss, &elems, rx_status, beacon); + ieee80211_update_bss_from_elems(local, bss, elems, rx_status, beacon); list_for_each_entry(non_tx_cbss, &cbss->nontrans_list, nontrans_list) { non_tx_bss = (void *)non_tx_cbss->priv; - ieee80211_update_bss_from_elems(local, non_tx_bss, &elems, + ieee80211_update_bss_from_elems(local, non_tx_bss, elems, rx_status, beacon); } + kfree(elems); + return bss; } diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 2b5acb37587f..51b49f0d3ad4 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -444,6 +444,7 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata, switch (i) { case NL80211_BAND_2GHZ: + case NL80211_BAND_LC: /* * We use both here, even if we cannot really know for * sure the station will support both, but the only use @@ -513,6 +514,8 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata, sta->cparams.target = MS2TIME(20); sta->cparams.interval = MS2TIME(100); sta->cparams.ecn = true; + sta->cparams.ce_threshold_selector = 0; + sta->cparams.ce_threshold_mask = 0; sta_dbg(sdata, "Allocated STA %pM\n", sta->sta.addr); diff --git a/net/mac80211/tdls.c b/net/mac80211/tdls.c index 45e532ad1215..137be9ec94af 100644 --- a/net/mac80211/tdls.c +++ b/net/mac80211/tdls.c @@ -6,7 +6,7 @@ * Copyright 2014, Intel Corporation * Copyright 2014 Intel Mobile Communications GmbH * Copyright 2015 - 2016 Intel Deutschland GmbH - * Copyright (C) 2019 Intel Corporation + * Copyright (C) 2019, 2021 Intel Corporation */ #include @@ -1684,7 +1684,7 @@ ieee80211_process_tdls_channel_switch_resp(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb) { struct ieee80211_local *local = sdata->local; - struct ieee802_11_elems elems; + struct ieee802_11_elems *elems = NULL; struct sta_info *sta; struct ieee80211_tdls_data *tf = (void *)skb->data; bool local_initiator; @@ -1718,16 +1718,20 @@ ieee80211_process_tdls_channel_switch_resp(struct ieee80211_sub_if_data *sdata, goto call_drv; } - ieee802_11_parse_elems(tf->u.chan_switch_resp.variable, - skb->len - baselen, false, &elems, - NULL, NULL); - if (elems.parse_error) { + elems = ieee802_11_parse_elems(tf->u.chan_switch_resp.variable, + skb->len - baselen, false, NULL, NULL); + if (!elems) { + ret = -ENOMEM; + goto out; + } + + if (elems->parse_error) { tdls_dbg(sdata, "Invalid IEs in TDLS channel switch resp\n"); ret = -EINVAL; goto out; } - if (!elems.ch_sw_timing || !elems.lnk_id) { + if (!elems->ch_sw_timing || !elems->lnk_id) { tdls_dbg(sdata, "TDLS channel switch resp - missing IEs\n"); ret = -EINVAL; goto out; @@ -1735,15 +1739,15 @@ ieee80211_process_tdls_channel_switch_resp(struct ieee80211_sub_if_data *sdata, /* validate the initiator is set correctly */ local_initiator = - !memcmp(elems.lnk_id->init_sta, sdata->vif.addr, ETH_ALEN); + !memcmp(elems->lnk_id->init_sta, sdata->vif.addr, ETH_ALEN); if (local_initiator == sta->sta.tdls_initiator) { tdls_dbg(sdata, "TDLS chan switch invalid lnk-id initiator\n"); ret = -EINVAL; goto out; } - params.switch_time = le16_to_cpu(elems.ch_sw_timing->switch_time); - params.switch_timeout = le16_to_cpu(elems.ch_sw_timing->switch_timeout); + params.switch_time = le16_to_cpu(elems->ch_sw_timing->switch_time); + params.switch_timeout = le16_to_cpu(elems->ch_sw_timing->switch_timeout); params.tmpl_skb = ieee80211_tdls_ch_sw_resp_tmpl_get(sta, ¶ms.ch_sw_tm_ie); @@ -1763,6 +1767,7 @@ call_drv: out: mutex_unlock(&local->sta_mtx); dev_kfree_skb_any(params.tmpl_skb); + kfree(elems); return ret; } @@ -1771,7 +1776,7 @@ ieee80211_process_tdls_channel_switch_req(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb) { struct ieee80211_local *local = sdata->local; - struct ieee802_11_elems elems; + struct ieee802_11_elems *elems; struct cfg80211_chan_def chandef; struct ieee80211_channel *chan; enum nl80211_channel_type chan_type; @@ -1831,22 +1836,27 @@ ieee80211_process_tdls_channel_switch_req(struct ieee80211_sub_if_data *sdata, return -EINVAL; } - ieee802_11_parse_elems(tf->u.chan_switch_req.variable, - skb->len - baselen, false, &elems, NULL, NULL); - if (elems.parse_error) { + elems = ieee802_11_parse_elems(tf->u.chan_switch_req.variable, + skb->len - baselen, false, NULL, NULL); + if (!elems) + return -ENOMEM; + + if (elems->parse_error) { tdls_dbg(sdata, "Invalid IEs in TDLS channel switch req\n"); - return -EINVAL; + ret = -EINVAL; + goto free; } - if (!elems.ch_sw_timing || !elems.lnk_id) { + if (!elems->ch_sw_timing || !elems->lnk_id) { tdls_dbg(sdata, "TDLS channel switch req - missing IEs\n"); - return -EINVAL; + ret = -EINVAL; + goto free; } - if (!elems.sec_chan_offs) { + if (!elems->sec_chan_offs) { chan_type = NL80211_CHAN_HT20; } else { - switch (elems.sec_chan_offs->sec_chan_offs) { + switch (elems->sec_chan_offs->sec_chan_offs) { case IEEE80211_HT_PARAM_CHA_SEC_ABOVE: chan_type = NL80211_CHAN_HT40PLUS; break; @@ -1865,7 +1875,8 @@ ieee80211_process_tdls_channel_switch_req(struct ieee80211_sub_if_data *sdata, if (!cfg80211_reg_can_beacon_relax(sdata->local->hw.wiphy, &chandef, sdata->wdev.iftype)) { tdls_dbg(sdata, "TDLS chan switch to forbidden channel\n"); - return -EINVAL; + ret = -EINVAL; + goto free; } mutex_lock(&local->sta_mtx); @@ -1881,7 +1892,7 @@ ieee80211_process_tdls_channel_switch_req(struct ieee80211_sub_if_data *sdata, /* validate the initiator is set correctly */ local_initiator = - !memcmp(elems.lnk_id->init_sta, sdata->vif.addr, ETH_ALEN); + !memcmp(elems->lnk_id->init_sta, sdata->vif.addr, ETH_ALEN); if (local_initiator == sta->sta.tdls_initiator) { tdls_dbg(sdata, "TDLS chan switch invalid lnk-id initiator\n"); ret = -EINVAL; @@ -1889,16 +1900,16 @@ ieee80211_process_tdls_channel_switch_req(struct ieee80211_sub_if_data *sdata, } /* peer should have known better */ - if (!sta->sta.ht_cap.ht_supported && elems.sec_chan_offs && - elems.sec_chan_offs->sec_chan_offs) { + if (!sta->sta.ht_cap.ht_supported && elems->sec_chan_offs && + elems->sec_chan_offs->sec_chan_offs) { tdls_dbg(sdata, "TDLS chan switch - wide chan unsupported\n"); ret = -ENOTSUPP; goto out; } params.chandef = &chandef; - params.switch_time = le16_to_cpu(elems.ch_sw_timing->switch_time); - params.switch_timeout = le16_to_cpu(elems.ch_sw_timing->switch_timeout); + params.switch_time = le16_to_cpu(elems->ch_sw_timing->switch_time); + params.switch_timeout = le16_to_cpu(elems->ch_sw_timing->switch_timeout); params.tmpl_skb = ieee80211_tdls_ch_sw_resp_tmpl_get(sta, @@ -1917,6 +1928,8 @@ ieee80211_process_tdls_channel_switch_req(struct ieee80211_sub_if_data *sdata, out: mutex_unlock(&local->sta_mtx); dev_kfree_skb_any(params.tmpl_skb); +free: + kfree(elems); return ret; } diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 8921088a5df6..a756a197c770 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -146,7 +146,8 @@ static __le16 ieee80211_duration(struct ieee80211_tx_data *tx, rate = DIV_ROUND_UP(r->bitrate, 1 << shift); switch (sband->band) { - case NL80211_BAND_2GHZ: { + case NL80211_BAND_2GHZ: + case NL80211_BAND_LC: { u32 flag; if (tx->sdata->flags & IEEE80211_SDATA_OPERATING_GMODE) flag = IEEE80211_RATE_MANDATORY_G; @@ -4991,6 +4992,115 @@ static int ieee80211_beacon_protect(struct sk_buff *skb, return 0; } +static void +ieee80211_beacon_get_finish(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + struct ieee80211_mutable_offsets *offs, + struct beacon_data *beacon, + struct sk_buff *skb, + struct ieee80211_chanctx_conf *chanctx_conf, + u16 csa_off_base) +{ + struct ieee80211_local *local = hw_to_local(hw); + struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); + struct ieee80211_tx_info *info; + enum nl80211_band band; + struct ieee80211_tx_rate_control txrc; + + /* CSA offsets */ + if (offs && beacon) { + u16 i; + + for (i = 0; i < IEEE80211_MAX_CNTDWN_COUNTERS_NUM; i++) { + u16 csa_off = beacon->cntdwn_counter_offsets[i]; + + if (!csa_off) + continue; + + offs->cntdwn_counter_offs[i] = csa_off_base + csa_off; + } + } + + band = chanctx_conf->def.chan->band; + info = IEEE80211_SKB_CB(skb); + info->flags |= IEEE80211_TX_INTFL_DONT_ENCRYPT; + info->flags |= IEEE80211_TX_CTL_NO_ACK; + info->band = band; + + memset(&txrc, 0, sizeof(txrc)); + txrc.hw = hw; + txrc.sband = local->hw.wiphy->bands[band]; + txrc.bss_conf = &sdata->vif.bss_conf; + txrc.skb = skb; + txrc.reported_rate.idx = -1; + if (sdata->beacon_rate_set && sdata->beacon_rateidx_mask[band]) + txrc.rate_idx_mask = sdata->beacon_rateidx_mask[band]; + else + txrc.rate_idx_mask = sdata->rc_rateidx_mask[band]; + txrc.bss = true; + rate_control_get_rate(sdata, NULL, &txrc); + + info->control.vif = vif; + info->flags |= IEEE80211_TX_CTL_CLEAR_PS_FILT | + IEEE80211_TX_CTL_ASSIGN_SEQ | + IEEE80211_TX_CTL_FIRST_FRAGMENT; +} + +static struct sk_buff * +ieee80211_beacon_get_ap(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + struct ieee80211_mutable_offsets *offs, + bool is_template, + struct beacon_data *beacon, + struct ieee80211_chanctx_conf *chanctx_conf) +{ + struct ieee80211_local *local = hw_to_local(hw); + struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); + struct ieee80211_if_ap *ap = &sdata->u.ap; + struct sk_buff *skb = NULL; + u16 csa_off_base = 0; + + if (beacon->cntdwn_counter_offsets[0]) { + if (!is_template) + ieee80211_beacon_update_cntdwn(vif); + + ieee80211_set_beacon_cntdwn(sdata, beacon); + } + + /* headroom, head length, + * tail length and maximum TIM length + */ + skb = dev_alloc_skb(local->tx_headroom + beacon->head_len + + beacon->tail_len + 256 + + local->hw.extra_beacon_tailroom); + if (!skb) + return NULL; + + skb_reserve(skb, local->tx_headroom); + skb_put_data(skb, beacon->head, beacon->head_len); + + ieee80211_beacon_add_tim(sdata, &ap->ps, skb, is_template); + + if (offs) { + offs->tim_offset = beacon->head_len; + offs->tim_length = skb->len - beacon->head_len; + offs->cntdwn_counter_offs[0] = beacon->cntdwn_counter_offsets[0]; + + /* for AP the csa offsets are from tail */ + csa_off_base = skb->len; + } + + if (beacon->tail) + skb_put_data(skb, beacon->tail, beacon->tail_len); + + if (ieee80211_beacon_protect(skb, local, sdata) < 0) + return NULL; + + ieee80211_beacon_get_finish(hw, vif, offs, beacon, skb, chanctx_conf, + csa_off_base); + return skb; +} + static struct sk_buff * __ieee80211_beacon_get(struct ieee80211_hw *hw, struct ieee80211_vif *vif, @@ -5000,12 +5110,8 @@ __ieee80211_beacon_get(struct ieee80211_hw *hw, struct ieee80211_local *local = hw_to_local(hw); struct beacon_data *beacon = NULL; struct sk_buff *skb = NULL; - struct ieee80211_tx_info *info; struct ieee80211_sub_if_data *sdata = NULL; - enum nl80211_band band; - struct ieee80211_tx_rate_control txrc; struct ieee80211_chanctx_conf *chanctx_conf; - int csa_off_base = 0; rcu_read_lock(); @@ -5022,48 +5128,11 @@ __ieee80211_beacon_get(struct ieee80211_hw *hw, struct ieee80211_if_ap *ap = &sdata->u.ap; beacon = rcu_dereference(ap->beacon); - if (beacon) { - if (beacon->cntdwn_counter_offsets[0]) { - if (!is_template) - ieee80211_beacon_update_cntdwn(vif); - - ieee80211_set_beacon_cntdwn(sdata, beacon); - } - - /* - * headroom, head length, - * tail length and maximum TIM length - */ - skb = dev_alloc_skb(local->tx_headroom + - beacon->head_len + - beacon->tail_len + 256 + - local->hw.extra_beacon_tailroom); - if (!skb) - goto out; - - skb_reserve(skb, local->tx_headroom); - skb_put_data(skb, beacon->head, beacon->head_len); - - ieee80211_beacon_add_tim(sdata, &ap->ps, skb, - is_template); - - if (offs) { - offs->tim_offset = beacon->head_len; - offs->tim_length = skb->len - beacon->head_len; - offs->cntdwn_counter_offs[0] = beacon->cntdwn_counter_offsets[0]; - - /* for AP the csa offsets are from tail */ - csa_off_base = skb->len; - } - - if (beacon->tail) - skb_put_data(skb, beacon->tail, - beacon->tail_len); - - if (ieee80211_beacon_protect(skb, local, sdata) < 0) - goto out; - } else + if (!beacon) goto out; + + skb = ieee80211_beacon_get_ap(hw, vif, offs, is_template, + beacon, chanctx_conf); } else if (sdata->vif.type == NL80211_IFTYPE_ADHOC) { struct ieee80211_if_ibss *ifibss = &sdata->u.ibss; struct ieee80211_hdr *hdr; @@ -5089,6 +5158,9 @@ __ieee80211_beacon_get(struct ieee80211_hw *hw, hdr = (struct ieee80211_hdr *) skb->data; hdr->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_BEACON); + + ieee80211_beacon_get_finish(hw, vif, offs, beacon, skb, + chanctx_conf, 0); } else if (ieee80211_vif_is_mesh(&sdata->vif)) { struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; @@ -5128,51 +5200,13 @@ __ieee80211_beacon_get(struct ieee80211_hw *hw, } skb_put_data(skb, beacon->tail, beacon->tail_len); + ieee80211_beacon_get_finish(hw, vif, offs, beacon, skb, + chanctx_conf, 0); } else { WARN_ON(1); goto out; } - /* CSA offsets */ - if (offs && beacon) { - int i; - - for (i = 0; i < IEEE80211_MAX_CNTDWN_COUNTERS_NUM; i++) { - u16 csa_off = beacon->cntdwn_counter_offsets[i]; - - if (!csa_off) - continue; - - offs->cntdwn_counter_offs[i] = csa_off_base + csa_off; - } - } - - band = chanctx_conf->def.chan->band; - - info = IEEE80211_SKB_CB(skb); - - info->flags |= IEEE80211_TX_INTFL_DONT_ENCRYPT; - info->flags |= IEEE80211_TX_CTL_NO_ACK; - info->band = band; - - memset(&txrc, 0, sizeof(txrc)); - txrc.hw = hw; - txrc.sband = local->hw.wiphy->bands[band]; - txrc.bss_conf = &sdata->vif.bss_conf; - txrc.skb = skb; - txrc.reported_rate.idx = -1; - if (sdata->beacon_rate_set && sdata->beacon_rateidx_mask[band]) - txrc.rate_idx_mask = sdata->beacon_rateidx_mask[band]; - else - txrc.rate_idx_mask = sdata->rc_rateidx_mask[band]; - txrc.bss = true; - rate_control_get_rate(sdata, NULL, &txrc); - - info->control.vif = vif; - - info->flags |= IEEE80211_TX_CTL_CLEAR_PS_FILT | - IEEE80211_TX_CTL_ASSIGN_SEQ | - IEEE80211_TX_CTL_FIRST_FRAGMENT; out: rcu_read_unlock(); return skb; diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 49cb96d25169..39fa2a50385d 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -1112,10 +1112,6 @@ _ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action, } else elem_parse_failed = true; break; - case WLAN_EID_CHALLENGE: - elems->challenge = pos; - elems->challenge_len = elen; - break; case WLAN_EID_VENDOR_SPECIFIC: if (elen >= 4 && pos[0] == 0x00 && pos[1] == 0x50 && pos[2] == 0xf2) { @@ -1395,8 +1391,8 @@ _ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action, static size_t ieee802_11_find_bssid_profile(const u8 *start, size_t len, struct ieee802_11_elems *elems, - u8 *transmitter_bssid, - u8 *bss_bssid, + const u8 *transmitter_bssid, + const u8 *bss_bssid, u8 *nontransmitted_profile) { const struct element *elem, *sub; @@ -1461,16 +1457,20 @@ static size_t ieee802_11_find_bssid_profile(const u8 *start, size_t len, return found ? profile_len : 0; } -u32 ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action, - struct ieee802_11_elems *elems, - u64 filter, u32 crc, u8 *transmitter_bssid, - u8 *bss_bssid) +struct ieee802_11_elems *ieee802_11_parse_elems_crc(const u8 *start, size_t len, + bool action, u64 filter, + u32 crc, + const u8 *transmitter_bssid, + const u8 *bss_bssid) { + struct ieee802_11_elems *elems; const struct element *non_inherit = NULL; u8 *nontransmitted_profile; int nontransmitted_profile_len = 0; - memset(elems, 0, sizeof(*elems)); + elems = kzalloc(sizeof(*elems), GFP_ATOMIC); + if (!elems) + return NULL; elems->ie_start = start; elems->total_len = len; @@ -1516,7 +1516,9 @@ u32 ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action, kfree(nontransmitted_profile); - return crc; + elems->crc = crc; + + return elems; } void ieee80211_regulatory_limit_wmm_params(struct ieee80211_sub_if_data *sdata, @@ -3383,6 +3385,7 @@ bool ieee80211_chandef_he_6ghz_oper(struct ieee80211_sub_if_data *sdata, const struct ieee80211_sta_he_cap *he_cap; struct cfg80211_chan_def he_chandef = *chandef; const struct ieee80211_he_6ghz_oper *he_6ghz_oper; + struct ieee80211_bss_conf *bss_conf = &sdata->vif.bss_conf; bool support_80_80, support_160; u8 he_phy_cap; u32 freq; @@ -3426,6 +3429,19 @@ bool ieee80211_chandef_he_6ghz_oper(struct ieee80211_sub_if_data *sdata, NL80211_BAND_6GHZ); he_chandef.chan = ieee80211_get_channel(sdata->local->hw.wiphy, freq); + switch (u8_get_bits(he_6ghz_oper->control, + IEEE80211_HE_6GHZ_OPER_CTRL_REG_INFO)) { + case IEEE80211_6GHZ_CTRL_REG_LPI_AP: + bss_conf->power_type = IEEE80211_REG_LPI_AP; + break; + case IEEE80211_6GHZ_CTRL_REG_SP_AP: + bss_conf->power_type = IEEE80211_REG_SP_AP; + break; + default: + bss_conf->power_type = IEEE80211_REG_UNSET_AP; + break; + } + switch (u8_get_bits(he_6ghz_oper->control, IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH)) { case IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_20MHZ: diff --git a/net/mac802154/iface.c b/net/mac802154/iface.c index 323d3d2d986f..500ed1b81250 100644 --- a/net/mac802154/iface.c +++ b/net/mac802154/iface.c @@ -129,15 +129,14 @@ static int mac802154_wpan_mac_addr(struct net_device *dev, void *p) if (!ieee802154_is_valid_extended_unicast_addr(extended_addr)) return -EINVAL; - memcpy(dev->dev_addr, addr->sa_data, dev->addr_len); + dev_addr_set(dev, addr->sa_data); sdata->wpan_dev.extended_addr = extended_addr; /* update lowpan interface mac address when * wpan mac has been changed */ if (sdata->wpan_dev.lowpan_dev) - memcpy(sdata->wpan_dev.lowpan_dev->dev_addr, dev->dev_addr, - dev->addr_len); + dev_addr_set(sdata->wpan_dev.lowpan_dev, dev->dev_addr); return mac802154_wpan_update_llsec(dev); } @@ -615,6 +614,7 @@ ieee802154_if_add(struct ieee802154_local *local, const char *name, unsigned char name_assign_type, enum nl802154_iftype type, __le64 extended_addr) { + u8 addr[IEEE802154_EXTENDED_ADDR_LEN]; struct net_device *ndev = NULL; struct ieee802154_sub_if_data *sdata = NULL; int ret; @@ -638,11 +638,12 @@ ieee802154_if_add(struct ieee802154_local *local, const char *name, switch (type) { case NL802154_IFTYPE_NODE: ndev->type = ARPHRD_IEEE802154; - if (ieee802154_is_valid_extended_unicast_addr(extended_addr)) - ieee802154_le64_to_be64(ndev->dev_addr, &extended_addr); - else - memcpy(ndev->dev_addr, ndev->perm_addr, - IEEE802154_EXTENDED_ADDR_LEN); + if (ieee802154_is_valid_extended_unicast_addr(extended_addr)) { + ieee802154_le64_to_be64(addr, &extended_addr); + dev_addr_set(ndev, addr); + } else { + dev_addr_set(ndev, ndev->perm_addr); + } break; case NL802154_IFTYPE_MONITOR: ndev->type = ARPHRD_IEEE802154_MONITOR; diff --git a/net/mctp/route.c b/net/mctp/route.c index 04781459b2be..82fb5ae524f6 100644 --- a/net/mctp/route.c +++ b/net/mctp/route.c @@ -372,6 +372,7 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb) trace_mctp_key_acquire(key); /* we don't need to release key->lock on exit */ + mctp_key_unref(key); key = NULL; } else { @@ -584,6 +585,9 @@ static int mctp_alloc_local_tag(struct mctp_sock *msk, trace_mctp_key_acquire(key); *tagp = key->tag; + /* done with the key in this scope */ + mctp_key_unref(key); + key = NULL; rc = 0; } diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 050eea231528..7b96be1e9f14 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -654,9 +654,9 @@ void mptcp_pm_nl_addr_send_ack(struct mptcp_sock *msk) } } -int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk, - struct mptcp_addr_info *addr, - u8 bkup) +static int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk, + struct mptcp_addr_info *addr, + u8 bkup) { struct mptcp_subflow_context *subflow; @@ -2052,6 +2052,9 @@ static int __net_init pm_nl_init_net(struct net *net) struct pm_nl_pernet *pernet = net_generic(net, pm_nl_pernet_id); INIT_LIST_HEAD_RCU(&pernet->local_addr_list); + + /* Cit. 2 subflows ought to be enough for anybody. */ + pernet->subflows_max = 2; pernet->next_id = 1; pernet->stale_loss_cnt = 4; spin_lock_init(&pernet->lock); diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 7379ab580a7e..284fdcec067e 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -736,9 +736,6 @@ void mptcp_pm_nl_addr_send_ack(struct mptcp_sock *msk); void mptcp_pm_rm_addr_received(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list); void mptcp_pm_mp_prio_received(struct sock *sk, u8 bkup); -int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk, - struct mptcp_addr_info *addr, - u8 bkup); void mptcp_pm_mp_fail_received(struct sock *sk, u64 fail_seq); void mptcp_pm_free_anno_list(struct mptcp_sock *msk); bool mptcp_pm_sport_in_anno_list(struct mptcp_sock *msk, const struct sock *sk); diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index 8137cc3a4296..0f1e661c2032 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -861,6 +861,9 @@ static void mptcp_get_sub_addrs(const struct sock *sk, struct mptcp_subflow_addr } else if (sk->sk_family == AF_INET6) { const struct ipv6_pinfo *np = inet6_sk(sk); + if (WARN_ON_ONCE(!np)) + return; + a->sin6_local.sin6_family = AF_INET6; a->sin6_local.sin6_port = inet->inet_sport; diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 707bb64e5959..b40b94a4fb8d 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -10,6 +10,17 @@ config NETFILTER_INGRESS This allows you to classify packets from ingress using the Netfilter infrastructure. +config NETFILTER_EGRESS + bool "Netfilter egress support" + default y + select NET_EGRESS + help + This allows you to classify packets before transmission using the + Netfilter infrastructure. + +config NETFILTER_SKIP_EGRESS + def_bool NETFILTER_EGRESS && (NET_CLS_ACT || IFB) + config NETFILTER_NETLINK tristate diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 63d032191e62..6dec9cd395f1 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -316,6 +316,12 @@ nf_hook_entry_head(struct net *net, int pf, unsigned int hooknum, if (dev && dev_net(dev) == net) return &dev->nf_hooks_ingress; } +#endif +#ifdef CONFIG_NETFILTER_EGRESS + if (hooknum == NF_NETDEV_EGRESS) { + if (dev && dev_net(dev) == net) + return &dev->nf_hooks_egress; + } #endif WARN_ON_ONCE(1); return NULL; @@ -335,7 +341,8 @@ static int nf_ingress_check(struct net *net, const struct nf_hook_ops *reg, return 0; } -static inline bool nf_ingress_hook(const struct nf_hook_ops *reg, int pf) +static inline bool __maybe_unused nf_ingress_hook(const struct nf_hook_ops *reg, + int pf) { if ((pf == NFPROTO_NETDEV && reg->hooknum == NF_NETDEV_INGRESS) || (pf == NFPROTO_INET && reg->hooknum == NF_INET_INGRESS)) @@ -344,6 +351,12 @@ static inline bool nf_ingress_hook(const struct nf_hook_ops *reg, int pf) return false; } +static inline bool __maybe_unused nf_egress_hook(const struct nf_hook_ops *reg, + int pf) +{ + return pf == NFPROTO_NETDEV && reg->hooknum == NF_NETDEV_EGRESS; +} + static void nf_static_key_inc(const struct nf_hook_ops *reg, int pf) { #ifdef CONFIG_JUMP_LABEL @@ -383,9 +396,18 @@ static int __nf_register_net_hook(struct net *net, int pf, switch (pf) { case NFPROTO_NETDEV: - err = nf_ingress_check(net, reg, NF_NETDEV_INGRESS); - if (err < 0) - return err; +#ifndef CONFIG_NETFILTER_INGRESS + if (reg->hooknum == NF_NETDEV_INGRESS) + return -EOPNOTSUPP; +#endif +#ifndef CONFIG_NETFILTER_EGRESS + if (reg->hooknum == NF_NETDEV_EGRESS) + return -EOPNOTSUPP; +#endif + if ((reg->hooknum != NF_NETDEV_INGRESS && + reg->hooknum != NF_NETDEV_EGRESS) || + !reg->dev || dev_net(reg->dev) != net) + return -EINVAL; break; case NFPROTO_INET: if (reg->hooknum != NF_INET_INGRESS) @@ -417,6 +439,10 @@ static int __nf_register_net_hook(struct net *net, int pf, #ifdef CONFIG_NETFILTER_INGRESS if (nf_ingress_hook(reg, pf)) net_inc_ingress_queue(); +#endif +#ifdef CONFIG_NETFILTER_EGRESS + if (nf_egress_hook(reg, pf)) + net_inc_egress_queue(); #endif nf_static_key_inc(reg, pf); @@ -474,6 +500,10 @@ static void __nf_unregister_net_hook(struct net *net, int pf, #ifdef CONFIG_NETFILTER_INGRESS if (nf_ingress_hook(reg, pf)) net_dec_ingress_queue(); +#endif +#ifdef CONFIG_NETFILTER_EGRESS + if (nf_egress_hook(reg, pf)) + net_dec_egress_queue(); #endif nf_static_key_dec(reg, pf); } else { diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 128690c512df..e93c937a8bf0 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1330,12 +1330,15 @@ drop: * Check if outgoing packet belongs to the established ip_vs_conn. */ static unsigned int -ip_vs_out(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int af) +ip_vs_out_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { + struct netns_ipvs *ipvs = net_ipvs(state->net); + unsigned int hooknum = state->hook; struct ip_vs_iphdr iph; struct ip_vs_protocol *pp; struct ip_vs_proto_data *pd; struct ip_vs_conn *cp; + int af = state->pf; struct sock *sk; EnterFunction(11); @@ -1468,56 +1471,6 @@ ip_vs_out(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, in return NF_ACCEPT; } -/* - * It is hooked at the NF_INET_FORWARD and NF_INET_LOCAL_IN chain, - * used only for VS/NAT. - * Check if packet is reply for established ip_vs_conn. - */ -static unsigned int -ip_vs_reply4(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state) -{ - return ip_vs_out(net_ipvs(state->net), state->hook, skb, AF_INET); -} - -/* - * It is hooked at the NF_INET_LOCAL_OUT chain, used only for VS/NAT. - * Check if packet is reply for established ip_vs_conn. - */ -static unsigned int -ip_vs_local_reply4(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state) -{ - return ip_vs_out(net_ipvs(state->net), state->hook, skb, AF_INET); -} - -#ifdef CONFIG_IP_VS_IPV6 - -/* - * It is hooked at the NF_INET_FORWARD and NF_INET_LOCAL_IN chain, - * used only for VS/NAT. - * Check if packet is reply for established ip_vs_conn. - */ -static unsigned int -ip_vs_reply6(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state) -{ - return ip_vs_out(net_ipvs(state->net), state->hook, skb, AF_INET6); -} - -/* - * It is hooked at the NF_INET_LOCAL_OUT chain, used only for VS/NAT. - * Check if packet is reply for established ip_vs_conn. - */ -static unsigned int -ip_vs_local_reply6(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state) -{ - return ip_vs_out(net_ipvs(state->net), state->hook, skb, AF_INET6); -} - -#endif - static unsigned int ip_vs_try_to_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, @@ -1957,8 +1910,10 @@ out: * and send it on its way... */ static unsigned int -ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int af) +ip_vs_in_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { + struct netns_ipvs *ipvs = net_ipvs(state->net); + unsigned int hooknum = state->hook; struct ip_vs_iphdr iph; struct ip_vs_protocol *pp; struct ip_vs_proto_data *pd; @@ -1966,6 +1921,7 @@ ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int int ret, pkts; int conn_reuse_mode; struct sock *sk; + int af = state->pf; /* Already marked as IPVS request or reply? */ if (skb->ipvs_property) @@ -2137,55 +2093,6 @@ ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int return ret; } -/* - * AF_INET handler in NF_INET_LOCAL_IN chain - * Schedule and forward packets from remote clients - */ -static unsigned int -ip_vs_remote_request4(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state) -{ - return ip_vs_in(net_ipvs(state->net), state->hook, skb, AF_INET); -} - -/* - * AF_INET handler in NF_INET_LOCAL_OUT chain - * Schedule and forward packets from local clients - */ -static unsigned int -ip_vs_local_request4(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state) -{ - return ip_vs_in(net_ipvs(state->net), state->hook, skb, AF_INET); -} - -#ifdef CONFIG_IP_VS_IPV6 - -/* - * AF_INET6 handler in NF_INET_LOCAL_IN chain - * Schedule and forward packets from remote clients - */ -static unsigned int -ip_vs_remote_request6(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state) -{ - return ip_vs_in(net_ipvs(state->net), state->hook, skb, AF_INET6); -} - -/* - * AF_INET6 handler in NF_INET_LOCAL_OUT chain - * Schedule and forward packets from local clients - */ -static unsigned int -ip_vs_local_request6(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state) -{ - return ip_vs_in(net_ipvs(state->net), state->hook, skb, AF_INET6); -} - -#endif - - /* * It is hooked at the NF_INET_FORWARD chain, in order to catch ICMP * related packets destined for 0.0.0.0/0. @@ -2199,45 +2106,36 @@ static unsigned int ip_vs_forward_icmp(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - int r; struct netns_ipvs *ipvs = net_ipvs(state->net); - - if (ip_hdr(skb)->protocol != IPPROTO_ICMP) - return NF_ACCEPT; + int r; /* ipvs enabled in this netns ? */ if (unlikely(sysctl_backup_only(ipvs) || !ipvs->enable)) return NF_ACCEPT; + if (state->pf == NFPROTO_IPV4) { + if (ip_hdr(skb)->protocol != IPPROTO_ICMP) + return NF_ACCEPT; +#ifdef CONFIG_IP_VS_IPV6 + } else { + struct ip_vs_iphdr iphdr; + + ip_vs_fill_iph_skb(AF_INET6, skb, false, &iphdr); + + if (iphdr.protocol != IPPROTO_ICMPV6) + return NF_ACCEPT; + + return ip_vs_in_icmp_v6(ipvs, skb, &r, state->hook, &iphdr); +#endif + } + return ip_vs_in_icmp(ipvs, skb, &r, state->hook); } -#ifdef CONFIG_IP_VS_IPV6 -static unsigned int -ip_vs_forward_icmp_v6(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state) -{ - int r; - struct netns_ipvs *ipvs = net_ipvs(state->net); - struct ip_vs_iphdr iphdr; - - ip_vs_fill_iph_skb(AF_INET6, skb, false, &iphdr); - if (iphdr.protocol != IPPROTO_ICMPV6) - return NF_ACCEPT; - - /* ipvs enabled in this netns ? */ - if (unlikely(sysctl_backup_only(ipvs) || !ipvs->enable)) - return NF_ACCEPT; - - return ip_vs_in_icmp_v6(ipvs, skb, &r, state->hook, &iphdr); -} -#endif - - static const struct nf_hook_ops ip_vs_ops4[] = { /* After packet filtering, change source only for VS/NAT */ { - .hook = ip_vs_reply4, + .hook = ip_vs_out_hook, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP_PRI_NAT_SRC - 2, @@ -2246,21 +2144,21 @@ static const struct nf_hook_ops ip_vs_ops4[] = { * or VS/NAT(change destination), so that filtering rules can be * applied to IPVS. */ { - .hook = ip_vs_remote_request4, + .hook = ip_vs_in_hook, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP_PRI_NAT_SRC - 1, }, /* Before ip_vs_in, change source only for VS/NAT */ { - .hook = ip_vs_local_reply4, + .hook = ip_vs_out_hook, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP_PRI_NAT_DST + 1, }, /* After mangle, schedule and forward local requests */ { - .hook = ip_vs_local_request4, + .hook = ip_vs_in_hook, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP_PRI_NAT_DST + 2, @@ -2275,7 +2173,7 @@ static const struct nf_hook_ops ip_vs_ops4[] = { }, /* After packet filtering, change source only for VS/NAT */ { - .hook = ip_vs_reply4, + .hook = ip_vs_out_hook, .pf = NFPROTO_IPV4, .hooknum = NF_INET_FORWARD, .priority = 100, @@ -2286,7 +2184,7 @@ static const struct nf_hook_ops ip_vs_ops4[] = { static const struct nf_hook_ops ip_vs_ops6[] = { /* After packet filtering, change source only for VS/NAT */ { - .hook = ip_vs_reply6, + .hook = ip_vs_out_hook, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP6_PRI_NAT_SRC - 2, @@ -2295,21 +2193,21 @@ static const struct nf_hook_ops ip_vs_ops6[] = { * or VS/NAT(change destination), so that filtering rules can be * applied to IPVS. */ { - .hook = ip_vs_remote_request6, + .hook = ip_vs_in_hook, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP6_PRI_NAT_SRC - 1, }, /* Before ip_vs_in, change source only for VS/NAT */ { - .hook = ip_vs_local_reply6, + .hook = ip_vs_out_hook, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP6_PRI_NAT_DST + 1, }, /* After mangle, schedule and forward local requests */ { - .hook = ip_vs_local_request6, + .hook = ip_vs_in_hook, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP6_PRI_NAT_DST + 2, @@ -2317,14 +2215,14 @@ static const struct nf_hook_ops ip_vs_ops6[] = { /* After packet filtering (but before ip_vs_out_icmp), catch icmp * destined for 0.0.0.0/0, which is for incoming IPVS connections */ { - .hook = ip_vs_forward_icmp_v6, + .hook = ip_vs_forward_icmp, .pf = NFPROTO_IPV6, .hooknum = NF_INET_FORWARD, .priority = 99, }, /* After packet filtering, change source only for VS/NAT */ { - .hook = ip_vs_reply6, + .hook = ip_vs_out_hook, .pf = NFPROTO_IPV6, .hooknum = NF_INET_FORWARD, .priority = 100, diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 29ec3ef63edc..e62b40bd349e 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -2017,6 +2017,12 @@ static struct ctl_table vs_vars[] = { .mode = 0644, .proc_handler = proc_dointvec, }, + { + .procname = "run_estimation", + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, #ifdef CONFIG_IP_VS_DEBUG { .procname = "debug_level", @@ -4090,6 +4096,8 @@ static int __net_init ip_vs_control_net_init_sysctl(struct netns_ipvs *ipvs) tbl[idx++].data = &ipvs->sysctl_conn_reuse_mode; tbl[idx++].data = &ipvs->sysctl_schedule_icmp; tbl[idx++].data = &ipvs->sysctl_ignore_tunneled; + ipvs->sysctl_run_estimation = 1; + tbl[idx++].data = &ipvs->sysctl_run_estimation; #ifdef CONFIG_IP_VS_DEBUG /* Global sysctls must be ro in non-init netns */ if (!net_eq(net, &init_net)) diff --git a/net/netfilter/ipvs/ip_vs_est.c b/net/netfilter/ipvs/ip_vs_est.c index 05b8112ffb37..9a1a7af6a186 100644 --- a/net/netfilter/ipvs/ip_vs_est.c +++ b/net/netfilter/ipvs/ip_vs_est.c @@ -100,6 +100,9 @@ static void estimation_timer(struct timer_list *t) u64 rate; struct netns_ipvs *ipvs = from_timer(ipvs, t, est_timer); + if (!sysctl_run_estimation(ipvs)) + goto skip; + spin_lock(&ipvs->est_lock); list_for_each_entry(e, &ipvs->est_list, list) { s = container_of(e, struct ip_vs_stats, est); @@ -131,6 +134,8 @@ static void estimation_timer(struct timer_list *t) spin_unlock(&s->lock); } spin_unlock(&ipvs->est_lock); + +skip: mod_timer(&ipvs->est_timer, jiffies + 2*HZ); } diff --git a/net/netfilter/nfnetlink_hook.c b/net/netfilter/nfnetlink_hook.c index f554e2ea32ee..d5c719c9e36c 100644 --- a/net/netfilter/nfnetlink_hook.c +++ b/net/netfilter/nfnetlink_hook.c @@ -185,7 +185,7 @@ static const struct nf_hook_entries * nfnl_hook_entries_head(u8 pf, unsigned int hook, struct net *net, const char *dev) { const struct nf_hook_entries *hook_head = NULL; -#ifdef CONFIG_NETFILTER_INGRESS +#if defined(CONFIG_NETFILTER_INGRESS) || defined(CONFIG_NETFILTER_EGRESS) struct net_device *netdev; #endif @@ -221,9 +221,9 @@ nfnl_hook_entries_head(u8 pf, unsigned int hook, struct net *net, const char *de hook_head = rcu_dereference(net->nf.hooks_decnet[hook]); break; #endif -#ifdef CONFIG_NETFILTER_INGRESS +#if defined(CONFIG_NETFILTER_INGRESS) || defined(CONFIG_NETFILTER_EGRESS) case NFPROTO_NETDEV: - if (hook != NF_NETDEV_INGRESS) + if (hook >= NF_NETDEV_NUMHOOKS) return ERR_PTR(-EOPNOTSUPP); if (!dev) @@ -233,7 +233,15 @@ nfnl_hook_entries_head(u8 pf, unsigned int hook, struct net *net, const char *de if (!netdev) return ERR_PTR(-ENODEV); - return rcu_dereference(netdev->nf_hooks_ingress); +#ifdef CONFIG_NETFILTER_INGRESS + if (hook == NF_NETDEV_INGRESS) + return rcu_dereference(netdev->nf_hooks_ingress); +#endif +#ifdef CONFIG_NETFILTER_EGRESS + if (hook == NF_NETDEV_EGRESS) + return rcu_dereference(netdev->nf_hooks_egress); +#endif + fallthrough; #endif default: return ERR_PTR(-EPROTONOSUPPORT); diff --git a/net/netfilter/nft_chain_filter.c b/net/netfilter/nft_chain_filter.c index 3ced0eb6b7c3..c3563f0be269 100644 --- a/net/netfilter/nft_chain_filter.c +++ b/net/netfilter/nft_chain_filter.c @@ -310,9 +310,11 @@ static const struct nft_chain_type nft_chain_filter_netdev = { .name = "filter", .type = NFT_CHAIN_T_DEFAULT, .family = NFPROTO_NETDEV, - .hook_mask = (1 << NF_NETDEV_INGRESS), + .hook_mask = (1 << NF_NETDEV_INGRESS) | + (1 << NF_NETDEV_EGRESS), .hooks = { [NF_NETDEV_INGRESS] = nft_do_chain_netdev, + [NF_NETDEV_EGRESS] = nft_do_chain_netdev, }, }; diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c index 6ba3256fa844..87f3af4645d9 100644 --- a/net/netfilter/nft_dynset.c +++ b/net/netfilter/nft_dynset.c @@ -198,17 +198,8 @@ static int nft_dynset_init(const struct nft_ctx *ctx, return -EBUSY; priv->op = ntohl(nla_get_be32(tb[NFTA_DYNSET_OP])); - switch (priv->op) { - case NFT_DYNSET_OP_ADD: - case NFT_DYNSET_OP_DELETE: - break; - case NFT_DYNSET_OP_UPDATE: - if (!(set->flags & NFT_SET_TIMEOUT)) - return -EOPNOTSUPP; - break; - default: + if (priv->op > NFT_DYNSET_OP_DELETE) return -EOPNOTSUPP; - } timeout = 0; if (tb[NFTA_DYNSET_TIMEOUT] != NULL) { diff --git a/net/netfilter/xt_RATEEST.c b/net/netfilter/xt_RATEEST.c index 0d5c422f8745..8aec1b529364 100644 --- a/net/netfilter/xt_RATEEST.c +++ b/net/netfilter/xt_RATEEST.c @@ -94,11 +94,11 @@ static unsigned int xt_rateest_tg(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_rateest_target_info *info = par->targinfo; - struct gnet_stats_basic_packed *stats = &info->est->bstats; + struct gnet_stats_basic_sync *stats = &info->est->bstats; spin_lock_bh(&info->est->lock); - stats->bytes += skb->len; - stats->packets++; + u64_stats_add(&stats->bytes, skb->len); + u64_stats_inc(&stats->packets); spin_unlock_bh(&info->est->lock); return XT_CONTINUE; @@ -143,6 +143,7 @@ static int xt_rateest_tg_checkentry(const struct xt_tgchk_param *par) if (!est) goto err1; + gnet_stats_basic_sync_init(&est->bstats); strlcpy(est->name, info->name, sizeof(est->name)); spin_lock_init(&est->lock); est->refcnt = 1; diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index 6d16e1ab1a8a..775064cdd0ee 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -633,7 +633,7 @@ static int nr_connect(struct socket *sock, struct sockaddr *uaddr, struct sock *sk = sock->sk; struct nr_sock *nr = nr_sk(sk); struct sockaddr_ax25 *addr = (struct sockaddr_ax25 *)uaddr; - ax25_address *source = NULL; + const ax25_address *source = NULL; ax25_uid_assoc *user; struct net_device *dev; int err = 0; @@ -673,7 +673,7 @@ static int nr_connect(struct socket *sock, struct sockaddr *uaddr, err = -ENETUNREACH; goto out_release; } - source = (ax25_address *)dev->dev_addr; + source = (const ax25_address *)dev->dev_addr; user = ax25_findbyuid(current_euid()); if (user) { diff --git a/net/netrom/nr_dev.c b/net/netrom/nr_dev.c index 29e418c8c6c3..3aaac4a22b38 100644 --- a/net/netrom/nr_dev.c +++ b/net/netrom/nr_dev.c @@ -108,10 +108,10 @@ static int __must_check nr_set_mac_address(struct net_device *dev, void *addr) if (err) return err; - ax25_listen_release((ax25_address *)dev->dev_addr, NULL); + ax25_listen_release((const ax25_address *)dev->dev_addr, NULL); } - memcpy(dev->dev_addr, sa->sa_data, dev->addr_len); + dev_addr_set(dev, sa->sa_data); return 0; } @@ -120,7 +120,7 @@ static int nr_open(struct net_device *dev) { int err; - err = ax25_listen_register((ax25_address *)dev->dev_addr, NULL); + err = ax25_listen_register((const ax25_address *)dev->dev_addr, NULL); if (err) return err; @@ -131,7 +131,7 @@ static int nr_open(struct net_device *dev) static int nr_close(struct net_device *dev) { - ax25_listen_release((ax25_address *)dev->dev_addr, NULL); + ax25_listen_release((const ax25_address *)dev->dev_addr, NULL); netif_stop_queue(dev); return 0; } diff --git a/net/netrom/nr_route.c b/net/netrom/nr_route.c index ddd5cbd455e3..baea3cbd76ca 100644 --- a/net/netrom/nr_route.c +++ b/net/netrom/nr_route.c @@ -598,7 +598,7 @@ struct net_device *nr_dev_get(ax25_address *addr) rcu_read_lock(); for_each_netdev_rcu(&init_net, dev) { if ((dev->flags & IFF_UP) && dev->type == ARPHRD_NETROM && - ax25cmp(addr, (ax25_address *)dev->dev_addr) == 0) { + ax25cmp(addr, (const ax25_address *)dev->dev_addr) == 0) { dev_hold(dev); goto out; } @@ -825,7 +825,7 @@ int nr_route_frame(struct sk_buff *skb, ax25_cb *ax25) ax25s = nr_neigh->ax25; nr_neigh->ax25 = ax25_send_frame(skb, 256, - (ax25_address *)dev->dev_addr, + (const ax25_address *)dev->dev_addr, &nr_neigh->callsign, nr_neigh->digipeat, nr_neigh->dev); if (ax25s) diff --git a/net/nfc/hci/command.c b/net/nfc/hci/command.c index 3a89bd9b89fc..af6bacb3ba98 100644 --- a/net/nfc/hci/command.c +++ b/net/nfc/hci/command.c @@ -114,8 +114,6 @@ int nfc_hci_send_cmd(struct nfc_hci_dev *hdev, u8 gate, u8 cmd, { u8 pipe; - pr_debug("\n"); - pipe = hdev->gate2pipe[gate]; if (pipe == NFC_HCI_INVALID_PIPE) return -EADDRNOTAVAIL; @@ -130,8 +128,6 @@ int nfc_hci_send_cmd_async(struct nfc_hci_dev *hdev, u8 gate, u8 cmd, { u8 pipe; - pr_debug("\n"); - pipe = hdev->gate2pipe[gate]; if (pipe == NFC_HCI_INVALID_PIPE) return -EADDRNOTAVAIL; @@ -205,8 +201,6 @@ static int nfc_hci_open_pipe(struct nfc_hci_dev *hdev, u8 pipe) static int nfc_hci_close_pipe(struct nfc_hci_dev *hdev, u8 pipe) { - pr_debug("\n"); - return nfc_hci_execute_cmd(hdev, pipe, NFC_HCI_ANY_CLOSE_PIPE, NULL, 0, NULL); } @@ -242,8 +236,6 @@ static u8 nfc_hci_create_pipe(struct nfc_hci_dev *hdev, u8 dest_host, static int nfc_hci_delete_pipe(struct nfc_hci_dev *hdev, u8 pipe) { - pr_debug("\n"); - return nfc_hci_execute_cmd(hdev, NFC_HCI_ADMIN_PIPE, NFC_HCI_ADM_DELETE_PIPE, &pipe, 1, NULL); } @@ -256,8 +248,6 @@ static int nfc_hci_clear_all_pipes(struct nfc_hci_dev *hdev) /* TODO: Find out what the identity reference data is * and fill param with it. HCI spec 6.1.3.5 */ - pr_debug("\n"); - if (test_bit(NFC_HCI_QUIRK_SHORT_CLEAR, &hdev->quirks)) param_len = 0; @@ -271,8 +261,6 @@ int nfc_hci_disconnect_gate(struct nfc_hci_dev *hdev, u8 gate) int r; u8 pipe = hdev->gate2pipe[gate]; - pr_debug("\n"); - if (pipe == NFC_HCI_INVALID_PIPE) return -EADDRNOTAVAIL; @@ -296,8 +284,6 @@ int nfc_hci_disconnect_all_gates(struct nfc_hci_dev *hdev) { int r; - pr_debug("\n"); - r = nfc_hci_clear_all_pipes(hdev); if (r < 0) return r; @@ -314,8 +300,6 @@ int nfc_hci_connect_gate(struct nfc_hci_dev *hdev, u8 dest_host, u8 dest_gate, bool pipe_created = false; int r; - pr_debug("\n"); - if (pipe == NFC_HCI_DO_NOT_CREATE_PIPE) return 0; diff --git a/net/nfc/hci/llc_shdlc.c b/net/nfc/hci/llc_shdlc.c index 71e10347e6a9..e90f70385813 100644 --- a/net/nfc/hci/llc_shdlc.c +++ b/net/nfc/hci/llc_shdlc.c @@ -363,8 +363,6 @@ static int llc_shdlc_connect_initiate(const struct llc_shdlc *shdlc) { struct sk_buff *skb; - pr_debug("\n"); - skb = llc_shdlc_alloc_skb(shdlc, 2); if (skb == NULL) return -ENOMEM; @@ -379,8 +377,6 @@ static int llc_shdlc_connect_send_ua(const struct llc_shdlc *shdlc) { struct sk_buff *skb; - pr_debug("\n"); - skb = llc_shdlc_alloc_skb(shdlc, 0); if (skb == NULL) return -ENOMEM; @@ -570,8 +566,6 @@ static void llc_shdlc_connect_timeout(struct timer_list *t) { struct llc_shdlc *shdlc = from_timer(shdlc, t, connect_timer); - pr_debug("\n"); - schedule_work(&shdlc->sm_work); } @@ -598,8 +592,6 @@ static void llc_shdlc_sm_work(struct work_struct *work) struct llc_shdlc *shdlc = container_of(work, struct llc_shdlc, sm_work); int r; - pr_debug("\n"); - mutex_lock(&shdlc->state_mutex); switch (shdlc->state) { @@ -681,8 +673,6 @@ static int llc_shdlc_connect(struct llc_shdlc *shdlc) { DECLARE_WAIT_QUEUE_HEAD_ONSTACK(connect_wq); - pr_debug("\n"); - mutex_lock(&shdlc->state_mutex); shdlc->state = SHDLC_CONNECTING; @@ -701,8 +691,6 @@ static int llc_shdlc_connect(struct llc_shdlc *shdlc) static void llc_shdlc_disconnect(struct llc_shdlc *shdlc) { - pr_debug("\n"); - mutex_lock(&shdlc->state_mutex); shdlc->state = SHDLC_DISCONNECTED; diff --git a/net/nfc/llcp_commands.c b/net/nfc/llcp_commands.c index 3c4172a5aeb5..41e3a20c8935 100644 --- a/net/nfc/llcp_commands.c +++ b/net/nfc/llcp_commands.c @@ -337,8 +337,6 @@ int nfc_llcp_send_disconnect(struct nfc_llcp_sock *sock) struct nfc_dev *dev; struct nfc_llcp_local *local; - pr_debug("Sending DISC\n"); - local = sock->local; if (local == NULL) return -ENODEV; @@ -362,8 +360,6 @@ int nfc_llcp_send_symm(struct nfc_dev *dev) struct nfc_llcp_local *local; u16 size = 0; - pr_debug("Sending SYMM\n"); - local = nfc_llcp_find_local(dev); if (local == NULL) return -ENODEV; @@ -399,8 +395,6 @@ int nfc_llcp_send_connect(struct nfc_llcp_sock *sock) u16 size = 0; __be16 miux; - pr_debug("Sending CONNECT\n"); - local = sock->local; if (local == NULL) return -ENODEV; @@ -475,8 +469,6 @@ int nfc_llcp_send_cc(struct nfc_llcp_sock *sock) u16 size = 0; __be16 miux; - pr_debug("Sending CC\n"); - local = sock->local; if (local == NULL) return -ENODEV; diff --git a/net/nfc/llcp_core.c b/net/nfc/llcp_core.c index eaeb2b1cfa6a..5ad5157aa9c5 100644 --- a/net/nfc/llcp_core.c +++ b/net/nfc/llcp_core.c @@ -45,8 +45,6 @@ static void nfc_llcp_socket_purge(struct nfc_llcp_sock *sock) struct nfc_llcp_local *local = sock->local; struct sk_buff *s, *tmp; - pr_debug("%p\n", &sock->sk); - skb_queue_purge(&sock->tx_queue); skb_queue_purge(&sock->tx_pending_queue); @@ -1505,9 +1503,8 @@ void nfc_llcp_recv(void *data, struct sk_buff *skb, int err) { struct nfc_llcp_local *local = (struct nfc_llcp_local *) data; - pr_debug("Received an LLCP PDU\n"); if (err < 0) { - pr_err("err %d\n", err); + pr_err("LLCP PDU receive err %d\n", err); return; } diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c index 82ab39d80726..6fd873aa86be 100644 --- a/net/nfc/nci/core.c +++ b/net/nfc/nci/core.c @@ -930,8 +930,6 @@ static void nci_deactivate_target(struct nfc_dev *nfc_dev, struct nci_dev *ndev = nfc_get_drvdata(nfc_dev); unsigned long nci_mode = NCI_DEACTIVATE_TYPE_IDLE_MODE; - pr_debug("entry\n"); - if (!ndev->target_active_prot) { pr_err("unable to deactivate target, no active target\n"); return; @@ -977,8 +975,6 @@ static int nci_dep_link_down(struct nfc_dev *nfc_dev) struct nci_dev *ndev = nfc_get_drvdata(nfc_dev); int rc; - pr_debug("entry\n"); - if (nfc_dev->rf_mode == NFC_RF_INITIATOR) { nci_deactivate_target(nfc_dev, NULL, NCI_DEACTIVATE_TYPE_IDLE_MODE); } else { diff --git a/net/nfc/nci/hci.c b/net/nfc/nci/hci.c index e199912ee1e5..19703a649b5a 100644 --- a/net/nfc/nci/hci.c +++ b/net/nfc/nci/hci.c @@ -432,8 +432,6 @@ void nci_hci_data_received_cb(void *context, struct sk_buff *frag_skb; int msg_len; - pr_debug("\n"); - if (err) { nci_req_complete(ndev, err); return; @@ -547,8 +545,6 @@ static u8 nci_hci_create_pipe(struct nci_dev *ndev, u8 dest_host, static int nci_hci_delete_pipe(struct nci_dev *ndev, u8 pipe) { - pr_debug("\n"); - return nci_hci_send_cmd(ndev, NCI_HCI_ADMIN_GATE, NCI_HCI_ADM_DELETE_PIPE, &pipe, 1, NULL); } diff --git a/net/nfc/nci/ntf.c b/net/nfc/nci/ntf.c index c5eacaac41ae..282c51051dcc 100644 --- a/net/nfc/nci/ntf.c +++ b/net/nfc/nci/ntf.c @@ -738,8 +738,6 @@ static void nci_nfcee_discover_ntf_packet(struct nci_dev *ndev, const struct nci_nfcee_discover_ntf *nfcee_ntf = (struct nci_nfcee_discover_ntf *)skb->data; - pr_debug("\n"); - /* NFCForum NCI 9.2.1 HCI Network Specific Handling * If the NFCC supports the HCI Network, it SHALL return one, * and only one, NFCEE_DISCOVER_NTF with a Protocol type of @@ -751,12 +749,6 @@ static void nci_nfcee_discover_ntf_packet(struct nci_dev *ndev, nci_req_complete(ndev, status); } -static void nci_nfcee_action_ntf_packet(struct nci_dev *ndev, - const struct sk_buff *skb) -{ - pr_debug("\n"); -} - void nci_ntf_packet(struct nci_dev *ndev, struct sk_buff *skb) { __u16 ntf_opcode = nci_opcode(skb->data); @@ -813,7 +805,6 @@ void nci_ntf_packet(struct nci_dev *ndev, struct sk_buff *skb) break; case NCI_OP_RF_NFCEE_ACTION_NTF: - nci_nfcee_action_ntf_packet(ndev, skb); break; default: diff --git a/net/nfc/nci/uart.c b/net/nfc/nci/uart.c index 502e7a3f8948..57500c262cc3 100644 --- a/net/nfc/nci/uart.c +++ b/net/nfc/nci/uart.c @@ -1,20 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2015, Marvell International Ltd. * - * This software file (the "File") is distributed by Marvell International - * Ltd. under the terms of the GNU General Public License Version 2, June 1991 - * (the "License"). You may use, redistribute and/or modify this File in - * accordance with the terms and conditions of the License, a copy of which - * is available on the worldwide web at - * http://www.gnu.org/licenses/old-licenses/gpl-2.0.txt. - * - * THE FILE IS DISTRIBUTED AS-IS, WITHOUT WARRANTY OF ANY KIND, AND THE - * IMPLIED WARRANTIES OF MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE - * ARE EXPRESSLY DISCLAIMED. The License provides additional details about - * this warranty disclaimer. - */ - -/* Inspired (hugely) by HCI LDISC implementation in Bluetooth. + * Inspired (hugely) by HCI LDISC implementation in Bluetooth. * * Copyright (C) 2000-2001 Qualcomm Incorporated * Copyright (C) 2002-2003 Maxim Krasnyansky diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 2a2bc64f75cf..46943a18a10d 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -91,6 +91,7 @@ #endif #include #include +#include #include "internal.h" @@ -241,8 +242,42 @@ struct packet_skb_cb { static void __fanout_unlink(struct sock *sk, struct packet_sock *po); static void __fanout_link(struct sock *sk, struct packet_sock *po); +#ifdef CONFIG_NETFILTER_EGRESS +static noinline struct sk_buff *nf_hook_direct_egress(struct sk_buff *skb) +{ + struct sk_buff *next, *head = NULL, *tail; + int rc; + + rcu_read_lock(); + for (; skb != NULL; skb = next) { + next = skb->next; + skb_mark_not_on_list(skb); + + if (!nf_hook_egress(skb, &rc, skb->dev)) + continue; + + if (!head) + head = skb; + else + tail->next = skb; + + tail = skb; + } + rcu_read_unlock(); + + return head; +} +#endif + static int packet_direct_xmit(struct sk_buff *skb) { +#ifdef CONFIG_NETFILTER_EGRESS + if (nf_hook_egress_active()) { + skb = nf_hook_direct_egress(skb); + if (!skb) + return NET_XMIT_DROP; + } +#endif return dev_direct_xmit(skb, packet_pick_tx_queue(skb)); } diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index cf7d974e0f61..30a1cf4c16c6 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -109,7 +109,7 @@ char *rose2asc(char *buf, const rose_address *addr) /* * Compare two ROSE addresses, 0 == equal. */ -int rosecmp(rose_address *addr1, rose_address *addr2) +int rosecmp(const rose_address *addr1, const rose_address *addr2) { int i; @@ -123,7 +123,8 @@ int rosecmp(rose_address *addr1, rose_address *addr2) /* * Compare two ROSE addresses for only mask digits, 0 == equal. */ -int rosecmpm(rose_address *addr1, rose_address *addr2, unsigned short mask) +int rosecmpm(const rose_address *addr1, const rose_address *addr2, + unsigned short mask) { unsigned int i, j; diff --git a/net/rose/rose_dev.c b/net/rose/rose_dev.c index 051804fbee17..f1a76a5820f1 100644 --- a/net/rose/rose_dev.c +++ b/net/rose/rose_dev.c @@ -66,10 +66,10 @@ static int rose_set_mac_address(struct net_device *dev, void *addr) if (err) return err; - rose_del_loopback_node((rose_address *)dev->dev_addr); + rose_del_loopback_node((const rose_address *)dev->dev_addr); } - memcpy(dev->dev_addr, sa->sa_data, dev->addr_len); + dev_addr_set(dev, sa->sa_data); return 0; } @@ -78,7 +78,7 @@ static int rose_open(struct net_device *dev) { int err; - err = rose_add_loopback_node((rose_address *)dev->dev_addr); + err = rose_add_loopback_node((const rose_address *)dev->dev_addr); if (err) return err; @@ -90,7 +90,7 @@ static int rose_open(struct net_device *dev) static int rose_close(struct net_device *dev) { netif_stop_queue(dev); - rose_del_loopback_node((rose_address *)dev->dev_addr); + rose_del_loopback_node((const rose_address *)dev->dev_addr); return 0; } diff --git a/net/rose/rose_link.c b/net/rose/rose_link.c index f6102e6f5161..8b96a56d3a49 100644 --- a/net/rose/rose_link.c +++ b/net/rose/rose_link.c @@ -94,11 +94,11 @@ static void rose_t0timer_expiry(struct timer_list *t) */ static int rose_send_frame(struct sk_buff *skb, struct rose_neigh *neigh) { - ax25_address *rose_call; + const ax25_address *rose_call; ax25_cb *ax25s; if (ax25cmp(&rose_callsign, &null_ax25_address) == 0) - rose_call = (ax25_address *)neigh->dev->dev_addr; + rose_call = (const ax25_address *)neigh->dev->dev_addr; else rose_call = &rose_callsign; @@ -117,11 +117,11 @@ static int rose_send_frame(struct sk_buff *skb, struct rose_neigh *neigh) */ static int rose_link_up(struct rose_neigh *neigh) { - ax25_address *rose_call; + const ax25_address *rose_call; ax25_cb *ax25s; if (ax25cmp(&rose_callsign, &null_ax25_address) == 0) - rose_call = (ax25_address *)neigh->dev->dev_addr; + rose_call = (const ax25_address *)neigh->dev->dev_addr; else rose_call = &rose_callsign; diff --git a/net/rose/rose_route.c b/net/rose/rose_route.c index c0e04c261a15..e2e6b6b78578 100644 --- a/net/rose/rose_route.c +++ b/net/rose/rose_route.c @@ -401,7 +401,7 @@ void rose_add_loopback_neigh(void) /* * Add a loopback node. */ -int rose_add_loopback_node(rose_address *address) +int rose_add_loopback_node(const rose_address *address) { struct rose_node *rose_node; int err = 0; @@ -446,7 +446,7 @@ out: /* * Delete a loopback node. */ -void rose_del_loopback_node(rose_address *address) +void rose_del_loopback_node(const rose_address *address) { struct rose_node *rose_node; @@ -629,7 +629,8 @@ struct net_device *rose_dev_get(rose_address *addr) rcu_read_lock(); for_each_netdev_rcu(&init_net, dev) { - if ((dev->flags & IFF_UP) && dev->type == ARPHRD_ROSE && rosecmp(addr, (rose_address *)dev->dev_addr) == 0) { + if ((dev->flags & IFF_UP) && dev->type == ARPHRD_ROSE && + rosecmp(addr, (const rose_address *)dev->dev_addr) == 0) { dev_hold(dev); goto out; } @@ -646,7 +647,8 @@ static int rose_dev_exists(rose_address *addr) rcu_read_lock(); for_each_netdev_rcu(&init_net, dev) { - if ((dev->flags & IFF_UP) && dev->type == ARPHRD_ROSE && rosecmp(addr, (rose_address *)dev->dev_addr) == 0) + if ((dev->flags & IFF_UP) && dev->type == ARPHRD_ROSE && + rosecmp(addr, (const rose_address *)dev->dev_addr) == 0) goto out; } dev = NULL; diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 7dd3a2dc5fa4..3258da3d5bed 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -480,16 +480,18 @@ int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est, atomic_set(&p->tcfa_bindcnt, 1); if (cpustats) { - p->cpu_bstats = netdev_alloc_pcpu_stats(struct gnet_stats_basic_cpu); + p->cpu_bstats = netdev_alloc_pcpu_stats(struct gnet_stats_basic_sync); if (!p->cpu_bstats) goto err1; - p->cpu_bstats_hw = netdev_alloc_pcpu_stats(struct gnet_stats_basic_cpu); + p->cpu_bstats_hw = netdev_alloc_pcpu_stats(struct gnet_stats_basic_sync); if (!p->cpu_bstats_hw) goto err2; p->cpu_qstats = alloc_percpu(struct gnet_stats_queue); if (!p->cpu_qstats) goto err3; } + gnet_stats_basic_sync_init(&p->tcfa_bstats); + gnet_stats_basic_sync_init(&p->tcfa_bstats_hw); spin_lock_init(&p->tcfa_lock); p->tcfa_index = index; p->tcfa_tm.install = jiffies; @@ -499,7 +501,7 @@ int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est, if (est) { err = gen_new_estimator(&p->tcfa_bstats, p->cpu_bstats, &p->tcfa_rate_est, - &p->tcfa_lock, NULL, est); + &p->tcfa_lock, false, est); if (err) goto err4; } @@ -1126,13 +1128,13 @@ void tcf_action_update_stats(struct tc_action *a, u64 bytes, u64 packets, u64 drops, bool hw) { if (a->cpu_bstats) { - _bstats_cpu_update(this_cpu_ptr(a->cpu_bstats), bytes, packets); + _bstats_update(this_cpu_ptr(a->cpu_bstats), bytes, packets); this_cpu_ptr(a->cpu_qstats)->drops += drops; if (hw) - _bstats_cpu_update(this_cpu_ptr(a->cpu_bstats_hw), - bytes, packets); + _bstats_update(this_cpu_ptr(a->cpu_bstats_hw), + bytes, packets); return; } @@ -1171,9 +1173,10 @@ int tcf_action_copy_stats(struct sk_buff *skb, struct tc_action *p, if (err < 0) goto errout; - if (gnet_stats_copy_basic(NULL, &d, p->cpu_bstats, &p->tcfa_bstats) < 0 || - gnet_stats_copy_basic_hw(NULL, &d, p->cpu_bstats_hw, - &p->tcfa_bstats_hw) < 0 || + if (gnet_stats_copy_basic(&d, p->cpu_bstats, + &p->tcfa_bstats, false) < 0 || + gnet_stats_copy_basic_hw(&d, p->cpu_bstats_hw, + &p->tcfa_bstats_hw, false) < 0 || gnet_stats_copy_rate_est(&d, &p->tcfa_rate_est) < 0 || gnet_stats_copy_queue(&d, p->cpu_qstats, &p->tcfa_qstats, diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index 5c36013339e1..f2bf896331a5 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -41,7 +41,7 @@ static int tcf_bpf_act(struct sk_buff *skb, const struct tc_action *act, int action, filter_res; tcf_lastuse_update(&prog->tcf_tm); - bstats_cpu_update(this_cpu_ptr(prog->common.cpu_bstats), skb); + bstats_update(this_cpu_ptr(prog->common.cpu_bstats), skb); filter = rcu_dereference(prog->filter); if (at_ingress) { diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index 7064a365a1a9..b757f90a2d58 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -718,7 +718,7 @@ static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a, u8 *tlv_data; u16 metalen; - bstats_cpu_update(this_cpu_ptr(ife->common.cpu_bstats), skb); + bstats_update(this_cpu_ptr(ife->common.cpu_bstats), skb); tcf_lastuse_update(&ife->tcf_tm); if (skb_at_tc_ingress(skb)) @@ -806,7 +806,7 @@ static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a, exceed_mtu = true; } - bstats_cpu_update(this_cpu_ptr(ife->common.cpu_bstats), skb); + bstats_update(this_cpu_ptr(ife->common.cpu_bstats), skb); tcf_lastuse_update(&ife->tcf_tm); if (!metalen) { /* no metadata to send */ diff --git a/net/sched/act_mpls.c b/net/sched/act_mpls.c index e4529b428cf4..8faa4c58305e 100644 --- a/net/sched/act_mpls.c +++ b/net/sched/act_mpls.c @@ -59,7 +59,7 @@ static int tcf_mpls_act(struct sk_buff *skb, const struct tc_action *a, int ret, mac_len; tcf_lastuse_update(&m->tcf_tm); - bstats_cpu_update(this_cpu_ptr(m->common.cpu_bstats), skb); + bstats_update(this_cpu_ptr(m->common.cpu_bstats), skb); /* Ensure 'data' points at mac_header prior calling mpls manipulating * functions. diff --git a/net/sched/act_police.c b/net/sched/act_police.c index 832157a840fc..9e77ba8401e5 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -125,7 +125,7 @@ static int tcf_police_init(struct net *net, struct nlattr *nla, police->common.cpu_bstats, &police->tcf_rate_est, &police->tcf_lock, - NULL, est); + false, est); if (err) goto failure; } else if (tb[TCA_POLICE_AVRATE] && @@ -248,7 +248,7 @@ static int tcf_police_act(struct sk_buff *skb, const struct tc_action *a, int ret; tcf_lastuse_update(&police->tcf_tm); - bstats_cpu_update(this_cpu_ptr(police->common.cpu_bstats), skb); + bstats_update(this_cpu_ptr(police->common.cpu_bstats), skb); ret = READ_ONCE(police->tcf_action); p = rcu_dereference_bh(police->params); diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c index 230501eb9e06..ce859b0e0deb 100644 --- a/net/sched/act_sample.c +++ b/net/sched/act_sample.c @@ -163,7 +163,7 @@ static int tcf_sample_act(struct sk_buff *skb, const struct tc_action *a, int retval; tcf_lastuse_update(&s->tcf_tm); - bstats_cpu_update(this_cpu_ptr(s->common.cpu_bstats), skb); + bstats_update(this_cpu_ptr(s->common.cpu_bstats), skb); retval = READ_ONCE(s->tcf_action); psample_group = rcu_dereference_bh(s->psample_group); diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c index cbbe1861d3a2..e617ab4505ca 100644 --- a/net/sched/act_simple.c +++ b/net/sched/act_simple.c @@ -36,7 +36,8 @@ static int tcf_simp_act(struct sk_buff *skb, const struct tc_action *a, * then it would look like "hello_3" (without quotes) */ pr_info("simple: %s_%llu\n", - (char *)d->tcfd_defdata, d->tcf_bstats.packets); + (char *)d->tcfd_defdata, + u64_stats_read(&d->tcf_bstats.packets)); spin_unlock(&d->tcf_lock); return d->tcf_action; } diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index 605418538347..d30ecbfc8f84 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -31,7 +31,7 @@ static int tcf_skbedit_act(struct sk_buff *skb, const struct tc_action *a, int action; tcf_lastuse_update(&d->tcf_tm); - bstats_cpu_update(this_cpu_ptr(d->common.cpu_bstats), skb); + bstats_update(this_cpu_ptr(d->common.cpu_bstats), skb); params = rcu_dereference_bh(d->params); action = READ_ONCE(d->tcf_action); diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c index ecb9ee666095..9b6b52c5e24e 100644 --- a/net/sched/act_skbmod.c +++ b/net/sched/act_skbmod.c @@ -31,7 +31,7 @@ static int tcf_skbmod_act(struct sk_buff *skb, const struct tc_action *a, u64 flags; tcf_lastuse_update(&d->tcf_tm); - bstats_cpu_update(this_cpu_ptr(d->common.cpu_bstats), skb); + bstats_update(this_cpu_ptr(d->common.cpu_bstats), skb); action = READ_ONCE(d->tcf_action); if (unlikely(action == TC_ACT_SHOT)) diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 91820f67275c..efcd0b5e9a32 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -885,7 +885,7 @@ static void qdisc_offload_graft_root(struct net_device *dev, static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid, u32 portid, u32 seq, u16 flags, int event) { - struct gnet_stats_basic_cpu __percpu *cpu_bstats = NULL; + struct gnet_stats_basic_sync __percpu *cpu_bstats = NULL; struct gnet_stats_queue __percpu *cpu_qstats = NULL; struct tcmsg *tcm; struct nlmsghdr *nlh; @@ -943,8 +943,7 @@ static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid, cpu_qstats = q->cpu_qstats; } - if (gnet_stats_copy_basic(qdisc_root_sleeping_running(q), - &d, cpu_bstats, &q->bstats) < 0 || + if (gnet_stats_copy_basic(&d, cpu_bstats, &q->bstats, true) < 0 || gnet_stats_copy_rate_est(&d, &q->rate_est) < 0 || gnet_stats_copy_queue(&d, cpu_qstats, &q->qstats, qlen) < 0) goto nla_put_failure; @@ -1265,26 +1264,17 @@ static struct Qdisc *qdisc_create(struct net_device *dev, rcu_assign_pointer(sch->stab, stab); } if (tca[TCA_RATE]) { - seqcount_t *running; - err = -EOPNOTSUPP; if (sch->flags & TCQ_F_MQROOT) { NL_SET_ERR_MSG(extack, "Cannot attach rate estimator to a multi-queue root qdisc"); goto err_out4; } - if (sch->parent != TC_H_ROOT && - !(sch->flags & TCQ_F_INGRESS) && - (!p || !(p->flags & TCQ_F_MQROOT))) - running = qdisc_root_sleeping_running(sch); - else - running = &sch->running; - err = gen_new_estimator(&sch->bstats, sch->cpu_bstats, &sch->rate_est, NULL, - running, + true, tca[TCA_RATE]); if (err) { NL_SET_ERR_MSG(extack, "Failed to generate new estimator"); @@ -1360,7 +1350,7 @@ static int qdisc_change(struct Qdisc *sch, struct nlattr **tca, sch->cpu_bstats, &sch->rate_est, NULL, - qdisc_root_sleeping_running(sch), + true, tca[TCA_RATE]); } out: diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c index 7d8518176b45..4c8e994cf0a5 100644 --- a/net/sched/sch_atm.c +++ b/net/sched/sch_atm.c @@ -52,7 +52,7 @@ struct atm_flow_data { struct atm_qdisc_data *parent; /* parent qdisc */ struct socket *sock; /* for closing */ int ref; /* reference count */ - struct gnet_stats_basic_packed bstats; + struct gnet_stats_basic_sync bstats; struct gnet_stats_queue qstats; struct list_head list; struct atm_flow_data *excess; /* flow for excess traffic; @@ -548,6 +548,7 @@ static int atm_tc_init(struct Qdisc *sch, struct nlattr *opt, pr_debug("atm_tc_init(sch %p,[qdisc %p],opt %p)\n", sch, p, opt); INIT_LIST_HEAD(&p->flows); INIT_LIST_HEAD(&p->link.list); + gnet_stats_basic_sync_init(&p->link.bstats); list_add(&p->link.list, &p->flows); p->link.q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, sch->handle, extack); @@ -652,8 +653,7 @@ atm_tc_dump_class_stats(struct Qdisc *sch, unsigned long arg, { struct atm_flow_data *flow = (struct atm_flow_data *)arg; - if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), - d, NULL, &flow->bstats) < 0 || + if (gnet_stats_copy_basic(d, NULL, &flow->bstats, true) < 0 || gnet_stats_copy_queue(d, NULL, &flow->qstats, flow->q->q.qlen) < 0) return -1; diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index e0da15530f0e..02d9f0dfe356 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -116,7 +116,7 @@ struct cbq_class { long avgidle; long deficit; /* Saved deficit for WRR */ psched_time_t penalized; - struct gnet_stats_basic_packed bstats; + struct gnet_stats_basic_sync bstats; struct gnet_stats_queue qstats; struct net_rate_estimator __rcu *rate_est; struct tc_cbq_xstats xstats; @@ -565,8 +565,7 @@ cbq_update(struct cbq_sched_data *q) long avgidle = cl->avgidle; long idle; - cl->bstats.packets++; - cl->bstats.bytes += len; + _bstats_update(&cl->bstats, len, 1); /* * (now - last) is total time between packet right edges. @@ -1384,8 +1383,7 @@ cbq_dump_class_stats(struct Qdisc *sch, unsigned long arg, if (cl->undertime != PSCHED_PASTPERFECT) cl->xstats.undertime = cl->undertime - q->now; - if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), - d, NULL, &cl->bstats) < 0 || + if (gnet_stats_copy_basic(d, NULL, &cl->bstats, true) < 0 || gnet_stats_copy_rate_est(d, &cl->rate_est) < 0 || gnet_stats_copy_queue(d, NULL, &cl->qstats, qlen) < 0) return -1; @@ -1519,7 +1517,7 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t err = gen_replace_estimator(&cl->bstats, NULL, &cl->rate_est, NULL, - qdisc_root_sleeping_running(sch), + true, tca[TCA_RATE]); if (err) { NL_SET_ERR_MSG(extack, "Failed to replace specified rate estimator"); @@ -1611,6 +1609,7 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t if (cl == NULL) goto failure; + gnet_stats_basic_sync_init(&cl->bstats); err = tcf_block_get(&cl->block, &cl->filter_list, sch, extack); if (err) { kfree(cl); @@ -1619,9 +1618,7 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t if (tca[TCA_RATE]) { err = gen_new_estimator(&cl->bstats, NULL, &cl->rate_est, - NULL, - qdisc_root_sleeping_running(sch), - tca[TCA_RATE]); + NULL, true, tca[TCA_RATE]); if (err) { NL_SET_ERR_MSG(extack, "Couldn't create new estimator"); tcf_block_put(cl->block); diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c index 642cd179b7a7..18e4f7a0b291 100644 --- a/net/sched/sch_drr.c +++ b/net/sched/sch_drr.c @@ -19,7 +19,7 @@ struct drr_class { struct Qdisc_class_common common; unsigned int filter_cnt; - struct gnet_stats_basic_packed bstats; + struct gnet_stats_basic_sync bstats; struct gnet_stats_queue qstats; struct net_rate_estimator __rcu *rate_est; struct list_head alist; @@ -85,8 +85,7 @@ static int drr_change_class(struct Qdisc *sch, u32 classid, u32 parentid, if (tca[TCA_RATE]) { err = gen_replace_estimator(&cl->bstats, NULL, &cl->rate_est, - NULL, - qdisc_root_sleeping_running(sch), + NULL, true, tca[TCA_RATE]); if (err) { NL_SET_ERR_MSG(extack, "Failed to replace estimator"); @@ -106,6 +105,7 @@ static int drr_change_class(struct Qdisc *sch, u32 classid, u32 parentid, if (cl == NULL) return -ENOBUFS; + gnet_stats_basic_sync_init(&cl->bstats); cl->common.classid = classid; cl->quantum = quantum; cl->qdisc = qdisc_create_dflt(sch->dev_queue, @@ -118,9 +118,7 @@ static int drr_change_class(struct Qdisc *sch, u32 classid, u32 parentid, if (tca[TCA_RATE]) { err = gen_replace_estimator(&cl->bstats, NULL, &cl->rate_est, - NULL, - qdisc_root_sleeping_running(sch), - tca[TCA_RATE]); + NULL, true, tca[TCA_RATE]); if (err) { NL_SET_ERR_MSG(extack, "Failed to replace estimator"); qdisc_put(cl->qdisc); @@ -267,8 +265,7 @@ static int drr_dump_class_stats(struct Qdisc *sch, unsigned long arg, if (qlen) xstats.deficit = cl->deficit; - if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), - d, NULL, &cl->bstats) < 0 || + if (gnet_stats_copy_basic(d, NULL, &cl->bstats, true) < 0 || gnet_stats_copy_rate_est(d, &cl->rate_est) < 0 || gnet_stats_copy_queue(d, cl_q->cpu_qstats, &cl_q->qstats, qlen) < 0) return -1; diff --git a/net/sched/sch_ets.c b/net/sched/sch_ets.c index 1f857ffd1ac2..0eae9ff5edf6 100644 --- a/net/sched/sch_ets.c +++ b/net/sched/sch_ets.c @@ -41,7 +41,7 @@ struct ets_class { struct Qdisc *qdisc; u32 quantum; u32 deficit; - struct gnet_stats_basic_packed bstats; + struct gnet_stats_basic_sync bstats; struct gnet_stats_queue qstats; }; @@ -325,8 +325,7 @@ static int ets_class_dump_stats(struct Qdisc *sch, unsigned long arg, struct ets_class *cl = ets_class_from_arg(sch, arg); struct Qdisc *cl_q = cl->qdisc; - if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), - d, NULL, &cl_q->bstats) < 0 || + if (gnet_stats_copy_basic(d, NULL, &cl_q->bstats, true) < 0 || qdisc_qstats_copy(d, cl_q) < 0) return -1; @@ -661,7 +660,6 @@ static int ets_qdisc_change(struct Qdisc *sch, struct nlattr *opt, q->nbands = nbands; for (i = nstrict; i < q->nstrict; i++) { - INIT_LIST_HEAD(&q->classes[i].alist); if (q->classes[i].qdisc->q.qlen) { list_add_tail(&q->classes[i].alist, &q->active); q->classes[i].deficit = quanta[i]; @@ -687,7 +685,11 @@ static int ets_qdisc_change(struct Qdisc *sch, struct nlattr *opt, ets_offload_change(sch); for (i = q->nbands; i < oldbands; i++) { qdisc_put(q->classes[i].qdisc); - memset(&q->classes[i], 0, sizeof(q->classes[i])); + q->classes[i].qdisc = NULL; + q->classes[i].quantum = 0; + q->classes[i].deficit = 0; + gnet_stats_basic_sync_init(&q->classes[i].bstats); + memset(&q->classes[i].qstats, 0, sizeof(q->classes[i].qstats)); } return 0; } @@ -696,7 +698,7 @@ static int ets_qdisc_init(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { struct ets_sched *q = qdisc_priv(sch); - int err; + int err, i; if (!opt) return -EINVAL; @@ -706,6 +708,9 @@ static int ets_qdisc_init(struct Qdisc *sch, struct nlattr *opt, return err; INIT_LIST_HEAD(&q->active); + for (i = 0; i < TCQ_ETS_MAX_BANDS; i++) + INIT_LIST_HEAD(&q->classes[i].alist); + return ets_qdisc_change(sch, opt, extack); } diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index bb0cd6d3d2c2..839e1235db05 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -362,6 +362,8 @@ static const struct nla_policy fq_codel_policy[TCA_FQ_CODEL_MAX + 1] = { [TCA_FQ_CODEL_CE_THRESHOLD] = { .type = NLA_U32 }, [TCA_FQ_CODEL_DROP_BATCH_SIZE] = { .type = NLA_U32 }, [TCA_FQ_CODEL_MEMORY_LIMIT] = { .type = NLA_U32 }, + [TCA_FQ_CODEL_CE_THRESHOLD_SELECTOR] = { .type = NLA_U8 }, + [TCA_FQ_CODEL_CE_THRESHOLD_MASK] = { .type = NLA_U8 }, }; static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt, @@ -408,6 +410,11 @@ static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt, q->cparams.ce_threshold = (val * NSEC_PER_USEC) >> CODEL_SHIFT; } + if (tb[TCA_FQ_CODEL_CE_THRESHOLD_SELECTOR]) + q->cparams.ce_threshold_selector = nla_get_u8(tb[TCA_FQ_CODEL_CE_THRESHOLD_SELECTOR]); + if (tb[TCA_FQ_CODEL_CE_THRESHOLD_MASK]) + q->cparams.ce_threshold_mask = nla_get_u8(tb[TCA_FQ_CODEL_CE_THRESHOLD_MASK]); + if (tb[TCA_FQ_CODEL_INTERVAL]) { u64 interval = nla_get_u32(tb[TCA_FQ_CODEL_INTERVAL]); @@ -544,10 +551,15 @@ static int fq_codel_dump(struct Qdisc *sch, struct sk_buff *skb) q->flows_cnt)) goto nla_put_failure; - if (q->cparams.ce_threshold != CODEL_DISABLED_THRESHOLD && - nla_put_u32(skb, TCA_FQ_CODEL_CE_THRESHOLD, - codel_time_to_us(q->cparams.ce_threshold))) - goto nla_put_failure; + if (q->cparams.ce_threshold != CODEL_DISABLED_THRESHOLD) { + if (nla_put_u32(skb, TCA_FQ_CODEL_CE_THRESHOLD, + codel_time_to_us(q->cparams.ce_threshold))) + goto nla_put_failure; + if (nla_put_u8(skb, TCA_FQ_CODEL_CE_THRESHOLD_SELECTOR, q->cparams.ce_threshold_selector)) + goto nla_put_failure; + if (nla_put_u8(skb, TCA_FQ_CODEL_CE_THRESHOLD_MASK, q->cparams.ce_threshold_mask)) + goto nla_put_failure; + } return nla_nest_end(skb, opts); diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 8c64a552a64f..b0ff0dff2773 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -304,8 +304,8 @@ trace: /* * Transmit possibly several skbs, and handle the return status as - * required. Owning running seqcount bit guarantees that - * only one CPU can execute this function. + * required. Owning qdisc running bit guarantees that only one CPU + * can execute this function. * * Returns to the caller: * false - hardware queue frozen backoff @@ -606,7 +606,6 @@ struct Qdisc noop_qdisc = { .ops = &noop_qdisc_ops, .q.lock = __SPIN_LOCK_UNLOCKED(noop_qdisc.q.lock), .dev_queue = &noop_netdev_queue, - .running = SEQCNT_ZERO(noop_qdisc.running), .busylock = __SPIN_LOCK_UNLOCKED(noop_qdisc.busylock), .gso_skb = { .next = (struct sk_buff *)&noop_qdisc.gso_skb, @@ -867,7 +866,6 @@ struct Qdisc_ops pfifo_fast_ops __read_mostly = { EXPORT_SYMBOL(pfifo_fast_ops); static struct lock_class_key qdisc_tx_busylock; -static struct lock_class_key qdisc_running_key; struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, const struct Qdisc_ops *ops, @@ -892,11 +890,12 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, __skb_queue_head_init(&sch->gso_skb); __skb_queue_head_init(&sch->skb_bad_txq); qdisc_skb_head_init(&sch->q); + gnet_stats_basic_sync_init(&sch->bstats); spin_lock_init(&sch->q.lock); if (ops->static_flags & TCQ_F_CPUSTATS) { sch->cpu_bstats = - netdev_alloc_pcpu_stats(struct gnet_stats_basic_cpu); + netdev_alloc_pcpu_stats(struct gnet_stats_basic_sync); if (!sch->cpu_bstats) goto errout1; @@ -916,10 +915,6 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, lockdep_set_class(&sch->seqlock, dev->qdisc_tx_busylock ?: &qdisc_tx_busylock); - seqcount_init(&sch->running); - lockdep_set_class(&sch->running, - dev->qdisc_running_key ?: &qdisc_running_key); - sch->ops = ops; sch->flags = ops->static_flags; sch->enqueue = ops->enqueue; diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c index 621dc6afde8f..72de08ef8335 100644 --- a/net/sched/sch_gred.c +++ b/net/sched/sch_gred.c @@ -353,6 +353,7 @@ static int gred_offload_dump_stats(struct Qdisc *sch) { struct gred_sched *table = qdisc_priv(sch); struct tc_gred_qopt_offload *hw_stats; + u64 bytes = 0, packets = 0; unsigned int i; int ret; @@ -364,9 +365,11 @@ static int gred_offload_dump_stats(struct Qdisc *sch) hw_stats->handle = sch->handle; hw_stats->parent = sch->parent; - for (i = 0; i < MAX_DPs; i++) + for (i = 0; i < MAX_DPs; i++) { + gnet_stats_basic_sync_init(&hw_stats->stats.bstats[i]); if (table->tab[i]) hw_stats->stats.xstats[i] = &table->tab[i]->stats; + } ret = qdisc_offload_dump_helper(sch, TC_SETUP_QDISC_GRED, hw_stats); /* Even if driver returns failure adjust the stats - in case offload @@ -375,19 +378,19 @@ static int gred_offload_dump_stats(struct Qdisc *sch) for (i = 0; i < MAX_DPs; i++) { if (!table->tab[i]) continue; - table->tab[i]->packetsin += hw_stats->stats.bstats[i].packets; - table->tab[i]->bytesin += hw_stats->stats.bstats[i].bytes; + table->tab[i]->packetsin += u64_stats_read(&hw_stats->stats.bstats[i].packets); + table->tab[i]->bytesin += u64_stats_read(&hw_stats->stats.bstats[i].bytes); table->tab[i]->backlog += hw_stats->stats.qstats[i].backlog; - _bstats_update(&sch->bstats, - hw_stats->stats.bstats[i].bytes, - hw_stats->stats.bstats[i].packets); + bytes += u64_stats_read(&hw_stats->stats.bstats[i].bytes); + packets += u64_stats_read(&hw_stats->stats.bstats[i].packets); sch->qstats.qlen += hw_stats->stats.qstats[i].qlen; sch->qstats.backlog += hw_stats->stats.qstats[i].backlog; sch->qstats.drops += hw_stats->stats.qstats[i].drops; sch->qstats.requeues += hw_stats->stats.qstats[i].requeues; sch->qstats.overlimits += hw_stats->stats.qstats[i].overlimits; } + _bstats_update(&sch->bstats, bytes, packets); kfree(hw_stats); return ret; diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index b7ac30cca035..d3979a6000e7 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -111,7 +111,7 @@ enum hfsc_class_flags { struct hfsc_class { struct Qdisc_class_common cl_common; - struct gnet_stats_basic_packed bstats; + struct gnet_stats_basic_sync bstats; struct gnet_stats_queue qstats; struct net_rate_estimator __rcu *rate_est; struct tcf_proto __rcu *filter_list; /* filter list */ @@ -965,7 +965,7 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid, err = gen_replace_estimator(&cl->bstats, NULL, &cl->rate_est, NULL, - qdisc_root_sleeping_running(sch), + true, tca[TCA_RATE]); if (err) return err; @@ -1033,9 +1033,7 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid, if (tca[TCA_RATE]) { err = gen_new_estimator(&cl->bstats, NULL, &cl->rate_est, - NULL, - qdisc_root_sleeping_running(sch), - tca[TCA_RATE]); + NULL, true, tca[TCA_RATE]); if (err) { tcf_block_put(cl->block); kfree(cl); @@ -1328,7 +1326,7 @@ hfsc_dump_class_stats(struct Qdisc *sch, unsigned long arg, xstats.work = cl->cl_total; xstats.rtwork = cl->cl_cumul; - if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), d, NULL, &cl->bstats) < 0 || + if (gnet_stats_copy_basic(d, NULL, &cl->bstats, true) < 0 || gnet_stats_copy_rate_est(d, &cl->rate_est) < 0 || gnet_stats_copy_queue(d, NULL, &cl->qstats, qlen) < 0) return -1; @@ -1406,6 +1404,7 @@ hfsc_init_qdisc(struct Qdisc *sch, struct nlattr *opt, if (err) return err; + gnet_stats_basic_sync_init(&q->root.bstats); q->root.cl_common.classid = sch->handle; q->root.sched = q; q->root.qdisc = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 5067a6e5d4fd..cf1d45db4e84 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -113,8 +113,8 @@ struct htb_class { /* * Written often fields */ - struct gnet_stats_basic_packed bstats; - struct gnet_stats_basic_packed bstats_bias; + struct gnet_stats_basic_sync bstats; + struct gnet_stats_basic_sync bstats_bias; struct tc_htb_xstats xstats; /* our special stats */ /* token bucket parameters */ @@ -1308,10 +1308,11 @@ nla_put_failure: static void htb_offload_aggregate_stats(struct htb_sched *q, struct htb_class *cl) { + u64 bytes = 0, packets = 0; struct htb_class *c; unsigned int i; - memset(&cl->bstats, 0, sizeof(cl->bstats)); + gnet_stats_basic_sync_init(&cl->bstats); for (i = 0; i < q->clhash.hashsize; i++) { hlist_for_each_entry(c, &q->clhash.hash[i], common.hnode) { @@ -1323,14 +1324,15 @@ static void htb_offload_aggregate_stats(struct htb_sched *q, if (p != cl) continue; - cl->bstats.bytes += c->bstats_bias.bytes; - cl->bstats.packets += c->bstats_bias.packets; + bytes += u64_stats_read(&c->bstats_bias.bytes); + packets += u64_stats_read(&c->bstats_bias.packets); if (c->level == 0) { - cl->bstats.bytes += c->leaf.q->bstats.bytes; - cl->bstats.packets += c->leaf.q->bstats.packets; + bytes += u64_stats_read(&c->leaf.q->bstats.bytes); + packets += u64_stats_read(&c->leaf.q->bstats.packets); } } } + _bstats_update(&cl->bstats, bytes, packets); } static int @@ -1357,16 +1359,16 @@ htb_dump_class_stats(struct Qdisc *sch, unsigned long arg, struct gnet_dump *d) if (cl->leaf.q) cl->bstats = cl->leaf.q->bstats; else - memset(&cl->bstats, 0, sizeof(cl->bstats)); - cl->bstats.bytes += cl->bstats_bias.bytes; - cl->bstats.packets += cl->bstats_bias.packets; + gnet_stats_basic_sync_init(&cl->bstats); + _bstats_update(&cl->bstats, + u64_stats_read(&cl->bstats_bias.bytes), + u64_stats_read(&cl->bstats_bias.packets)); } else { htb_offload_aggregate_stats(q, cl); } } - if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), - d, NULL, &cl->bstats) < 0 || + if (gnet_stats_copy_basic(d, NULL, &cl->bstats, true) < 0 || gnet_stats_copy_rate_est(d, &cl->rate_est) < 0 || gnet_stats_copy_queue(d, NULL, &qs, qlen) < 0) return -1; @@ -1578,8 +1580,9 @@ static int htb_destroy_class_offload(struct Qdisc *sch, struct htb_class *cl, WARN_ON(old != q); if (cl->parent) { - cl->parent->bstats_bias.bytes += q->bstats.bytes; - cl->parent->bstats_bias.packets += q->bstats.packets; + _bstats_update(&cl->parent->bstats_bias, + u64_stats_read(&q->bstats.bytes), + u64_stats_read(&q->bstats.packets)); } offload_opt = (struct tc_htb_qopt_offload) { @@ -1849,6 +1852,9 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, if (!cl) goto failure; + gnet_stats_basic_sync_init(&cl->bstats); + gnet_stats_basic_sync_init(&cl->bstats_bias); + err = tcf_block_get(&cl->block, &cl->filter_list, sch, extack); if (err) { kfree(cl); @@ -1858,7 +1864,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, err = gen_new_estimator(&cl->bstats, NULL, &cl->rate_est, NULL, - qdisc_root_sleeping_running(sch), + true, tca[TCA_RATE] ? : &est.nla); if (err) goto err_block_put; @@ -1922,8 +1928,9 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, htb_graft_helper(dev_queue, old_q); goto err_kill_estimator; } - parent->bstats_bias.bytes += old_q->bstats.bytes; - parent->bstats_bias.packets += old_q->bstats.packets; + _bstats_update(&parent->bstats_bias, + u64_stats_read(&old_q->bstats.bytes), + u64_stats_read(&old_q->bstats.packets)); qdisc_put(old_q); } new_q = qdisc_create_dflt(dev_queue, &pfifo_qdisc_ops, @@ -1983,7 +1990,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, err = gen_replace_estimator(&cl->bstats, NULL, &cl->rate_est, NULL, - qdisc_root_sleeping_running(sch), + true, tca[TCA_RATE]); if (err) return err; diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c index e04f1a87642b..83d2e54bf303 100644 --- a/net/sched/sch_mq.c +++ b/net/sched/sch_mq.c @@ -130,10 +130,9 @@ static int mq_dump(struct Qdisc *sch, struct sk_buff *skb) struct net_device *dev = qdisc_dev(sch); struct Qdisc *qdisc; unsigned int ntx; - __u32 qlen = 0; sch->q.qlen = 0; - memset(&sch->bstats, 0, sizeof(sch->bstats)); + gnet_stats_basic_sync_init(&sch->bstats); memset(&sch->qstats, 0, sizeof(sch->qstats)); /* MQ supports lockless qdiscs. However, statistics accounting needs @@ -145,25 +144,11 @@ static int mq_dump(struct Qdisc *sch, struct sk_buff *skb) qdisc = netdev_get_tx_queue(dev, ntx)->qdisc_sleeping; spin_lock_bh(qdisc_lock(qdisc)); - if (qdisc_is_percpu_stats(qdisc)) { - qlen = qdisc_qlen_sum(qdisc); - __gnet_stats_copy_basic(NULL, &sch->bstats, - qdisc->cpu_bstats, - &qdisc->bstats); - __gnet_stats_copy_queue(&sch->qstats, - qdisc->cpu_qstats, - &qdisc->qstats, qlen); - sch->q.qlen += qlen; - } else { - sch->q.qlen += qdisc->q.qlen; - sch->bstats.bytes += qdisc->bstats.bytes; - sch->bstats.packets += qdisc->bstats.packets; - sch->qstats.qlen += qdisc->qstats.qlen; - sch->qstats.backlog += qdisc->qstats.backlog; - sch->qstats.drops += qdisc->qstats.drops; - sch->qstats.requeues += qdisc->qstats.requeues; - sch->qstats.overlimits += qdisc->qstats.overlimits; - } + gnet_stats_add_basic(&sch->bstats, qdisc->cpu_bstats, + &qdisc->bstats, false); + gnet_stats_add_queue(&sch->qstats, qdisc->cpu_qstats, + &qdisc->qstats); + sch->q.qlen += qdisc_qlen(qdisc); spin_unlock_bh(qdisc_lock(qdisc)); } @@ -246,8 +231,7 @@ static int mq_dump_class_stats(struct Qdisc *sch, unsigned long cl, struct netdev_queue *dev_queue = mq_queue_get(sch, cl); sch = dev_queue->qdisc_sleeping; - if (gnet_stats_copy_basic(&sch->running, d, sch->cpu_bstats, - &sch->bstats) < 0 || + if (gnet_stats_copy_basic(d, sch->cpu_bstats, &sch->bstats, true) < 0 || qdisc_qstats_copy(d, sch) < 0) return -1; return 0; diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c index e1904e62425e..b29f3453c6ea 100644 --- a/net/sched/sch_mqprio.c +++ b/net/sched/sch_mqprio.c @@ -390,7 +390,7 @@ static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb) unsigned int ntx, tc; sch->q.qlen = 0; - memset(&sch->bstats, 0, sizeof(sch->bstats)); + gnet_stats_basic_sync_init(&sch->bstats); memset(&sch->qstats, 0, sizeof(sch->qstats)); /* MQ supports lockless qdiscs. However, statistics accounting needs @@ -402,25 +402,11 @@ static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb) qdisc = netdev_get_tx_queue(dev, ntx)->qdisc_sleeping; spin_lock_bh(qdisc_lock(qdisc)); - if (qdisc_is_percpu_stats(qdisc)) { - __u32 qlen = qdisc_qlen_sum(qdisc); - - __gnet_stats_copy_basic(NULL, &sch->bstats, - qdisc->cpu_bstats, - &qdisc->bstats); - __gnet_stats_copy_queue(&sch->qstats, - qdisc->cpu_qstats, - &qdisc->qstats, qlen); - sch->q.qlen += qlen; - } else { - sch->q.qlen += qdisc->q.qlen; - sch->bstats.bytes += qdisc->bstats.bytes; - sch->bstats.packets += qdisc->bstats.packets; - sch->qstats.backlog += qdisc->qstats.backlog; - sch->qstats.drops += qdisc->qstats.drops; - sch->qstats.requeues += qdisc->qstats.requeues; - sch->qstats.overlimits += qdisc->qstats.overlimits; - } + gnet_stats_add_basic(&sch->bstats, qdisc->cpu_bstats, + &qdisc->bstats, false); + gnet_stats_add_queue(&sch->qstats, qdisc->cpu_qstats, + &qdisc->qstats); + sch->q.qlen += qdisc_qlen(qdisc); spin_unlock_bh(qdisc_lock(qdisc)); } @@ -512,12 +498,13 @@ static int mqprio_dump_class_stats(struct Qdisc *sch, unsigned long cl, { if (cl >= TC_H_MIN_PRIORITY) { int i; - __u32 qlen = 0; + __u32 qlen; struct gnet_stats_queue qstats = {0}; - struct gnet_stats_basic_packed bstats = {0}; + struct gnet_stats_basic_sync bstats; struct net_device *dev = qdisc_dev(sch); struct netdev_tc_txq tc = dev->tc_to_txq[cl & TC_BITMASK]; + gnet_stats_basic_sync_init(&bstats); /* Drop lock here it will be reclaimed before touching * statistics this is required because the d->lock we * hold here is the look on dev_queue->qdisc_sleeping @@ -532,40 +519,28 @@ static int mqprio_dump_class_stats(struct Qdisc *sch, unsigned long cl, spin_lock_bh(qdisc_lock(qdisc)); - if (qdisc_is_percpu_stats(qdisc)) { - qlen = qdisc_qlen_sum(qdisc); + gnet_stats_add_basic(&bstats, qdisc->cpu_bstats, + &qdisc->bstats, false); + gnet_stats_add_queue(&qstats, qdisc->cpu_qstats, + &qdisc->qstats); + sch->q.qlen += qdisc_qlen(qdisc); - __gnet_stats_copy_basic(NULL, &bstats, - qdisc->cpu_bstats, - &qdisc->bstats); - __gnet_stats_copy_queue(&qstats, - qdisc->cpu_qstats, - &qdisc->qstats, - qlen); - } else { - qlen += qdisc->q.qlen; - bstats.bytes += qdisc->bstats.bytes; - bstats.packets += qdisc->bstats.packets; - qstats.backlog += qdisc->qstats.backlog; - qstats.drops += qdisc->qstats.drops; - qstats.requeues += qdisc->qstats.requeues; - qstats.overlimits += qdisc->qstats.overlimits; - } spin_unlock_bh(qdisc_lock(qdisc)); } + qlen = qdisc_qlen(sch) + qstats.qlen; /* Reclaim root sleeping lock before completing stats */ if (d->lock) spin_lock_bh(d->lock); - if (gnet_stats_copy_basic(NULL, d, NULL, &bstats) < 0 || + if (gnet_stats_copy_basic(d, NULL, &bstats, false) < 0 || gnet_stats_copy_queue(d, NULL, &qstats, qlen) < 0) return -1; } else { struct netdev_queue *dev_queue = mqprio_queue_get(sch, cl); sch = dev_queue->qdisc_sleeping; - if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), d, - sch->cpu_bstats, &sch->bstats) < 0 || + if (gnet_stats_copy_basic(d, sch->cpu_bstats, + &sch->bstats, true) < 0 || qdisc_qstats_copy(d, sch) < 0) return -1; } diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c index e282e7382117..cd8ab90c4765 100644 --- a/net/sched/sch_multiq.c +++ b/net/sched/sch_multiq.c @@ -338,8 +338,7 @@ static int multiq_dump_class_stats(struct Qdisc *sch, unsigned long cl, struct Qdisc *cl_q; cl_q = q->queues[cl - 1]; - if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), - d, cl_q->cpu_bstats, &cl_q->bstats) < 0 || + if (gnet_stats_copy_basic(d, cl_q->cpu_bstats, &cl_q->bstats, true) < 0 || qdisc_qstats_copy(d, cl_q) < 0) return -1; diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c index 03fdf31ccb6a..3b8d7197c06b 100644 --- a/net/sched/sch_prio.c +++ b/net/sched/sch_prio.c @@ -361,8 +361,8 @@ static int prio_dump_class_stats(struct Qdisc *sch, unsigned long cl, struct Qdisc *cl_q; cl_q = q->queues[cl - 1]; - if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), - d, cl_q->cpu_bstats, &cl_q->bstats) < 0 || + if (gnet_stats_copy_basic(d, cl_q->cpu_bstats, + &cl_q->bstats, true) < 0 || qdisc_qstats_copy(d, cl_q) < 0) return -1; diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index 58a9d42b52b8..0b7f9ba28deb 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -131,7 +131,7 @@ struct qfq_class { unsigned int filter_cnt; - struct gnet_stats_basic_packed bstats; + struct gnet_stats_basic_sync bstats; struct gnet_stats_queue qstats; struct net_rate_estimator __rcu *rate_est; struct Qdisc *qdisc; @@ -451,7 +451,7 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, err = gen_replace_estimator(&cl->bstats, NULL, &cl->rate_est, NULL, - qdisc_root_sleeping_running(sch), + true, tca[TCA_RATE]); if (err) return err; @@ -465,6 +465,7 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, if (cl == NULL) return -ENOBUFS; + gnet_stats_basic_sync_init(&cl->bstats); cl->common.classid = classid; cl->deficit = lmax; @@ -477,7 +478,7 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, err = gen_new_estimator(&cl->bstats, NULL, &cl->rate_est, NULL, - qdisc_root_sleeping_running(sch), + true, tca[TCA_RATE]); if (err) goto destroy_class; @@ -639,8 +640,7 @@ static int qfq_dump_class_stats(struct Qdisc *sch, unsigned long arg, xstats.weight = cl->agg->class_weight; xstats.lmax = cl->agg->lmax; - if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), - d, NULL, &cl->bstats) < 0 || + if (gnet_stats_copy_basic(d, NULL, &cl->bstats, true) < 0 || gnet_stats_copy_rate_est(d, &cl->rate_est) < 0 || qdisc_qstats_copy(d, cl->qdisc) < 0) return -1; @@ -1234,8 +1234,7 @@ static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch, return err; } - cl->bstats.bytes += len; - cl->bstats.packets += gso_segs; + _bstats_update(&cl->bstats, len, gso_segs); sch->qstats.backlog += len; ++sch->q.qlen; diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index b9fd18d98646..9ab068fa2672 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -1977,7 +1977,7 @@ static int taprio_dump_class_stats(struct Qdisc *sch, unsigned long cl, struct netdev_queue *dev_queue = taprio_queue_get(sch, cl); sch = dev_queue->qdisc_sleeping; - if (gnet_stats_copy_basic(&sch->running, d, NULL, &sch->bstats) < 0 || + if (gnet_stats_copy_basic(d, NULL, &sch->bstats, true) < 0 || qdisc_qstats_copy(d, sch) < 0) return -1; return 0; diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c index 78e79029dc63..72102277449e 100644 --- a/net/sched/sch_tbf.c +++ b/net/sched/sch_tbf.c @@ -184,6 +184,20 @@ static int tbf_offload_dump(struct Qdisc *sch) return qdisc_offload_dump_helper(sch, TC_SETUP_QDISC_TBF, &qopt); } +static void tbf_offload_graft(struct Qdisc *sch, struct Qdisc *new, + struct Qdisc *old, struct netlink_ext_ack *extack) +{ + struct tc_tbf_qopt_offload graft_offload = { + .handle = sch->handle, + .parent = sch->parent, + .child_handle = new->handle, + .command = TC_TBF_GRAFT, + }; + + qdisc_offload_graft_helper(qdisc_dev(sch), sch, new, old, + TC_SETUP_QDISC_TBF, &graft_offload, extack); +} + /* GSO packet is too big, segment it so that tbf can transmit * each segment in time */ @@ -547,6 +561,8 @@ static int tbf_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, new = &noop_qdisc; *old = qdisc_replace(sch, new, &q->qdisc); + + tbf_offload_graft(sch, new, *old, extack); return 0; } diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 7fd1fd6abfb6..8dc34388b2c1 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -439,6 +439,47 @@ static int smcr_clnt_conf_first_link(struct smc_sock *smc) return 0; } +static bool smc_isascii(char *hostname) +{ + int i; + + for (i = 0; i < SMC_MAX_HOSTNAME_LEN; i++) + if (!isascii(hostname[i])) + return false; + return true; +} + +static void smc_conn_save_peer_info_fce(struct smc_sock *smc, + struct smc_clc_msg_accept_confirm *clc) +{ + struct smc_clc_msg_accept_confirm_v2 *clc_v2 = + (struct smc_clc_msg_accept_confirm_v2 *)clc; + struct smc_clc_first_contact_ext *fce; + int clc_v2_len; + + if (clc->hdr.version == SMC_V1 || + !(clc->hdr.typev2 & SMC_FIRST_CONTACT_MASK)) + return; + + if (smc->conn.lgr->is_smcd) { + memcpy(smc->conn.lgr->negotiated_eid, clc_v2->d1.eid, + SMC_MAX_EID_LEN); + clc_v2_len = offsetofend(struct smc_clc_msg_accept_confirm_v2, + d1); + } else { + memcpy(smc->conn.lgr->negotiated_eid, clc_v2->r1.eid, + SMC_MAX_EID_LEN); + clc_v2_len = offsetofend(struct smc_clc_msg_accept_confirm_v2, + r1); + } + fce = (struct smc_clc_first_contact_ext *)(((u8 *)clc_v2) + clc_v2_len); + smc->conn.lgr->peer_os = fce->os_type; + smc->conn.lgr->peer_smc_release = fce->release; + if (smc_isascii(fce->hostname)) + memcpy(smc->conn.lgr->peer_hostname, fce->hostname, + SMC_MAX_HOSTNAME_LEN); +} + static void smcr_conn_save_peer_info(struct smc_sock *smc, struct smc_clc_msg_accept_confirm *clc) { @@ -451,16 +492,6 @@ static void smcr_conn_save_peer_info(struct smc_sock *smc, smc->conn.tx_off = bufsize * (smc->conn.peer_rmbe_idx - 1); } -static bool smc_isascii(char *hostname) -{ - int i; - - for (i = 0; i < SMC_MAX_HOSTNAME_LEN; i++) - if (!isascii(hostname[i])) - return false; - return true; -} - static void smcd_conn_save_peer_info(struct smc_sock *smc, struct smc_clc_msg_accept_confirm *clc) { @@ -472,22 +503,6 @@ static void smcd_conn_save_peer_info(struct smc_sock *smc, smc->conn.peer_rmbe_size = bufsize - sizeof(struct smcd_cdc_msg); atomic_set(&smc->conn.peer_rmbe_space, smc->conn.peer_rmbe_size); smc->conn.tx_off = bufsize * smc->conn.peer_rmbe_idx; - if (clc->hdr.version > SMC_V1 && - (clc->hdr.typev2 & SMC_FIRST_CONTACT_MASK)) { - struct smc_clc_msg_accept_confirm_v2 *clc_v2 = - (struct smc_clc_msg_accept_confirm_v2 *)clc; - struct smc_clc_first_contact_ext *fce = - (struct smc_clc_first_contact_ext *) - (((u8 *)clc_v2) + sizeof(*clc_v2)); - - memcpy(smc->conn.lgr->negotiated_eid, clc_v2->eid, - SMC_MAX_EID_LEN); - smc->conn.lgr->peer_os = fce->os_type; - smc->conn.lgr->peer_smc_release = fce->release; - if (smc_isascii(fce->hostname)) - memcpy(smc->conn.lgr->peer_hostname, fce->hostname, - SMC_MAX_HOSTNAME_LEN); - } } static void smc_conn_save_peer_info(struct smc_sock *smc, @@ -497,14 +512,16 @@ static void smc_conn_save_peer_info(struct smc_sock *smc, smcd_conn_save_peer_info(smc, clc); else smcr_conn_save_peer_info(smc, clc); + smc_conn_save_peer_info_fce(smc, clc); } static void smc_link_save_peer_info(struct smc_link *link, - struct smc_clc_msg_accept_confirm *clc) + struct smc_clc_msg_accept_confirm *clc, + struct smc_init_info *ini) { link->peer_qpn = ntoh24(clc->r0.qpn); - memcpy(link->peer_gid, clc->r0.lcl.gid, SMC_GID_SIZE); - memcpy(link->peer_mac, clc->r0.lcl.mac, sizeof(link->peer_mac)); + memcpy(link->peer_gid, ini->peer_gid, SMC_GID_SIZE); + memcpy(link->peer_mac, ini->peer_mac, sizeof(link->peer_mac)); link->peer_psn = ntoh24(clc->r0.psn); link->peer_mtu = clc->r0.qp_mtu; } @@ -608,7 +625,9 @@ static int smc_find_rdma_device(struct smc_sock *smc, struct smc_init_info *ini) * used for the internal TCP socket */ smc_pnet_find_roce_resource(smc->clcsock->sk, ini); - if (!ini->ib_dev) + if (!ini->check_smcrv2 && !ini->ib_dev) + return SMC_CLC_DECL_NOSMCRDEV; + if (ini->check_smcrv2 && !ini->smcrv2.ib_dev_v2) return SMC_CLC_DECL_NOSMCRDEV; return 0; } @@ -692,27 +711,42 @@ static int smc_find_proposal_devices(struct smc_sock *smc, int rc = 0; /* check if there is an ism device available */ - if (ini->smcd_version & SMC_V1) { - if (smc_find_ism_device(smc, ini) || - smc_connect_ism_vlan_setup(smc, ini)) { - if (ini->smc_type_v1 == SMC_TYPE_B) - ini->smc_type_v1 = SMC_TYPE_R; - else - ini->smc_type_v1 = SMC_TYPE_N; - } /* else ISM V1 is supported for this connection */ - if (smc_find_rdma_device(smc, ini)) { - if (ini->smc_type_v1 == SMC_TYPE_B) - ini->smc_type_v1 = SMC_TYPE_D; - else - ini->smc_type_v1 = SMC_TYPE_N; - } /* else RDMA is supported for this connection */ - } - if (smc_ism_is_v2_capable() && smc_find_ism_v2_device_clnt(smc, ini)) - ini->smc_type_v2 = SMC_TYPE_N; + if (!(ini->smcd_version & SMC_V1) || + smc_find_ism_device(smc, ini) || + smc_connect_ism_vlan_setup(smc, ini)) + ini->smcd_version &= ~SMC_V1; + /* else ISM V1 is supported for this connection */ + + /* check if there is an rdma device available */ + if (!(ini->smcr_version & SMC_V1) || + smc_find_rdma_device(smc, ini)) + ini->smcr_version &= ~SMC_V1; + /* else RDMA is supported for this connection */ + + ini->smc_type_v1 = smc_indicated_type(ini->smcd_version & SMC_V1, + ini->smcr_version & SMC_V1); + + /* check if there is an ism v2 device available */ + if (!(ini->smcd_version & SMC_V2) || + !smc_ism_is_v2_capable() || + smc_find_ism_v2_device_clnt(smc, ini)) + ini->smcd_version &= ~SMC_V2; + + /* check if there is an rdma v2 device available */ + ini->check_smcrv2 = true; + ini->smcrv2.saddr = smc->clcsock->sk->sk_rcv_saddr; + if (!(ini->smcr_version & SMC_V2) || + smc->clcsock->sk->sk_family != AF_INET || + !smc_clc_ueid_count() || + smc_find_rdma_device(smc, ini)) + ini->smcr_version &= ~SMC_V2; + ini->check_smcrv2 = false; + + ini->smc_type_v2 = smc_indicated_type(ini->smcd_version & SMC_V2, + ini->smcr_version & SMC_V2); /* if neither ISM nor RDMA are supported, fallback */ - if (!smcr_indicated(ini->smc_type_v1) && - ini->smc_type_v1 == SMC_TYPE_N && ini->smc_type_v2 == SMC_TYPE_N) + if (ini->smc_type_v1 == SMC_TYPE_N && ini->smc_type_v2 == SMC_TYPE_N) rc = SMC_CLC_DECL_NOSMCDEV; return rc; @@ -752,6 +786,64 @@ static int smc_connect_clc(struct smc_sock *smc, SMC_CLC_ACCEPT, CLC_WAIT_TIME); } +void smc_fill_gid_list(struct smc_link_group *lgr, + struct smc_gidlist *gidlist, + struct smc_ib_device *known_dev, u8 *known_gid) +{ + struct smc_init_info *alt_ini = NULL; + + memset(gidlist, 0, sizeof(*gidlist)); + memcpy(gidlist->list[gidlist->len++], known_gid, SMC_GID_SIZE); + + alt_ini = kzalloc(sizeof(*alt_ini), GFP_KERNEL); + if (!alt_ini) + goto out; + + alt_ini->vlan_id = lgr->vlan_id; + alt_ini->check_smcrv2 = true; + alt_ini->smcrv2.saddr = lgr->saddr; + smc_pnet_find_alt_roce(lgr, alt_ini, known_dev); + + if (!alt_ini->smcrv2.ib_dev_v2) + goto out; + + memcpy(gidlist->list[gidlist->len++], alt_ini->smcrv2.ib_gid_v2, + SMC_GID_SIZE); + +out: + kfree(alt_ini); +} + +static int smc_connect_rdma_v2_prepare(struct smc_sock *smc, + struct smc_clc_msg_accept_confirm *aclc, + struct smc_init_info *ini) +{ + struct smc_clc_msg_accept_confirm_v2 *clc_v2 = + (struct smc_clc_msg_accept_confirm_v2 *)aclc; + struct smc_clc_first_contact_ext *fce = + (struct smc_clc_first_contact_ext *) + (((u8 *)clc_v2) + sizeof(*clc_v2)); + + if (!ini->first_contact_peer || aclc->hdr.version == SMC_V1) + return 0; + + if (fce->v2_direct) { + memcpy(ini->smcrv2.nexthop_mac, &aclc->r0.lcl.mac, ETH_ALEN); + ini->smcrv2.uses_gateway = false; + } else { + if (smc_ib_find_route(smc->clcsock->sk->sk_rcv_saddr, + smc_ib_gid_to_ipv4(aclc->r0.lcl.gid), + ini->smcrv2.nexthop_mac, + &ini->smcrv2.uses_gateway)) + return SMC_CLC_DECL_NOROUTE; + if (!ini->smcrv2.uses_gateway) { + /* mismatch: peer claims indirect, but its direct */ + return SMC_CLC_DECL_NOINDIRECT; + } + } + return 0; +} + /* setup for RDMA connection of client */ static int smc_connect_rdma(struct smc_sock *smc, struct smc_clc_msg_accept_confirm *aclc, @@ -759,11 +851,18 @@ static int smc_connect_rdma(struct smc_sock *smc, { int i, reason_code = 0; struct smc_link *link; + u8 *eid = NULL; ini->is_smcd = false; - ini->ib_lcl = &aclc->r0.lcl; ini->ib_clcqpn = ntoh24(aclc->r0.qpn); ini->first_contact_peer = aclc->hdr.typev2 & SMC_FIRST_CONTACT_MASK; + memcpy(ini->peer_systemid, aclc->r0.lcl.id_for_peer, SMC_SYSTEMID_LEN); + memcpy(ini->peer_gid, aclc->r0.lcl.gid, SMC_GID_SIZE); + memcpy(ini->peer_mac, aclc->r0.lcl.mac, ETH_ALEN); + + reason_code = smc_connect_rdma_v2_prepare(smc, aclc, ini); + if (reason_code) + return reason_code; mutex_lock(&smc_client_lgr_pending); reason_code = smc_conn_create(smc, ini); @@ -785,8 +884,9 @@ static int smc_connect_rdma(struct smc_sock *smc, if (l->peer_qpn == ntoh24(aclc->r0.qpn) && !memcmp(l->peer_gid, &aclc->r0.lcl.gid, SMC_GID_SIZE) && - !memcmp(l->peer_mac, &aclc->r0.lcl.mac, - sizeof(l->peer_mac))) { + (aclc->hdr.version > SMC_V1 || + !memcmp(l->peer_mac, &aclc->r0.lcl.mac, + sizeof(l->peer_mac)))) { link = l; break; } @@ -805,7 +905,7 @@ static int smc_connect_rdma(struct smc_sock *smc, } if (ini->first_contact_local) - smc_link_save_peer_info(link, aclc); + smc_link_save_peer_info(link, aclc, ini); if (smc_rmb_rtoken_handling(&smc->conn, link, aclc)) { reason_code = SMC_CLC_DECL_ERR_RTOK; @@ -828,8 +928,18 @@ static int smc_connect_rdma(struct smc_sock *smc, } smc_rmb_sync_sg_for_device(&smc->conn); + if (aclc->hdr.version > SMC_V1) { + struct smc_clc_msg_accept_confirm_v2 *clc_v2 = + (struct smc_clc_msg_accept_confirm_v2 *)aclc; + + eid = clc_v2->r1.eid; + if (ini->first_contact_local) + smc_fill_gid_list(link->lgr, &ini->smcrv2.gidlist, + link->smcibdev, link->gid); + } + reason_code = smc_clc_send_confirm(smc, ini->first_contact_local, - SMC_V1, NULL); + aclc->hdr.version, eid, ini); if (reason_code) goto connect_abort; @@ -869,7 +979,7 @@ smc_v2_determine_accepted_chid(struct smc_clc_msg_accept_confirm_v2 *aclc, int i; for (i = 0; i < ini->ism_offered_cnt + 1; i++) { - if (ini->ism_chid[i] == ntohs(aclc->chid)) { + if (ini->ism_chid[i] == ntohs(aclc->d1.chid)) { ini->ism_selected = i; return 0; } @@ -923,11 +1033,11 @@ static int smc_connect_ism(struct smc_sock *smc, struct smc_clc_msg_accept_confirm_v2 *clc_v2 = (struct smc_clc_msg_accept_confirm_v2 *)aclc; - eid = clc_v2->eid; + eid = clc_v2->d1.eid; } rc = smc_clc_send_confirm(smc, ini->first_contact_local, - aclc->hdr.version, eid); + aclc->hdr.version, eid, NULL); if (rc) goto connect_abort; mutex_unlock(&smc_server_lgr_pending); @@ -950,17 +1060,24 @@ connect_abort: static int smc_connect_check_aclc(struct smc_init_info *ini, struct smc_clc_msg_accept_confirm *aclc) { - if ((aclc->hdr.typev1 == SMC_TYPE_R && - !smcr_indicated(ini->smc_type_v1)) || - (aclc->hdr.typev1 == SMC_TYPE_D && - ((!smcd_indicated(ini->smc_type_v1) && - !smcd_indicated(ini->smc_type_v2)) || - (aclc->hdr.version == SMC_V1 && - !smcd_indicated(ini->smc_type_v1)) || - (aclc->hdr.version == SMC_V2 && - !smcd_indicated(ini->smc_type_v2))))) + if (aclc->hdr.typev1 != SMC_TYPE_R && + aclc->hdr.typev1 != SMC_TYPE_D) return SMC_CLC_DECL_MODEUNSUPP; + if (aclc->hdr.version >= SMC_V2) { + if ((aclc->hdr.typev1 == SMC_TYPE_R && + !smcr_indicated(ini->smc_type_v2)) || + (aclc->hdr.typev1 == SMC_TYPE_D && + !smcd_indicated(ini->smc_type_v2))) + return SMC_CLC_DECL_MODEUNSUPP; + } else { + if ((aclc->hdr.typev1 == SMC_TYPE_R && + !smcr_indicated(ini->smc_type_v1)) || + (aclc->hdr.typev1 == SMC_TYPE_D && + !smcd_indicated(ini->smc_type_v1))) + return SMC_CLC_DECL_MODEUNSUPP; + } + return 0; } @@ -991,14 +1108,15 @@ static int __smc_connect(struct smc_sock *smc) return smc_connect_decline_fallback(smc, SMC_CLC_DECL_MEM, version); - ini->smcd_version = SMC_V1; - ini->smcd_version |= smc_ism_is_v2_capable() ? SMC_V2 : 0; + ini->smcd_version = SMC_V1 | SMC_V2; + ini->smcr_version = SMC_V1 | SMC_V2; ini->smc_type_v1 = SMC_TYPE_B; - ini->smc_type_v2 = smc_ism_is_v2_capable() ? SMC_TYPE_D : SMC_TYPE_N; + ini->smc_type_v2 = SMC_TYPE_B; /* get vlan id from IP device */ if (smc_vlan_by_tcpsk(smc->clcsock, ini)) { ini->smcd_version &= ~SMC_V1; + ini->smcr_version = 0; ini->smc_type_v1 = SMC_TYPE_N; if (!ini->smcd_version) { rc = SMC_CLC_DECL_GETVLANERR; @@ -1026,15 +1144,17 @@ static int __smc_connect(struct smc_sock *smc) /* check if smc modes and versions of CLC proposal and accept match */ rc = smc_connect_check_aclc(ini, aclc); version = aclc->hdr.version == SMC_V1 ? SMC_V1 : SMC_V2; - ini->smcd_version = version; if (rc) goto vlan_cleanup; /* depending on previous steps, connect using rdma or ism */ - if (aclc->hdr.typev1 == SMC_TYPE_R) + if (aclc->hdr.typev1 == SMC_TYPE_R) { + ini->smcr_version = version; rc = smc_connect_rdma(smc, aclc, ini); - else if (aclc->hdr.typev1 == SMC_TYPE_D) + } else if (aclc->hdr.typev1 == SMC_TYPE_D) { + ini->smcd_version = version; rc = smc_connect_ism(smc, aclc, ini); + } if (rc) goto vlan_cleanup; @@ -1315,7 +1435,7 @@ static int smcr_serv_conf_first_link(struct smc_sock *smc) smcr_lgr_set_type(link->lgr, SMC_LGR_SINGLE); /* initial contact - try to establish second link */ - smc_llc_srv_add_link(link); + smc_llc_srv_add_link(link, NULL); return 0; } @@ -1395,33 +1515,48 @@ static int smc_listen_v2_check(struct smc_sock *new_smc, ini->smc_type_v1 = pclc->hdr.typev1; ini->smc_type_v2 = pclc->hdr.typev2; - ini->smcd_version = ini->smc_type_v1 != SMC_TYPE_N ? SMC_V1 : 0; - if (pclc->hdr.version > SMC_V1) - ini->smcd_version |= - ini->smc_type_v2 != SMC_TYPE_N ? SMC_V2 : 0; - if (!(ini->smcd_version & SMC_V2)) { - rc = SMC_CLC_DECL_PEERNOSMC; - goto out; + ini->smcd_version = smcd_indicated(ini->smc_type_v1) ? SMC_V1 : 0; + ini->smcr_version = smcr_indicated(ini->smc_type_v1) ? SMC_V1 : 0; + if (pclc->hdr.version > SMC_V1) { + if (smcd_indicated(ini->smc_type_v2)) + ini->smcd_version |= SMC_V2; + if (smcr_indicated(ini->smc_type_v2)) + ini->smcr_version |= SMC_V2; } - if (!smc_ism_is_v2_capable()) { - ini->smcd_version &= ~SMC_V2; - rc = SMC_CLC_DECL_NOISM2SUPP; + if (!(ini->smcd_version & SMC_V2) && !(ini->smcr_version & SMC_V2)) { + rc = SMC_CLC_DECL_PEERNOSMC; goto out; } pclc_v2_ext = smc_get_clc_v2_ext(pclc); if (!pclc_v2_ext) { ini->smcd_version &= ~SMC_V2; + ini->smcr_version &= ~SMC_V2; rc = SMC_CLC_DECL_NOV2EXT; goto out; } pclc_smcd_v2_ext = smc_get_clc_smcd_v2_ext(pclc_v2_ext); - if (!pclc_smcd_v2_ext) { - ini->smcd_version &= ~SMC_V2; - rc = SMC_CLC_DECL_NOV2DEXT; + if (ini->smcd_version & SMC_V2) { + if (!smc_ism_is_v2_capable()) { + ini->smcd_version &= ~SMC_V2; + rc = SMC_CLC_DECL_NOISM2SUPP; + } else if (!pclc_smcd_v2_ext) { + ini->smcd_version &= ~SMC_V2; + rc = SMC_CLC_DECL_NOV2DEXT; + } else if (!pclc_v2_ext->hdr.eid_cnt && + !pclc_v2_ext->hdr.flag.seid) { + ini->smcd_version &= ~SMC_V2; + rc = SMC_CLC_DECL_NOUEID; + } + } + if (ini->smcr_version & SMC_V2) { + if (!pclc_v2_ext->hdr.eid_cnt) { + ini->smcr_version &= ~SMC_V2; + rc = SMC_CLC_DECL_NOUEID; + } } out: - if (!ini->smcd_version) + if (!ini->smcd_version && !ini->smcr_version) return rc; return 0; @@ -1541,10 +1676,6 @@ static void smc_find_ism_v2_device_serv(struct smc_sock *new_smc, pclc_smcd = smc_get_clc_msg_smcd(pclc); smc_v2_ext = smc_get_clc_v2_ext(pclc); smcd_v2_ext = smc_get_clc_smcd_v2_ext(smc_v2_ext); - if (!smcd_v2_ext) { - smc_find_ism_store_rc(SMC_CLC_DECL_NOV2DEXT, ini); - goto not_found; - } mutex_lock(&smcd_dev_list.mutex); if (pclc_smcd->ism.chid) @@ -1562,8 +1693,10 @@ static void smc_find_ism_v2_device_serv(struct smc_sock *new_smc, } mutex_unlock(&smcd_dev_list.mutex); - if (!ini->ism_dev[0]) + if (!ini->ism_dev[0]) { + smc_find_ism_store_rc(SMC_CLC_DECL_NOSMCD2DEV, ini); goto not_found; + } smc_ism_get_system_eid(&eid); if (!smc_clc_match_eid(ini->negotiated_eid, smc_v2_ext, @@ -1616,6 +1749,7 @@ static void smc_find_ism_v1_device_serv(struct smc_sock *new_smc, not_found: smc_find_ism_store_rc(rc, ini); + ini->smcd_version &= ~SMC_V1; ini->ism_dev[0] = NULL; ini->is_smcd = false; } @@ -1634,24 +1768,69 @@ static int smc_listen_rdma_reg(struct smc_sock *new_smc, bool local_first) return 0; } +static void smc_find_rdma_v2_device_serv(struct smc_sock *new_smc, + struct smc_clc_msg_proposal *pclc, + struct smc_init_info *ini) +{ + struct smc_clc_v2_extension *smc_v2_ext; + u8 smcr_version; + int rc; + + if (!(ini->smcr_version & SMC_V2) || !smcr_indicated(ini->smc_type_v2)) + goto not_found; + + smc_v2_ext = smc_get_clc_v2_ext(pclc); + if (!smc_clc_match_eid(ini->negotiated_eid, smc_v2_ext, NULL, NULL)) + goto not_found; + + /* prepare RDMA check */ + memcpy(ini->peer_systemid, pclc->lcl.id_for_peer, SMC_SYSTEMID_LEN); + memcpy(ini->peer_gid, smc_v2_ext->roce, SMC_GID_SIZE); + memcpy(ini->peer_mac, pclc->lcl.mac, ETH_ALEN); + ini->check_smcrv2 = true; + ini->smcrv2.clc_sk = new_smc->clcsock->sk; + ini->smcrv2.saddr = new_smc->clcsock->sk->sk_rcv_saddr; + ini->smcrv2.daddr = smc_ib_gid_to_ipv4(smc_v2_ext->roce); + rc = smc_find_rdma_device(new_smc, ini); + if (rc) { + smc_find_ism_store_rc(rc, ini); + goto not_found; + } + if (!ini->smcrv2.uses_gateway) + memcpy(ini->smcrv2.nexthop_mac, pclc->lcl.mac, ETH_ALEN); + + smcr_version = ini->smcr_version; + ini->smcr_version = SMC_V2; + rc = smc_listen_rdma_init(new_smc, ini); + if (!rc) + rc = smc_listen_rdma_reg(new_smc, ini->first_contact_local); + if (!rc) + return; + ini->smcr_version = smcr_version; + smc_find_ism_store_rc(rc, ini); + +not_found: + ini->smcr_version &= ~SMC_V2; + ini->check_smcrv2 = false; +} + static int smc_find_rdma_v1_device_serv(struct smc_sock *new_smc, struct smc_clc_msg_proposal *pclc, struct smc_init_info *ini) { int rc; - if (!smcr_indicated(ini->smc_type_v1)) + if (!(ini->smcr_version & SMC_V1) || !smcr_indicated(ini->smc_type_v1)) return SMC_CLC_DECL_NOSMCDEV; /* prepare RDMA check */ - ini->ib_lcl = &pclc->lcl; + memcpy(ini->peer_systemid, pclc->lcl.id_for_peer, SMC_SYSTEMID_LEN); + memcpy(ini->peer_gid, pclc->lcl.gid, SMC_GID_SIZE); + memcpy(ini->peer_mac, pclc->lcl.mac, ETH_ALEN); rc = smc_find_rdma_device(new_smc, ini); if (rc) { /* no RDMA device found */ - if (ini->smc_type_v1 == SMC_TYPE_B) - /* neither ISM nor RDMA device found */ - rc = SMC_CLC_DECL_NOSMCDEV; - return rc; + return SMC_CLC_DECL_NOSMCDEV; } rc = smc_listen_rdma_init(new_smc, ini); if (rc) @@ -1664,51 +1843,60 @@ static int smc_listen_find_device(struct smc_sock *new_smc, struct smc_clc_msg_proposal *pclc, struct smc_init_info *ini) { - int rc; + int prfx_rc; /* check for ISM device matching V2 proposed device */ smc_find_ism_v2_device_serv(new_smc, pclc, ini); if (ini->ism_dev[0]) return 0; - if (!(ini->smcd_version & SMC_V1)) - return ini->rc ?: SMC_CLC_DECL_NOSMCD2DEV; - - /* check for matching IP prefix and subnet length */ - rc = smc_listen_prfx_check(new_smc, pclc); - if (rc) - return ini->rc ?: rc; + /* check for matching IP prefix and subnet length (V1) */ + prfx_rc = smc_listen_prfx_check(new_smc, pclc); + if (prfx_rc) + smc_find_ism_store_rc(prfx_rc, ini); /* get vlan id from IP device */ if (smc_vlan_by_tcpsk(new_smc->clcsock, ini)) return ini->rc ?: SMC_CLC_DECL_GETVLANERR; /* check for ISM device matching V1 proposed device */ - smc_find_ism_v1_device_serv(new_smc, pclc, ini); + if (!prfx_rc) + smc_find_ism_v1_device_serv(new_smc, pclc, ini); if (ini->ism_dev[0]) return 0; - if (pclc->hdr.typev1 == SMC_TYPE_D) + if (!smcr_indicated(pclc->hdr.typev1) && + !smcr_indicated(pclc->hdr.typev2)) /* skip RDMA and decline */ return ini->rc ?: SMC_CLC_DECL_NOSMCDDEV; - /* check if RDMA is available */ - rc = smc_find_rdma_v1_device_serv(new_smc, pclc, ini); - smc_find_ism_store_rc(rc, ini); + /* check if RDMA V2 is available */ + smc_find_rdma_v2_device_serv(new_smc, pclc, ini); + if (ini->smcrv2.ib_dev_v2) + return 0; - return (!rc) ? 0 : ini->rc; + /* check if RDMA V1 is available */ + if (!prfx_rc) { + int rc; + + rc = smc_find_rdma_v1_device_serv(new_smc, pclc, ini); + smc_find_ism_store_rc(rc, ini); + return (!rc) ? 0 : ini->rc; + } + return SMC_CLC_DECL_NOSMCDEV; } /* listen worker: finish RDMA setup */ static int smc_listen_rdma_finish(struct smc_sock *new_smc, struct smc_clc_msg_accept_confirm *cclc, - bool local_first) + bool local_first, + struct smc_init_info *ini) { struct smc_link *link = new_smc->conn.lnk; int reason_code = 0; if (local_first) - smc_link_save_peer_info(link, cclc); + smc_link_save_peer_info(link, cclc, ini); if (smc_rmb_rtoken_handling(&new_smc->conn, link, cclc)) return SMC_CLC_DECL_ERR_RTOK; @@ -1729,12 +1917,13 @@ static void smc_listen_work(struct work_struct *work) { struct smc_sock *new_smc = container_of(work, struct smc_sock, smc_listen_work); - u8 version = smc_ism_is_v2_capable() ? SMC_V2 : SMC_V1; struct socket *newclcsock = new_smc->clcsock; struct smc_clc_msg_accept_confirm *cclc; struct smc_clc_msg_proposal_area *buf; struct smc_clc_msg_proposal *pclc; struct smc_init_info *ini = NULL; + u8 proposal_version = SMC_V1; + u8 accept_version; int rc = 0; if (new_smc->listen_smc->sk.sk_state != SMC_LISTEN) @@ -1765,7 +1954,9 @@ static void smc_listen_work(struct work_struct *work) SMC_CLC_PROPOSAL, CLC_WAIT_TIME); if (rc) goto out_decl; - version = pclc->hdr.version == SMC_V1 ? SMC_V1 : version; + + if (pclc->hdr.version > SMC_V1) + proposal_version = SMC_V2; /* IPSec connections opt out of SMC optimizations */ if (using_ipsec(new_smc)) { @@ -1795,9 +1986,9 @@ static void smc_listen_work(struct work_struct *work) goto out_unlock; /* send SMC Accept CLC message */ + accept_version = ini->is_smcd ? ini->smcd_version : ini->smcr_version; rc = smc_clc_send_accept(new_smc, ini->first_contact_local, - ini->smcd_version == SMC_V2 ? SMC_V2 : SMC_V1, - ini->negotiated_eid); + accept_version, ini->negotiated_eid); if (rc) goto out_unlock; @@ -1819,7 +2010,7 @@ static void smc_listen_work(struct work_struct *work) /* finish worker */ if (!ini->is_smcd) { rc = smc_listen_rdma_finish(new_smc, cclc, - ini->first_contact_local); + ini->first_contact_local, ini); if (rc) goto out_unlock; mutex_unlock(&smc_server_lgr_pending); @@ -1833,7 +2024,7 @@ out_unlock: mutex_unlock(&smc_server_lgr_pending); out_decl: smc_listen_decline(new_smc, rc, ini ? ini->first_contact_local : 0, - version); + proposal_version); out_free: kfree(ini); kfree(buf); diff --git a/net/smc/smc.h b/net/smc/smc.h index 5e7def3ab730..f4286ca1f228 100644 --- a/net/smc/smc.h +++ b/net/smc/smc.h @@ -56,7 +56,20 @@ enum smc_state { /* possible states of an SMC socket */ struct smc_link_group; struct smc_wr_rx_hdr { /* common prefix part of LLC and CDC to demultiplex */ - u8 type; + union { + u8 type; +#if defined(__BIG_ENDIAN_BITFIELD) + struct { + u8 llc_version:4, + llc_type:4; + }; +#elif defined(__LITTLE_ENDIAN_BITFIELD) + struct { + u8 llc_type:4, + llc_version:4; + }; +#endif + }; } __aligned(1); struct smc_cdc_conn_state_flags { @@ -286,7 +299,12 @@ static inline bool using_ipsec(struct smc_sock *smc) } #endif +struct smc_gidlist; + struct sock *smc_accept_dequeue(struct sock *parent, struct socket *new_sock); void smc_close_non_accepted(struct sock *sk); +void smc_fill_gid_list(struct smc_link_group *lgr, + struct smc_gidlist *gidlist, + struct smc_ib_device *known_dev, u8 *known_gid); #endif /* __SMC_H */ diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index 1cc8a76b39f9..8409ab71a5e4 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -31,6 +31,7 @@ #define SMCR_CLC_ACCEPT_CONFIRM_LEN 68 #define SMCD_CLC_ACCEPT_CONFIRM_LEN 48 #define SMCD_CLC_ACCEPT_CONFIRM_LEN_V2 78 +#define SMCR_CLC_ACCEPT_CONFIRM_LEN_V2 108 #define SMC_CLC_RECV_BUF_LEN 100 /* eye catcher "SMCR" EBCDIC for CLC messages */ @@ -114,6 +115,17 @@ err_out: return rc; } +int smc_clc_ueid_count(void) +{ + int count; + + read_lock(&smc_clc_eid_table.lock); + count = smc_clc_eid_table.ueid_cnt; + read_unlock(&smc_clc_eid_table.lock); + + return count; +} + int smc_nl_add_ueid(struct sk_buff *skb, struct genl_info *info) { struct nlattr *nla_ueid = info->attrs[SMC_NLA_EID_TABLE_ENTRY]; @@ -298,7 +310,8 @@ bool smc_clc_match_eid(u8 *negotiated_eid, negotiated_eid[0] = 0; read_lock(&smc_clc_eid_table.lock); - if (smc_clc_eid_table.seid_enabled && + if (peer_eid && local_eid && + smc_clc_eid_table.seid_enabled && smc_v2_ext->hdr.flag.seid && !memcmp(peer_eid, local_eid, SMC_MAX_EID_LEN)) { memcpy(negotiated_eid, peer_eid, SMC_MAX_EID_LEN); @@ -380,6 +393,27 @@ smc_clc_msg_acc_conf_valid(struct smc_clc_msg_accept_confirm_v2 *clc_v2) (ntohs(hdr->length) != SMCD_CLC_ACCEPT_CONFIRM_LEN_V2 + sizeof(struct smc_clc_first_contact_ext))) return false; + if (hdr->typev1 == SMC_TYPE_R && + ntohs(hdr->length) < SMCR_CLC_ACCEPT_CONFIRM_LEN_V2) + return false; + } + return true; +} + +/* check arriving CLC decline */ +static bool +smc_clc_msg_decl_valid(struct smc_clc_msg_decline *dclc) +{ + struct smc_clc_msg_hdr *hdr = &dclc->hdr; + + if (hdr->typev1 != SMC_TYPE_R && hdr->typev1 != SMC_TYPE_D) + return false; + if (hdr->version == SMC_V1) { + if (ntohs(hdr->length) != sizeof(struct smc_clc_msg_decline)) + return false; + } else { + if (ntohs(hdr->length) != sizeof(struct smc_clc_msg_decline_v2)) + return false; } return true; } @@ -425,9 +459,9 @@ static bool smc_clc_msg_hdr_valid(struct smc_clc_msg_hdr *clcm, bool check_trl) break; case SMC_CLC_DECLINE: dclc = (struct smc_clc_msg_decline *)clcm; - if (ntohs(dclc->hdr.length) != sizeof(*dclc)) + if (!smc_clc_msg_decl_valid(dclc)) return false; - trl = &dclc->trl; + check_trl = false; break; default: return false; @@ -726,15 +760,16 @@ out: /* send CLC DECLINE message across internal TCP socket */ int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info, u8 version) { - struct smc_clc_msg_decline dclc; + struct smc_clc_msg_decline *dclc_v1; + struct smc_clc_msg_decline_v2 dclc; struct msghdr msg; + int len, send_len; struct kvec vec; - int len; + dclc_v1 = (struct smc_clc_msg_decline *)&dclc; memset(&dclc, 0, sizeof(dclc)); memcpy(dclc.hdr.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER)); dclc.hdr.type = SMC_CLC_DECLINE; - dclc.hdr.length = htons(sizeof(struct smc_clc_msg_decline)); dclc.hdr.version = version; dclc.os_type = version == SMC_V1 ? 0 : SMC_CLC_OS_LINUX; dclc.hdr.typev2 = (peer_diag_info == SMC_CLC_DECL_SYNCERR) ? @@ -744,14 +779,22 @@ int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info, u8 version) memcpy(dclc.id_for_peer, local_systemid, sizeof(local_systemid)); dclc.peer_diagnosis = htonl(peer_diag_info); - memcpy(dclc.trl.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER)); + if (version == SMC_V1) { + memcpy(dclc_v1->trl.eyecatcher, SMC_EYECATCHER, + sizeof(SMC_EYECATCHER)); + send_len = sizeof(*dclc_v1); + } else { + memcpy(dclc.trl.eyecatcher, SMC_EYECATCHER, + sizeof(SMC_EYECATCHER)); + send_len = sizeof(dclc); + } + dclc.hdr.length = htons(send_len); memset(&msg, 0, sizeof(msg)); vec.iov_base = &dclc; - vec.iov_len = sizeof(struct smc_clc_msg_decline); - len = kernel_sendmsg(smc->clcsock, &msg, &vec, 1, - sizeof(struct smc_clc_msg_decline)); - if (len < 0 || len < sizeof(struct smc_clc_msg_decline)) + vec.iov_len = send_len; + len = kernel_sendmsg(smc->clcsock, &msg, &vec, 1, send_len); + if (len < 0 || len < send_len) len = -EPROTO; return len > 0 ? 0 : len; } @@ -833,8 +876,8 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini) } else { struct smc_clc_eid_entry *ueident; u16 v2_ext_offset; - u8 *eid = NULL; + v2_ext->hdr.flag.release = SMC_RELEASE; v2_ext_offset = sizeof(*pclc_smcd) - offsetofend(struct smc_clc_msg_smcd, v2_ext_offset); if (ini->smc_type_v1 != SMC_TYPE_N) @@ -842,6 +885,7 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini) pclc_prfx->ipv6_prefixes_cnt * sizeof(ipv6_prfx[0]); pclc_smcd->v2_ext_offset = htons(v2_ext_offset); + plen += sizeof(*v2_ext); read_lock(&smc_clc_eid_table.lock); v2_ext->hdr.eid_cnt = smc_clc_eid_table.ueid_cnt; @@ -851,10 +895,13 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini) memcpy(v2_ext->user_eids[i++], ueident->eid, sizeof(ueident->eid)); } - v2_ext->hdr.flag.seid = smc_clc_eid_table.seid_enabled; read_unlock(&smc_clc_eid_table.lock); + } + if (smcd_indicated(ini->smc_type_v2)) { + u8 *eid = NULL; + + v2_ext->hdr.flag.seid = smc_clc_eid_table.seid_enabled; v2_ext->hdr.ism_gid_cnt = ini->ism_offered_cnt; - v2_ext->hdr.flag.release = SMC_RELEASE; v2_ext->hdr.smcd_v2_ext_offset = htons(sizeof(*v2_ext) - offsetofend(struct smc_clnt_opts_area_hdr, smcd_v2_ext_offset) + @@ -862,7 +909,7 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini) smc_ism_get_system_eid(&eid); if (eid && v2_ext->hdr.flag.seid) memcpy(smcd_v2_ext->system_eid, eid, SMC_MAX_EID_LEN); - plen += sizeof(*v2_ext) + sizeof(*smcd_v2_ext); + plen += sizeof(*smcd_v2_ext); if (ini->ism_offered_cnt) { for (i = 1; i <= ini->ism_offered_cnt; i++) { gidchids[i - 1].gid = @@ -874,6 +921,9 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini) sizeof(struct smc_clc_smcd_gid_chid); } } + if (smcr_indicated(ini->smc_type_v2)) + memcpy(v2_ext->roce, ini->smcrv2.ib_gid_v2, SMC_GID_SIZE); + pclc_base->hdr.length = htons(plen); memcpy(trl->eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER)); @@ -897,12 +947,14 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini) vec[i].iov_base = v2_ext; vec[i++].iov_len = sizeof(*v2_ext) + (v2_ext->hdr.eid_cnt * SMC_MAX_EID_LEN); - vec[i].iov_base = smcd_v2_ext; - vec[i++].iov_len = sizeof(*smcd_v2_ext); - if (ini->ism_offered_cnt) { - vec[i].iov_base = gidchids; - vec[i++].iov_len = ini->ism_offered_cnt * + if (smcd_indicated(ini->smc_type_v2)) { + vec[i].iov_base = smcd_v2_ext; + vec[i++].iov_len = sizeof(*smcd_v2_ext); + if (ini->ism_offered_cnt) { + vec[i].iov_base = gidchids; + vec[i++].iov_len = ini->ism_offered_cnt * sizeof(struct smc_clc_smcd_gid_chid); + } } } vec[i].iov_base = trl; @@ -925,13 +977,14 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini) static int smc_clc_send_confirm_accept(struct smc_sock *smc, struct smc_clc_msg_accept_confirm_v2 *clc_v2, int first_contact, u8 version, - u8 *eid) + u8 *eid, struct smc_init_info *ini) { struct smc_connection *conn = &smc->conn; struct smc_clc_msg_accept_confirm *clc; struct smc_clc_first_contact_ext fce; + struct smc_clc_fce_gid_ext gle; struct smc_clc_msg_trail trl; - struct kvec vec[3]; + struct kvec vec[5]; struct msghdr msg; int i, len; @@ -953,9 +1006,10 @@ static int smc_clc_send_confirm_accept(struct smc_sock *smc, if (version == SMC_V1) { clc->hdr.length = htons(SMCD_CLC_ACCEPT_CONFIRM_LEN); } else { - clc_v2->chid = htons(smc_ism_get_chid(conn->lgr->smcd)); - if (eid[0]) - memcpy(clc_v2->eid, eid, SMC_MAX_EID_LEN); + clc_v2->d1.chid = + htons(smc_ism_get_chid(conn->lgr->smcd)); + if (eid && eid[0]) + memcpy(clc_v2->d1.eid, eid, SMC_MAX_EID_LEN); len = SMCD_CLC_ACCEPT_CONFIRM_LEN_V2; if (first_contact) smc_clc_fill_fce(&fce, &len); @@ -994,6 +1048,26 @@ static int smc_clc_send_confirm_accept(struct smc_sock *smc, clc->r0.rmb_dma_addr = cpu_to_be64((u64)sg_dma_address (conn->rmb_desc->sgt[link->link_idx].sgl)); hton24(clc->r0.psn, link->psn_initial); + if (version == SMC_V1) { + clc->hdr.length = htons(SMCR_CLC_ACCEPT_CONFIRM_LEN); + } else { + if (eid && eid[0]) + memcpy(clc_v2->r1.eid, eid, SMC_MAX_EID_LEN); + len = SMCR_CLC_ACCEPT_CONFIRM_LEN_V2; + if (first_contact) { + smc_clc_fill_fce(&fce, &len); + fce.v2_direct = !link->lgr->uses_gateway; + memset(&gle, 0, sizeof(gle)); + if (ini && clc->hdr.type == SMC_CLC_CONFIRM) { + gle.gid_cnt = ini->smcrv2.gidlist.len; + len += sizeof(gle); + len += gle.gid_cnt * sizeof(gle.gid[0]); + } else { + len += sizeof(gle.reserved); + } + } + clc_v2->hdr.length = htons(len); + } memcpy(trl.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER)); } @@ -1001,7 +1075,10 @@ static int smc_clc_send_confirm_accept(struct smc_sock *smc, i = 0; vec[i].iov_base = clc_v2; if (version > SMC_V1) - vec[i++].iov_len = SMCD_CLC_ACCEPT_CONFIRM_LEN_V2 - sizeof(trl); + vec[i++].iov_len = (clc->hdr.typev1 == SMC_TYPE_D ? + SMCD_CLC_ACCEPT_CONFIRM_LEN_V2 : + SMCR_CLC_ACCEPT_CONFIRM_LEN_V2) - + sizeof(trl); else vec[i++].iov_len = (clc->hdr.typev1 == SMC_TYPE_D ? SMCD_CLC_ACCEPT_CONFIRM_LEN : @@ -1010,6 +1087,18 @@ static int smc_clc_send_confirm_accept(struct smc_sock *smc, if (version > SMC_V1 && first_contact) { vec[i].iov_base = &fce; vec[i++].iov_len = sizeof(fce); + if (!conn->lgr->is_smcd) { + if (clc->hdr.type == SMC_CLC_CONFIRM) { + vec[i].iov_base = &gle; + vec[i++].iov_len = sizeof(gle); + vec[i].iov_base = &ini->smcrv2.gidlist.list; + vec[i++].iov_len = gle.gid_cnt * + sizeof(gle.gid[0]); + } else { + vec[i].iov_base = &gle.reserved; + vec[i++].iov_len = sizeof(gle.reserved); + } + } } vec[i].iov_base = &trl; vec[i++].iov_len = sizeof(trl); @@ -1019,7 +1108,7 @@ static int smc_clc_send_confirm_accept(struct smc_sock *smc, /* send CLC CONFIRM message across internal TCP socket */ int smc_clc_send_confirm(struct smc_sock *smc, bool clnt_first_contact, - u8 version, u8 *eid) + u8 version, u8 *eid, struct smc_init_info *ini) { struct smc_clc_msg_accept_confirm_v2 cclc_v2; int reason_code = 0; @@ -1029,7 +1118,7 @@ int smc_clc_send_confirm(struct smc_sock *smc, bool clnt_first_contact, memset(&cclc_v2, 0, sizeof(cclc_v2)); cclc_v2.hdr.type = SMC_CLC_CONFIRM; len = smc_clc_send_confirm_accept(smc, &cclc_v2, clnt_first_contact, - version, eid); + version, eid, ini); if (len < ntohs(cclc_v2.hdr.length)) { if (len >= 0) { reason_code = -ENETUNREACH; @@ -1052,7 +1141,7 @@ int smc_clc_send_accept(struct smc_sock *new_smc, bool srv_first_contact, memset(&aclc_v2, 0, sizeof(aclc_v2)); aclc_v2.hdr.type = SMC_CLC_ACCEPT; len = smc_clc_send_confirm_accept(new_smc, &aclc_v2, srv_first_contact, - version, negotiated_eid); + version, negotiated_eid, NULL); if (len < ntohs(aclc_v2.hdr.length)) len = len >= 0 ? -EPROTO : -new_smc->clcsock->sk->sk_err; diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h index 974d01d16bb5..83f02f131fc0 100644 --- a/net/smc/smc_clc.h +++ b/net/smc/smc_clc.h @@ -44,6 +44,7 @@ #define SMC_CLC_DECL_NOV2DEXT 0x03030005 /* peer sent no clc SMC-Dv2 ext. */ #define SMC_CLC_DECL_NOSEID 0x03030006 /* peer sent no SEID */ #define SMC_CLC_DECL_NOSMCD2DEV 0x03030007 /* no SMC-Dv2 device found */ +#define SMC_CLC_DECL_NOUEID 0x03030008 /* peer sent no UEID */ #define SMC_CLC_DECL_MODEUNSUPP 0x03040000 /* smc modes do not match (R or D)*/ #define SMC_CLC_DECL_RMBE_EC 0x03050000 /* peer has eyecatcher in RMBE */ #define SMC_CLC_DECL_OPTUNSUPP 0x03060000 /* fastopen sockopt not supported */ @@ -54,6 +55,8 @@ #define SMC_CLC_DECL_NOSRVLINK 0x030b0000 /* SMC-R link from srv not found */ #define SMC_CLC_DECL_VERSMISMAT 0x030c0000 /* SMC version mismatch */ #define SMC_CLC_DECL_MAX_DMB 0x030d0000 /* SMC-D DMB limit exceeded */ +#define SMC_CLC_DECL_NOROUTE 0x030e0000 /* SMC-Rv2 conn. no route to peer */ +#define SMC_CLC_DECL_NOINDIRECT 0x030f0000 /* SMC-Rv2 conn. indirect mismatch*/ #define SMC_CLC_DECL_SYNCERR 0x04000000 /* synchronization error */ #define SMC_CLC_DECL_PEERDECL 0x05000000 /* peer declined during handshake */ #define SMC_CLC_DECL_INTERR 0x09990000 /* internal error */ @@ -213,11 +216,14 @@ struct smcd_clc_msg_accept_confirm_common { /* SMCD accept/confirm */ #define SMC_CLC_OS_AIX 3 struct smc_clc_first_contact_ext { - u8 reserved1; #if defined(__BIG_ENDIAN_BITFIELD) + u8 v2_direct : 1, + reserved : 7; u8 os_type : 4, release : 4; #elif defined(__LITTLE_ENDIAN_BITFIELD) + u8 reserved : 7, + v2_direct : 1; u8 release : 4, os_type : 4; #endif @@ -225,6 +231,13 @@ struct smc_clc_first_contact_ext { u8 hostname[SMC_MAX_HOSTNAME_LEN]; }; +struct smc_clc_fce_gid_ext { + u8 reserved[16]; + u8 gid_cnt; + u8 reserved2[3]; + u8 gid[][SMC_GID_SIZE]; +}; + struct smc_clc_msg_accept_confirm { /* clc accept / confirm message */ struct smc_clc_msg_hdr hdr; union { @@ -239,13 +252,17 @@ struct smc_clc_msg_accept_confirm { /* clc accept / confirm message */ struct smc_clc_msg_accept_confirm_v2 { /* clc accept / confirm message */ struct smc_clc_msg_hdr hdr; union { - struct smcr_clc_msg_accept_confirm r0; /* SMC-R */ + struct { /* SMC-R */ + struct smcr_clc_msg_accept_confirm r0; + u8 eid[SMC_MAX_EID_LEN]; + u8 reserved6[8]; + } r1; struct { /* SMC-D */ struct smcd_clc_msg_accept_confirm_common d0; __be16 chid; u8 eid[SMC_MAX_EID_LEN]; u8 reserved5[8]; - }; + } d1; }; }; @@ -264,6 +281,24 @@ struct smc_clc_msg_decline { /* clc decline message */ struct smc_clc_msg_trail trl; /* eye catcher "SMCD" or "SMCR" EBCDIC */ } __aligned(4); +#define SMC_DECL_DIAG_COUNT_V2 4 /* no. of additional peer diagnosis codes */ + +struct smc_clc_msg_decline_v2 { /* clc decline message */ + struct smc_clc_msg_hdr hdr; + u8 id_for_peer[SMC_SYSTEMID_LEN]; /* sender peer_id */ + __be32 peer_diagnosis; /* diagnosis information */ +#if defined(__BIG_ENDIAN_BITFIELD) + u8 os_type : 4, + reserved : 4; +#elif defined(__LITTLE_ENDIAN_BITFIELD) + u8 reserved : 4, + os_type : 4; +#endif + u8 reserved2[3]; + __be32 peer_diagnosis_v2[SMC_DECL_DIAG_COUNT_V2]; + struct smc_clc_msg_trail trl; /* eye catcher "SMCD" or "SMCR" EBCDIC */ +} __aligned(4); + /* determine start of the prefix area within the proposal message */ static inline struct smc_clc_msg_proposal_prefix * smc_clc_proposal_get_prefix(struct smc_clc_msg_proposal *pclc) @@ -282,6 +317,17 @@ static inline bool smcd_indicated(int smc_type) return smc_type == SMC_TYPE_D || smc_type == SMC_TYPE_B; } +static inline u8 smc_indicated_type(int is_smcd, int is_smcr) +{ + if (is_smcd && is_smcr) + return SMC_TYPE_B; + if (is_smcd) + return SMC_TYPE_D; + if (is_smcr) + return SMC_TYPE_R; + return SMC_TYPE_N; +} + /* get SMC-D info from proposal message */ static inline struct smc_clc_msg_smcd * smc_get_clc_msg_smcd(struct smc_clc_msg_proposal *prop) @@ -334,7 +380,7 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen, int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info, u8 version); int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini); int smc_clc_send_confirm(struct smc_sock *smc, bool clnt_first_contact, - u8 version, u8 *eid); + u8 version, u8 *eid, struct smc_init_info *ini); int smc_clc_send_accept(struct smc_sock *smc, bool srv_first_contact, u8 version, u8 *negotiated_eid); void smc_clc_init(void) __init; @@ -343,6 +389,7 @@ void smc_clc_get_hostname(u8 **host); bool smc_clc_match_eid(u8 *negotiated_eid, struct smc_clc_v2_extension *smc_v2_ext, u8 *peer_eid, u8 *local_eid); +int smc_clc_ueid_count(void); int smc_nl_dump_ueid(struct sk_buff *skb, struct netlink_callback *cb); int smc_nl_add_ueid(struct sk_buff *skb, struct genl_info *info); int smc_nl_remove_ueid(struct sk_buff *skb, struct genl_info *info); diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 4d463701a759..8e642f8f334f 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -244,6 +244,8 @@ int smc_nl_get_sys_info(struct sk_buff *skb, struct netlink_callback *cb) goto errattr; if (nla_put_u8(skb, SMC_NLA_SYS_IS_ISM_V2, smc_ism_is_v2_capable())) goto errattr; + if (nla_put_u8(skb, SMC_NLA_SYS_IS_SMCR_V2, true)) + goto errattr; smc_clc_get_hostname(&host); if (host) { memcpy(hostname, host, SMC_MAX_HOSTNAME_LEN); @@ -271,12 +273,65 @@ errmsg: return skb->len; } +/* Fill SMC_NLA_LGR_D_V2_COMMON/SMC_NLA_LGR_R_V2_COMMON nested attributes */ +static int smc_nl_fill_lgr_v2_common(struct smc_link_group *lgr, + struct sk_buff *skb, + struct netlink_callback *cb, + struct nlattr *v2_attrs) +{ + char smc_host[SMC_MAX_HOSTNAME_LEN + 1]; + char smc_eid[SMC_MAX_EID_LEN + 1]; + + if (nla_put_u8(skb, SMC_NLA_LGR_V2_VER, lgr->smc_version)) + goto errv2attr; + if (nla_put_u8(skb, SMC_NLA_LGR_V2_REL, lgr->peer_smc_release)) + goto errv2attr; + if (nla_put_u8(skb, SMC_NLA_LGR_V2_OS, lgr->peer_os)) + goto errv2attr; + memcpy(smc_host, lgr->peer_hostname, SMC_MAX_HOSTNAME_LEN); + smc_host[SMC_MAX_HOSTNAME_LEN] = 0; + if (nla_put_string(skb, SMC_NLA_LGR_V2_PEER_HOST, smc_host)) + goto errv2attr; + memcpy(smc_eid, lgr->negotiated_eid, SMC_MAX_EID_LEN); + smc_eid[SMC_MAX_EID_LEN] = 0; + if (nla_put_string(skb, SMC_NLA_LGR_V2_NEG_EID, smc_eid)) + goto errv2attr; + + nla_nest_end(skb, v2_attrs); + return 0; + +errv2attr: + nla_nest_cancel(skb, v2_attrs); + return -EMSGSIZE; +} + +static int smc_nl_fill_smcr_lgr_v2(struct smc_link_group *lgr, + struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct nlattr *v2_attrs; + + v2_attrs = nla_nest_start(skb, SMC_NLA_LGR_R_V2); + if (!v2_attrs) + goto errattr; + if (nla_put_u8(skb, SMC_NLA_LGR_R_V2_DIRECT, !lgr->uses_gateway)) + goto errv2attr; + + nla_nest_end(skb, v2_attrs); + return 0; + +errv2attr: + nla_nest_cancel(skb, v2_attrs); +errattr: + return -EMSGSIZE; +} + static int smc_nl_fill_lgr(struct smc_link_group *lgr, struct sk_buff *skb, struct netlink_callback *cb) { char smc_target[SMC_MAX_PNETID_LEN + 1]; - struct nlattr *attrs; + struct nlattr *attrs, *v2_attrs; attrs = nla_nest_start(skb, SMC_GEN_LGR_SMCR); if (!attrs) @@ -296,6 +351,15 @@ static int smc_nl_fill_lgr(struct smc_link_group *lgr, smc_target[SMC_MAX_PNETID_LEN] = 0; if (nla_put_string(skb, SMC_NLA_LGR_R_PNETID, smc_target)) goto errattr; + if (lgr->smc_version > SMC_V1) { + v2_attrs = nla_nest_start(skb, SMC_NLA_LGR_R_V2_COMMON); + if (!v2_attrs) + goto errattr; + if (smc_nl_fill_lgr_v2_common(lgr, skb, cb, v2_attrs)) + goto errattr; + if (smc_nl_fill_smcr_lgr_v2(lgr, skb, cb)) + goto errattr; + } nla_nest_end(skb, attrs); return 0; @@ -428,10 +492,7 @@ static int smc_nl_fill_smcd_lgr(struct smc_link_group *lgr, struct sk_buff *skb, struct netlink_callback *cb) { - char smc_host[SMC_MAX_HOSTNAME_LEN + 1]; char smc_pnet[SMC_MAX_PNETID_LEN + 1]; - char smc_eid[SMC_MAX_EID_LEN + 1]; - struct nlattr *v2_attrs; struct nlattr *attrs; void *nlh; @@ -463,32 +524,19 @@ static int smc_nl_fill_smcd_lgr(struct smc_link_group *lgr, smc_pnet[SMC_MAX_PNETID_LEN] = 0; if (nla_put_string(skb, SMC_NLA_LGR_D_PNETID, smc_pnet)) goto errattr; + if (lgr->smc_version > SMC_V1) { + struct nlattr *v2_attrs; - v2_attrs = nla_nest_start(skb, SMC_NLA_LGR_V2); - if (!v2_attrs) - goto errattr; - if (nla_put_u8(skb, SMC_NLA_LGR_V2_VER, lgr->smc_version)) - goto errv2attr; - if (nla_put_u8(skb, SMC_NLA_LGR_V2_REL, lgr->peer_smc_release)) - goto errv2attr; - if (nla_put_u8(skb, SMC_NLA_LGR_V2_OS, lgr->peer_os)) - goto errv2attr; - memcpy(smc_host, lgr->peer_hostname, SMC_MAX_HOSTNAME_LEN); - smc_host[SMC_MAX_HOSTNAME_LEN] = 0; - if (nla_put_string(skb, SMC_NLA_LGR_V2_PEER_HOST, smc_host)) - goto errv2attr; - memcpy(smc_eid, lgr->negotiated_eid, SMC_MAX_EID_LEN); - smc_eid[SMC_MAX_EID_LEN] = 0; - if (nla_put_string(skb, SMC_NLA_LGR_V2_NEG_EID, smc_eid)) - goto errv2attr; - - nla_nest_end(skb, v2_attrs); + v2_attrs = nla_nest_start(skb, SMC_NLA_LGR_D_V2_COMMON); + if (!v2_attrs) + goto errattr; + if (smc_nl_fill_lgr_v2_common(lgr, skb, cb, v2_attrs)) + goto errattr; + } nla_nest_end(skb, attrs); genlmsg_end(skb, nlh); return 0; -errv2attr: - nla_nest_cancel(skb, v2_attrs); errattr: nla_nest_cancel(skb, attrs); errout: @@ -684,24 +732,30 @@ static void smcr_copy_dev_info_to_link(struct smc_link *link) int smcr_link_init(struct smc_link_group *lgr, struct smc_link *lnk, u8 link_idx, struct smc_init_info *ini) { + struct smc_ib_device *smcibdev; u8 rndvec[3]; int rc; - get_device(&ini->ib_dev->ibdev->dev); - atomic_inc(&ini->ib_dev->lnk_cnt); + if (lgr->smc_version == SMC_V2) { + lnk->smcibdev = ini->smcrv2.ib_dev_v2; + lnk->ibport = ini->smcrv2.ib_port_v2; + } else { + lnk->smcibdev = ini->ib_dev; + lnk->ibport = ini->ib_port; + } + get_device(&lnk->smcibdev->ibdev->dev); + atomic_inc(&lnk->smcibdev->lnk_cnt); + lnk->path_mtu = lnk->smcibdev->pattr[lnk->ibport - 1].active_mtu; lnk->link_id = smcr_next_link_id(lgr); lnk->lgr = lgr; lnk->link_idx = link_idx; - lnk->smcibdev = ini->ib_dev; - lnk->ibport = ini->ib_port; smc_ibdev_cnt_inc(lnk); smcr_copy_dev_info_to_link(lnk); - lnk->path_mtu = ini->ib_dev->pattr[ini->ib_port - 1].active_mtu; atomic_set(&lnk->conn_cnt, 0); smc_llc_link_set_uid(lnk); INIT_WORK(&lnk->link_down_wrk, smc_link_down_work); - if (!ini->ib_dev->initialized) { - rc = (int)smc_ib_setup_per_ibdev(ini->ib_dev); + if (!lnk->smcibdev->initialized) { + rc = (int)smc_ib_setup_per_ibdev(lnk->smcibdev); if (rc) goto out; } @@ -709,7 +763,9 @@ int smcr_link_init(struct smc_link_group *lgr, struct smc_link *lnk, lnk->psn_initial = rndvec[0] + (rndvec[1] << 8) + (rndvec[2] << 16); rc = smc_ib_determine_gid(lnk->smcibdev, lnk->ibport, - ini->vlan_id, lnk->gid, &lnk->sgid_index); + ini->vlan_id, lnk->gid, &lnk->sgid_index, + lgr->smc_version == SMC_V2 ? + &ini->smcrv2 : NULL); if (rc) goto out; rc = smc_llc_link_init(lnk); @@ -740,11 +796,12 @@ clear_llc_lnk: smc_llc_link_clear(lnk, false); out: smc_ibdev_cnt_dec(lnk); - put_device(&ini->ib_dev->ibdev->dev); + put_device(&lnk->smcibdev->ibdev->dev); + smcibdev = lnk->smcibdev; memset(lnk, 0, sizeof(struct smc_link)); lnk->state = SMC_LNK_UNUSED; - if (!atomic_dec_return(&ini->ib_dev->lnk_cnt)) - wake_up(&ini->ib_dev->lnks_deleted); + if (!atomic_dec_return(&smcibdev->lnk_cnt)) + wake_up(&smcibdev->lnks_deleted); return rc; } @@ -808,18 +865,37 @@ static int smc_lgr_create(struct smc_sock *smc, struct smc_init_info *ini) atomic_inc(&ini->ism_dev[ini->ism_selected]->lgr_cnt); } else { /* SMC-R specific settings */ + struct smc_ib_device *ibdev; + int ibport; + lgr->role = smc->listen_smc ? SMC_SERV : SMC_CLNT; - memcpy(lgr->peer_systemid, ini->ib_lcl->id_for_peer, + lgr->smc_version = ini->smcr_version; + memcpy(lgr->peer_systemid, ini->peer_systemid, SMC_SYSTEMID_LEN); - memcpy(lgr->pnet_id, ini->ib_dev->pnetid[ini->ib_port - 1], + if (lgr->smc_version == SMC_V2) { + ibdev = ini->smcrv2.ib_dev_v2; + ibport = ini->smcrv2.ib_port_v2; + lgr->saddr = ini->smcrv2.saddr; + lgr->uses_gateway = ini->smcrv2.uses_gateway; + memcpy(lgr->nexthop_mac, ini->smcrv2.nexthop_mac, + ETH_ALEN); + } else { + ibdev = ini->ib_dev; + ibport = ini->ib_port; + } + memcpy(lgr->pnet_id, ibdev->pnetid[ibport - 1], SMC_MAX_PNETID_LEN); + if (smc_wr_alloc_lgr_mem(lgr)) + goto free_wq; smc_llc_lgr_init(lgr, smc); link_idx = SMC_SINGLE_LINK; lnk = &lgr->lnk[link_idx]; rc = smcr_link_init(lgr, lnk, link_idx, ini); - if (rc) + if (rc) { + smc_wr_free_lgr_mem(lgr); goto free_wq; + } lgr_list = &smc_lgr_list.list; lgr_lock = &smc_lgr_list.lock; atomic_inc(&lgr_cnt); @@ -1226,6 +1302,7 @@ static void smc_lgr_free(struct smc_link_group *lgr) if (!atomic_dec_return(&lgr->smcd->lgr_cnt)) wake_up(&lgr->smcd->lgrs_deleted); } else { + smc_wr_free_lgr_mem(lgr); if (!atomic_dec_return(&lgr_cnt)) wake_up(&lgrs_deleted); } @@ -1636,13 +1713,15 @@ out: return rc; } -static bool smcr_lgr_match(struct smc_link_group *lgr, - struct smc_clc_msg_local *lcl, +static bool smcr_lgr_match(struct smc_link_group *lgr, u8 smcr_version, + u8 peer_systemid[], + u8 peer_gid[], + u8 peer_mac_v1[], enum smc_lgr_role role, u32 clcqpn) { int i; - if (memcmp(lgr->peer_systemid, lcl->id_for_peer, SMC_SYSTEMID_LEN) || + if (memcmp(lgr->peer_systemid, peer_systemid, SMC_SYSTEMID_LEN) || lgr->role != role) return false; @@ -1650,8 +1729,9 @@ static bool smcr_lgr_match(struct smc_link_group *lgr, if (!smc_link_active(&lgr->lnk[i])) continue; if ((lgr->role == SMC_SERV || lgr->lnk[i].peer_qpn == clcqpn) && - !memcmp(lgr->lnk[i].peer_gid, &lcl->gid, SMC_GID_SIZE) && - !memcmp(lgr->lnk[i].peer_mac, lcl->mac, sizeof(lcl->mac))) + !memcmp(lgr->lnk[i].peer_gid, peer_gid, SMC_GID_SIZE) && + (smcr_version == SMC_V2 || + !memcmp(lgr->lnk[i].peer_mac, peer_mac_v1, ETH_ALEN))) return true; } return false; @@ -1690,7 +1770,10 @@ int smc_conn_create(struct smc_sock *smc, struct smc_init_info *ini) if ((ini->is_smcd ? smcd_lgr_match(lgr, ini->ism_dev[ini->ism_selected], ini->ism_peer_gid[ini->ism_selected]) : - smcr_lgr_match(lgr, ini->ib_lcl, role, ini->ib_clcqpn)) && + smcr_lgr_match(lgr, ini->smcr_version, + ini->peer_systemid, + ini->peer_gid, ini->peer_mac, role, + ini->ib_clcqpn)) && !lgr->sync_err && (ini->smcd_version == SMC_V2 || lgr->vlan_id == ini->vlan_id) && diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h index 83d30b06016f..59cef3b830d8 100644 --- a/net/smc/smc_core.h +++ b/net/smc/smc_core.h @@ -42,11 +42,16 @@ enum smc_link_state { /* possible states of a link */ }; #define SMC_WR_BUF_SIZE 48 /* size of work request buffer */ +#define SMC_WR_BUF_V2_SIZE 8192 /* size of v2 work request buffer */ struct smc_wr_buf { u8 raw[SMC_WR_BUF_SIZE]; }; +struct smc_wr_v2_buf { + u8 raw[SMC_WR_BUF_V2_SIZE]; +}; + #define SMC_WR_REG_MR_WAIT_TIME (5 * HZ)/* wait time for ib_wr_reg_mr result */ enum smc_wr_reg_state { @@ -92,7 +97,11 @@ struct smc_link { struct smc_wr_tx_pend *wr_tx_pends; /* WR send waiting for CQE */ struct completion *wr_tx_compl; /* WR send CQE completion */ /* above four vectors have wr_tx_cnt elements and use the same index */ + struct ib_send_wr *wr_tx_v2_ib; /* WR send v2 meta data */ + struct ib_sge *wr_tx_v2_sge; /* WR send v2 gather meta data*/ + struct smc_wr_tx_pend *wr_tx_v2_pend; /* WR send v2 waiting for CQE */ dma_addr_t wr_tx_dma_addr; /* DMA address of wr_tx_bufs */ + dma_addr_t wr_tx_v2_dma_addr; /* DMA address of v2 tx buf*/ atomic_long_t wr_tx_id; /* seq # of last sent WR */ unsigned long *wr_tx_mask; /* bit mask of used indexes */ u32 wr_tx_cnt; /* number of WR send buffers */ @@ -104,6 +113,7 @@ struct smc_link { struct ib_sge *wr_rx_sges; /* WR recv scatter meta data */ /* above three vectors have wr_rx_cnt elements and use the same index */ dma_addr_t wr_rx_dma_addr; /* DMA address of wr_rx_bufs */ + dma_addr_t wr_rx_v2_dma_addr; /* DMA address of v2 rx buf*/ u64 wr_rx_id; /* seq # of last recv WR */ u32 wr_rx_cnt; /* number of WR recv buffers */ unsigned long wr_rx_tstamp; /* jiffies when last buf rx */ @@ -208,6 +218,7 @@ enum smc_llc_flowtype { SMC_LLC_FLOW_NONE = 0, SMC_LLC_FLOW_ADD_LINK = 2, SMC_LLC_FLOW_DEL_LINK = 4, + SMC_LLC_FLOW_REQ_ADD_LINK = 5, SMC_LLC_FLOW_RKEY = 6, }; @@ -250,6 +261,10 @@ struct smc_link_group { /* client or server */ struct smc_link lnk[SMC_LINKS_PER_LGR_MAX]; /* smc link */ + struct smc_wr_v2_buf *wr_rx_buf_v2; + /* WR v2 recv payload buffer */ + struct smc_wr_v2_buf *wr_tx_buf_v2; + /* WR v2 send payload buffer */ char peer_systemid[SMC_SYSTEMID_LEN]; /* unique system_id of peer */ struct smc_rtoken rtokens[SMC_RMBS_PER_LGR_MAX] @@ -288,6 +303,9 @@ struct smc_link_group { /* link keep alive time */ u32 llc_termination_rsn; /* rsn code for termination */ + u8 nexthop_mac[ETH_ALEN]; + u8 uses_gateway; + __be32 saddr; }; struct { /* SMC-D */ u64 peer_gid; @@ -302,6 +320,31 @@ struct smc_link_group { struct smc_clc_msg_local; +#define GID_LIST_SIZE 2 + +struct smc_gidlist { + u8 len; + u8 list[GID_LIST_SIZE][SMC_GID_SIZE]; +}; + +struct smc_init_info_smcrv2 { + /* Input fields */ + __be32 saddr; + struct sock *clc_sk; + __be32 daddr; + + /* Output fields when saddr is set */ + struct smc_ib_device *ib_dev_v2; + u8 ib_port_v2; + u8 ib_gid_v2[SMC_GID_SIZE]; + + /* Additional output fields when clc_sk and daddr is set as well */ + u8 uses_gateway; + u8 nexthop_mac[ETH_ALEN]; + + struct smc_gidlist gidlist; +}; + struct smc_init_info { u8 is_smcd; u8 smc_type_v1; @@ -312,11 +355,16 @@ struct smc_init_info { u32 rc; u8 negotiated_eid[SMC_MAX_EID_LEN]; /* SMC-R */ - struct smc_clc_msg_local *ib_lcl; + u8 smcr_version; + u8 check_smcrv2; + u8 peer_gid[SMC_GID_SIZE]; + u8 peer_mac[ETH_ALEN]; + u8 peer_systemid[SMC_SYSTEMID_LEN]; struct smc_ib_device *ib_dev; u8 ib_gid[SMC_GID_SIZE]; u8 ib_port; u32 ib_clcqpn; + struct smc_init_info_smcrv2 smcrv2; /* SMC-D */ u64 ism_peer_gid[SMC_MAX_ISM_DEVS + 1]; struct smcd_dev *ism_dev[SMC_MAX_ISM_DEVS + 1]; diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c index a8845343d183..d93055ec17ae 100644 --- a/net/smc/smc_ib.c +++ b/net/smc/smc_ib.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include @@ -62,16 +63,23 @@ static int smc_ib_modify_qp_rtr(struct smc_link *lnk) IB_QP_STATE | IB_QP_AV | IB_QP_PATH_MTU | IB_QP_DEST_QPN | IB_QP_RQ_PSN | IB_QP_MAX_DEST_RD_ATOMIC | IB_QP_MIN_RNR_TIMER; struct ib_qp_attr qp_attr; + u8 hop_lim = 1; memset(&qp_attr, 0, sizeof(qp_attr)); qp_attr.qp_state = IB_QPS_RTR; qp_attr.path_mtu = min(lnk->path_mtu, lnk->peer_mtu); qp_attr.ah_attr.type = RDMA_AH_ATTR_TYPE_ROCE; rdma_ah_set_port_num(&qp_attr.ah_attr, lnk->ibport); - rdma_ah_set_grh(&qp_attr.ah_attr, NULL, 0, lnk->sgid_index, 1, 0); + if (lnk->lgr->smc_version == SMC_V2 && lnk->lgr->uses_gateway) + hop_lim = IPV6_DEFAULT_HOPLIMIT; + rdma_ah_set_grh(&qp_attr.ah_attr, NULL, 0, lnk->sgid_index, hop_lim, 0); rdma_ah_set_dgid_raw(&qp_attr.ah_attr, lnk->peer_gid); - memcpy(&qp_attr.ah_attr.roce.dmac, lnk->peer_mac, - sizeof(lnk->peer_mac)); + if (lnk->lgr->smc_version == SMC_V2 && lnk->lgr->uses_gateway) + memcpy(&qp_attr.ah_attr.roce.dmac, lnk->lgr->nexthop_mac, + sizeof(lnk->lgr->nexthop_mac)); + else + memcpy(&qp_attr.ah_attr.roce.dmac, lnk->peer_mac, + sizeof(lnk->peer_mac)); qp_attr.dest_qp_num = lnk->peer_qpn; qp_attr.rq_psn = lnk->peer_psn; /* starting receive packet seq # */ qp_attr.max_dest_rd_atomic = 1; /* max # of resources for incoming @@ -183,9 +191,81 @@ bool smc_ib_port_active(struct smc_ib_device *smcibdev, u8 ibport) return smcibdev->pattr[ibport - 1].state == IB_PORT_ACTIVE; } +int smc_ib_find_route(__be32 saddr, __be32 daddr, + u8 nexthop_mac[], u8 *uses_gateway) +{ + struct neighbour *neigh = NULL; + struct rtable *rt = NULL; + struct flowi4 fl4 = { + .saddr = saddr, + .daddr = daddr + }; + + if (daddr == cpu_to_be32(INADDR_NONE)) + goto out; + rt = ip_route_output_flow(&init_net, &fl4, NULL); + if (IS_ERR(rt)) + goto out; + if (rt->rt_uses_gateway && rt->rt_gw_family != AF_INET) + goto out; + neigh = rt->dst.ops->neigh_lookup(&rt->dst, NULL, &fl4.daddr); + if (neigh) { + memcpy(nexthop_mac, neigh->ha, ETH_ALEN); + *uses_gateway = rt->rt_uses_gateway; + return 0; + } +out: + return -ENOENT; +} + +static int smc_ib_determine_gid_rcu(const struct net_device *ndev, + const struct ib_gid_attr *attr, + u8 gid[], u8 *sgid_index, + struct smc_init_info_smcrv2 *smcrv2) +{ + if (!smcrv2 && attr->gid_type == IB_GID_TYPE_ROCE) { + if (gid) + memcpy(gid, &attr->gid, SMC_GID_SIZE); + if (sgid_index) + *sgid_index = attr->index; + return 0; + } + if (smcrv2 && attr->gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP && + smc_ib_gid_to_ipv4((u8 *)&attr->gid) != cpu_to_be32(INADDR_NONE)) { + struct in_device *in_dev = __in_dev_get_rcu(ndev); + const struct in_ifaddr *ifa; + bool subnet_match = false; + + if (!in_dev) + goto out; + in_dev_for_each_ifa_rcu(ifa, in_dev) { + if (!inet_ifa_match(smcrv2->saddr, ifa)) + continue; + subnet_match = true; + break; + } + if (!subnet_match) + goto out; + if (smcrv2->daddr && smc_ib_find_route(smcrv2->saddr, + smcrv2->daddr, + smcrv2->nexthop_mac, + &smcrv2->uses_gateway)) + goto out; + + if (gid) + memcpy(gid, &attr->gid, SMC_GID_SIZE); + if (sgid_index) + *sgid_index = attr->index; + return 0; + } +out: + return -ENODEV; +} + /* determine the gid for an ib-device port and vlan id */ int smc_ib_determine_gid(struct smc_ib_device *smcibdev, u8 ibport, - unsigned short vlan_id, u8 gid[], u8 *sgid_index) + unsigned short vlan_id, u8 gid[], u8 *sgid_index, + struct smc_init_info_smcrv2 *smcrv2) { const struct ib_gid_attr *attr; const struct net_device *ndev; @@ -201,15 +281,13 @@ int smc_ib_determine_gid(struct smc_ib_device *smcibdev, u8 ibport, if (!IS_ERR(ndev) && ((!vlan_id && !is_vlan_dev(ndev)) || (vlan_id && is_vlan_dev(ndev) && - vlan_dev_vlan_id(ndev) == vlan_id)) && - attr->gid_type == IB_GID_TYPE_ROCE) { - rcu_read_unlock(); - if (gid) - memcpy(gid, &attr->gid, SMC_GID_SIZE); - if (sgid_index) - *sgid_index = attr->index; - rdma_put_gid_attr(attr); - return 0; + vlan_dev_vlan_id(ndev) == vlan_id))) { + if (!smc_ib_determine_gid_rcu(ndev, attr, gid, + sgid_index, smcrv2)) { + rcu_read_unlock(); + rdma_put_gid_attr(attr); + return 0; + } } rcu_read_unlock(); rdma_put_gid_attr(attr); @@ -217,6 +295,58 @@ int smc_ib_determine_gid(struct smc_ib_device *smcibdev, u8 ibport, return -ENODEV; } +/* check if gid is still defined on smcibdev */ +static bool smc_ib_check_link_gid(u8 gid[SMC_GID_SIZE], bool smcrv2, + struct smc_ib_device *smcibdev, u8 ibport) +{ + const struct ib_gid_attr *attr; + bool rc = false; + int i; + + for (i = 0; !rc && i < smcibdev->pattr[ibport - 1].gid_tbl_len; i++) { + attr = rdma_get_gid_attr(smcibdev->ibdev, ibport, i); + if (IS_ERR(attr)) + continue; + + rcu_read_lock(); + if ((!smcrv2 && attr->gid_type == IB_GID_TYPE_ROCE) || + (smcrv2 && attr->gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP && + !(ipv6_addr_type((const struct in6_addr *)&attr->gid) + & IPV6_ADDR_LINKLOCAL))) + if (!memcmp(gid, &attr->gid, SMC_GID_SIZE)) + rc = true; + rcu_read_unlock(); + rdma_put_gid_attr(attr); + } + return rc; +} + +/* check all links if the gid is still defined on smcibdev */ +static void smc_ib_gid_check(struct smc_ib_device *smcibdev, u8 ibport) +{ + struct smc_link_group *lgr; + int i; + + spin_lock_bh(&smc_lgr_list.lock); + list_for_each_entry(lgr, &smc_lgr_list.list, list) { + if (strncmp(smcibdev->pnetid[ibport - 1], lgr->pnet_id, + SMC_MAX_PNETID_LEN)) + continue; /* lgr is not affected */ + if (list_empty(&lgr->list)) + continue; + for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { + if (lgr->lnk[i].state == SMC_LNK_UNUSED || + lgr->lnk[i].smcibdev != smcibdev) + continue; + if (!smc_ib_check_link_gid(lgr->lnk[i].gid, + lgr->smc_version == SMC_V2, + smcibdev, ibport)) + smcr_port_err(smcibdev, ibport); + } + } + spin_unlock_bh(&smc_lgr_list.lock); +} + static int smc_ib_remember_port_attr(struct smc_ib_device *smcibdev, u8 ibport) { int rc; @@ -255,6 +385,7 @@ static void smc_ib_port_event_work(struct work_struct *work) } else { clear_bit(port_idx, smcibdev->ports_going_away); smcr_port_add(smcibdev, port_idx + 1); + smc_ib_gid_check(smcibdev, port_idx + 1); } } } @@ -523,6 +654,7 @@ void smc_ib_destroy_queue_pair(struct smc_link *lnk) /* create a queue pair within the protection domain for a link */ int smc_ib_create_queue_pair(struct smc_link *lnk) { + int sges_per_buf = (lnk->lgr->smc_version == SMC_V2) ? 2 : 1; struct ib_qp_init_attr qp_attr = { .event_handler = smc_ib_qp_event_handler, .qp_context = lnk, @@ -536,7 +668,7 @@ int smc_ib_create_queue_pair(struct smc_link *lnk) .max_send_wr = SMC_WR_BUF_CNT * 3, .max_recv_wr = SMC_WR_BUF_CNT * 3, .max_send_sge = SMC_IB_MAX_SEND_SGE, - .max_recv_sge = 1, + .max_recv_sge = sges_per_buf, }, .sq_sig_type = IB_SIGNAL_REQ_WR, .qp_type = IB_QPT_RC, diff --git a/net/smc/smc_ib.h b/net/smc/smc_ib.h index 3085f5180da7..07585937370e 100644 --- a/net/smc/smc_ib.h +++ b/net/smc/smc_ib.h @@ -59,6 +59,17 @@ struct smc_ib_device { /* ib-device infos for smc */ int ndev_ifidx[SMC_MAX_PORTS]; /* ndev if indexes */ }; +static inline __be32 smc_ib_gid_to_ipv4(u8 gid[SMC_GID_SIZE]) +{ + struct in6_addr *addr6 = (struct in6_addr *)gid; + + if (ipv6_addr_v4mapped(addr6) || + !(addr6->s6_addr32[0] | addr6->s6_addr32[1] | addr6->s6_addr32[2])) + return addr6->s6_addr32[3]; + return cpu_to_be32(INADDR_NONE); +} + +struct smc_init_info_smcrv2; struct smc_buf_desc; struct smc_link; @@ -90,7 +101,10 @@ void smc_ib_sync_sg_for_device(struct smc_link *lnk, struct smc_buf_desc *buf_slot, enum dma_data_direction data_direction); int smc_ib_determine_gid(struct smc_ib_device *smcibdev, u8 ibport, - unsigned short vlan_id, u8 gid[], u8 *sgid_index); + unsigned short vlan_id, u8 gid[], u8 *sgid_index, + struct smc_init_info_smcrv2 *smcrv2); +int smc_ib_find_route(__be32 saddr, __be32 daddr, + u8 nexthop_mac[], u8 *uses_gateway); bool smc_ib_is_valid_local_systemid(void); int smcr_nl_get_device(struct sk_buff *skb, struct netlink_callback *cb); #endif diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c index f1d323439a2a..b102680296b8 100644 --- a/net/smc/smc_llc.c +++ b/net/smc/smc_llc.c @@ -23,16 +23,24 @@ struct smc_llc_hdr { struct smc_wr_rx_hdr common; - u8 length; /* 44 */ -#if defined(__BIG_ENDIAN_BITFIELD) - u8 reserved:4, - add_link_rej_rsn:4; + union { + struct { + u8 length; /* 44 */ + #if defined(__BIG_ENDIAN_BITFIELD) + u8 reserved:4, + add_link_rej_rsn:4; #elif defined(__LITTLE_ENDIAN_BITFIELD) - u8 add_link_rej_rsn:4, - reserved:4; + u8 add_link_rej_rsn:4, + reserved:4; #endif + }; + u16 length_v2; /* 44 - 8192*/ + }; u8 flags; -}; +} __packed; /* format defined in + * IBM Shared Memory Communications Version 2 + * (https://www.ibm.com/support/pages/node/6326337) + */ #define SMC_LLC_FLAG_NO_RMBE_EYEC 0x03 @@ -76,6 +84,32 @@ struct smc_llc_msg_add_link_cont_rt { __be64 rmb_vaddr_new; }; +struct smc_llc_msg_add_link_v2_ext { +#if defined(__BIG_ENDIAN_BITFIELD) + u8 v2_direct : 1, + reserved : 7; +#elif defined(__LITTLE_ENDIAN_BITFIELD) + u8 reserved : 7, + v2_direct : 1; +#endif + u8 reserved2; + u8 client_target_gid[SMC_GID_SIZE]; + u8 reserved3[8]; + u16 num_rkeys; + struct smc_llc_msg_add_link_cont_rt rt[]; +} __packed; /* format defined in + * IBM Shared Memory Communications Version 2 + * (https://www.ibm.com/support/pages/node/6326337) + */ + +struct smc_llc_msg_req_add_link_v2 { + struct smc_llc_hdr hd; + u8 reserved[20]; + u8 gid_cnt; + u8 reserved2[3]; + u8 gid[][SMC_GID_SIZE]; +}; + #define SMC_LLC_RKEYS_PER_CONT_MSG 2 struct smc_llc_msg_add_link_cont { /* type 0x03 */ @@ -114,7 +148,8 @@ struct smc_rmb_rtoken { __be64 rmb_vaddr; } __packed; /* format defined in RFC7609 */ -#define SMC_LLC_RKEYS_PER_MSG 3 +#define SMC_LLC_RKEYS_PER_MSG 3 +#define SMC_LLC_RKEYS_PER_MSG_V2 255 struct smc_llc_msg_confirm_rkey { /* type 0x06 */ struct smc_llc_hdr hd; @@ -135,9 +170,18 @@ struct smc_llc_msg_delete_rkey { /* type 0x09 */ u8 reserved2[4]; }; +struct smc_llc_msg_delete_rkey_v2 { /* type 0x29 */ + struct smc_llc_hdr hd; + u8 num_rkeys; + u8 num_inval_rkeys; + u8 reserved[2]; + __be32 rkey[]; +}; + union smc_llc_msg { struct smc_llc_msg_confirm_link confirm_link; struct smc_llc_msg_add_link add_link; + struct smc_llc_msg_req_add_link_v2 req_add_link; struct smc_llc_msg_add_link_cont add_link_cont; struct smc_llc_msg_del_link delete_link; @@ -189,7 +233,7 @@ static inline void smc_llc_flow_qentry_set(struct smc_llc_flow *flow, static void smc_llc_flow_parallel(struct smc_link_group *lgr, u8 flow_type, struct smc_llc_qentry *qentry) { - u8 msg_type = qentry->msg.raw.hdr.common.type; + u8 msg_type = qentry->msg.raw.hdr.common.llc_type; if ((msg_type == SMC_LLC_ADD_LINK || msg_type == SMC_LLC_DELETE_LINK) && flow_type != msg_type && !lgr->delayed_event) { @@ -219,7 +263,7 @@ static bool smc_llc_flow_start(struct smc_llc_flow *flow, spin_unlock_bh(&lgr->llc_flow_lock); return false; } - switch (qentry->msg.raw.hdr.common.type) { + switch (qentry->msg.raw.hdr.common.llc_type) { case SMC_LLC_ADD_LINK: flow->type = SMC_LLC_FLOW_ADD_LINK; break; @@ -306,7 +350,7 @@ struct smc_llc_qentry *smc_llc_wait(struct smc_link_group *lgr, smc_llc_flow_qentry_del(flow); goto out; } - rcv_msg = flow->qentry->msg.raw.hdr.common.type; + rcv_msg = flow->qentry->msg.raw.hdr.common.llc_type; if (exp_msg && rcv_msg != exp_msg) { if (exp_msg == SMC_LLC_ADD_LINK && rcv_msg == SMC_LLC_DELETE_LINK) { @@ -374,6 +418,30 @@ static int smc_llc_add_pending_send(struct smc_link *link, return 0; } +static int smc_llc_add_pending_send_v2(struct smc_link *link, + struct smc_wr_v2_buf **wr_buf, + struct smc_wr_tx_pend_priv **pend) +{ + int rc; + + rc = smc_wr_tx_get_v2_slot(link, smc_llc_tx_handler, wr_buf, pend); + if (rc < 0) + return rc; + return 0; +} + +static void smc_llc_init_msg_hdr(struct smc_llc_hdr *hdr, + struct smc_link_group *lgr, size_t len) +{ + if (lgr->smc_version == SMC_V2) { + hdr->common.llc_version = SMC_V2; + hdr->length_v2 = len; + } else { + hdr->common.llc_version = 0; + hdr->length = len; + } +} + /* high-level API to send LLC confirm link */ int smc_llc_send_confirm_link(struct smc_link *link, enum smc_llc_reqresp reqresp) @@ -390,8 +458,8 @@ int smc_llc_send_confirm_link(struct smc_link *link, goto put_out; confllc = (struct smc_llc_msg_confirm_link *)wr_buf; memset(confllc, 0, sizeof(*confllc)); - confllc->hd.common.type = SMC_LLC_CONFIRM_LINK; - confllc->hd.length = sizeof(struct smc_llc_msg_confirm_link); + confllc->hd.common.llc_type = SMC_LLC_CONFIRM_LINK; + smc_llc_init_msg_hdr(&confllc->hd, link->lgr, sizeof(*confllc)); confllc->hd.flags |= SMC_LLC_FLAG_NO_RMBE_EYEC; if (reqresp == SMC_LLC_RESP) confllc->hd.flags |= SMC_LLC_FLAG_RESP; @@ -426,8 +494,8 @@ static int smc_llc_send_confirm_rkey(struct smc_link *send_link, goto put_out; rkeyllc = (struct smc_llc_msg_confirm_rkey *)wr_buf; memset(rkeyllc, 0, sizeof(*rkeyllc)); - rkeyllc->hd.common.type = SMC_LLC_CONFIRM_RKEY; - rkeyllc->hd.length = sizeof(struct smc_llc_msg_confirm_rkey); + rkeyllc->hd.common.llc_type = SMC_LLC_CONFIRM_RKEY; + smc_llc_init_msg_hdr(&rkeyllc->hd, send_link->lgr, sizeof(*rkeyllc)); rtok_ix = 1; for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { @@ -471,8 +539,8 @@ static int smc_llc_send_delete_rkey(struct smc_link *link, goto put_out; rkeyllc = (struct smc_llc_msg_delete_rkey *)wr_buf; memset(rkeyllc, 0, sizeof(*rkeyllc)); - rkeyllc->hd.common.type = SMC_LLC_DELETE_RKEY; - rkeyllc->hd.length = sizeof(struct smc_llc_msg_delete_rkey); + rkeyllc->hd.common.llc_type = SMC_LLC_DELETE_RKEY; + smc_llc_init_msg_hdr(&rkeyllc->hd, link->lgr, sizeof(*rkeyllc)); rkeyllc->num_rkeys = 1; rkeyllc->rkey[0] = htonl(rmb_desc->mr_rx[link->link_idx]->rkey); /* send llc message */ @@ -482,26 +550,116 @@ put_out: return rc; } +/* return first buffer from any of the next buf lists */ +static struct smc_buf_desc *_smc_llc_get_next_rmb(struct smc_link_group *lgr, + int *buf_lst) +{ + struct smc_buf_desc *buf_pos; + + while (*buf_lst < SMC_RMBE_SIZES) { + buf_pos = list_first_entry_or_null(&lgr->rmbs[*buf_lst], + struct smc_buf_desc, list); + if (buf_pos) + return buf_pos; + (*buf_lst)++; + } + return NULL; +} + +/* return next rmb from buffer lists */ +static struct smc_buf_desc *smc_llc_get_next_rmb(struct smc_link_group *lgr, + int *buf_lst, + struct smc_buf_desc *buf_pos) +{ + struct smc_buf_desc *buf_next; + + if (!buf_pos || list_is_last(&buf_pos->list, &lgr->rmbs[*buf_lst])) { + (*buf_lst)++; + return _smc_llc_get_next_rmb(lgr, buf_lst); + } + buf_next = list_next_entry(buf_pos, list); + return buf_next; +} + +static struct smc_buf_desc *smc_llc_get_first_rmb(struct smc_link_group *lgr, + int *buf_lst) +{ + *buf_lst = 0; + return smc_llc_get_next_rmb(lgr, buf_lst, NULL); +} + +static int smc_llc_fill_ext_v2(struct smc_llc_msg_add_link_v2_ext *ext, + struct smc_link *link, struct smc_link *link_new) +{ + struct smc_link_group *lgr = link->lgr; + struct smc_buf_desc *buf_pos; + int prim_lnk_idx, lnk_idx, i; + struct smc_buf_desc *rmb; + int len = sizeof(*ext); + int buf_lst; + + ext->v2_direct = !lgr->uses_gateway; + memcpy(ext->client_target_gid, link_new->gid, SMC_GID_SIZE); + + prim_lnk_idx = link->link_idx; + lnk_idx = link_new->link_idx; + mutex_lock(&lgr->rmbs_lock); + ext->num_rkeys = lgr->conns_num; + if (!ext->num_rkeys) + goto out; + buf_pos = smc_llc_get_first_rmb(lgr, &buf_lst); + for (i = 0; i < ext->num_rkeys; i++) { + if (!buf_pos) + break; + rmb = buf_pos; + ext->rt[i].rmb_key = htonl(rmb->mr_rx[prim_lnk_idx]->rkey); + ext->rt[i].rmb_key_new = htonl(rmb->mr_rx[lnk_idx]->rkey); + ext->rt[i].rmb_vaddr_new = + cpu_to_be64((u64)sg_dma_address(rmb->sgt[lnk_idx].sgl)); + buf_pos = smc_llc_get_next_rmb(lgr, &buf_lst, buf_pos); + while (buf_pos && !(buf_pos)->used) + buf_pos = smc_llc_get_next_rmb(lgr, &buf_lst, buf_pos); + } + len += i * sizeof(ext->rt[0]); +out: + mutex_unlock(&lgr->rmbs_lock); + return len; +} + /* send ADD LINK request or response */ int smc_llc_send_add_link(struct smc_link *link, u8 mac[], u8 gid[], struct smc_link *link_new, enum smc_llc_reqresp reqresp) { + struct smc_llc_msg_add_link_v2_ext *ext = NULL; struct smc_llc_msg_add_link *addllc; struct smc_wr_tx_pend_priv *pend; - struct smc_wr_buf *wr_buf; + int len = sizeof(*addllc); int rc; if (!smc_wr_tx_link_hold(link)) return -ENOLINK; - rc = smc_llc_add_pending_send(link, &wr_buf, &pend); - if (rc) - goto put_out; - addllc = (struct smc_llc_msg_add_link *)wr_buf; + if (link->lgr->smc_version == SMC_V2) { + struct smc_wr_v2_buf *wr_buf; + + rc = smc_llc_add_pending_send_v2(link, &wr_buf, &pend); + if (rc) + goto put_out; + addllc = (struct smc_llc_msg_add_link *)wr_buf; + ext = (struct smc_llc_msg_add_link_v2_ext *) + &wr_buf->raw[sizeof(*addllc)]; + memset(ext, 0, SMC_WR_TX_SIZE); + } else { + struct smc_wr_buf *wr_buf; + + rc = smc_llc_add_pending_send(link, &wr_buf, &pend); + if (rc) + goto put_out; + addllc = (struct smc_llc_msg_add_link *)wr_buf; + } memset(addllc, 0, sizeof(*addllc)); - addllc->hd.common.type = SMC_LLC_ADD_LINK; - addllc->hd.length = sizeof(struct smc_llc_msg_add_link); + addllc->hd.common.llc_type = SMC_LLC_ADD_LINK; if (reqresp == SMC_LLC_RESP) addllc->hd.flags |= SMC_LLC_FLAG_RESP; memcpy(addllc->sender_mac, mac, ETH_ALEN); @@ -516,8 +674,14 @@ int smc_llc_send_add_link(struct smc_link *link, u8 mac[], u8 gid[], addllc->qp_mtu = min(link_new->path_mtu, link_new->peer_mtu); } + if (ext && link_new) + len += smc_llc_fill_ext_v2(ext, link, link_new); + smc_llc_init_msg_hdr(&addllc->hd, link->lgr, len); /* send llc message */ - rc = smc_wr_tx_send(link, pend); + if (link->lgr->smc_version == SMC_V2) + rc = smc_wr_tx_v2_send(link, pend, len); + else + rc = smc_wr_tx_send(link, pend); put_out: smc_wr_tx_link_put(link); return rc; @@ -541,8 +705,8 @@ int smc_llc_send_delete_link(struct smc_link *link, u8 link_del_id, delllc = (struct smc_llc_msg_del_link *)wr_buf; memset(delllc, 0, sizeof(*delllc)); - delllc->hd.common.type = SMC_LLC_DELETE_LINK; - delllc->hd.length = sizeof(struct smc_llc_msg_del_link); + delllc->hd.common.llc_type = SMC_LLC_DELETE_LINK; + smc_llc_init_msg_hdr(&delllc->hd, link->lgr, sizeof(*delllc)); if (reqresp == SMC_LLC_RESP) delllc->hd.flags |= SMC_LLC_FLAG_RESP; if (orderly) @@ -574,8 +738,8 @@ static int smc_llc_send_test_link(struct smc_link *link, u8 user_data[16]) goto put_out; testllc = (struct smc_llc_msg_test_link *)wr_buf; memset(testllc, 0, sizeof(*testllc)); - testllc->hd.common.type = SMC_LLC_TEST_LINK; - testllc->hd.length = sizeof(struct smc_llc_msg_test_link); + testllc->hd.common.llc_type = SMC_LLC_TEST_LINK; + smc_llc_init_msg_hdr(&testllc->hd, link->lgr, sizeof(*testllc)); memcpy(testllc->user_data, user_data, sizeof(testllc->user_data)); /* send llc message */ rc = smc_wr_tx_send(link, pend); @@ -651,44 +815,6 @@ static int smc_llc_alloc_alt_link(struct smc_link_group *lgr, return -EMLINK; } -/* return first buffer from any of the next buf lists */ -static struct smc_buf_desc *_smc_llc_get_next_rmb(struct smc_link_group *lgr, - int *buf_lst) -{ - struct smc_buf_desc *buf_pos; - - while (*buf_lst < SMC_RMBE_SIZES) { - buf_pos = list_first_entry_or_null(&lgr->rmbs[*buf_lst], - struct smc_buf_desc, list); - if (buf_pos) - return buf_pos; - (*buf_lst)++; - } - return NULL; -} - -/* return next rmb from buffer lists */ -static struct smc_buf_desc *smc_llc_get_next_rmb(struct smc_link_group *lgr, - int *buf_lst, - struct smc_buf_desc *buf_pos) -{ - struct smc_buf_desc *buf_next; - - if (!buf_pos || list_is_last(&buf_pos->list, &lgr->rmbs[*buf_lst])) { - (*buf_lst)++; - return _smc_llc_get_next_rmb(lgr, buf_lst); - } - buf_next = list_next_entry(buf_pos, list); - return buf_next; -} - -static struct smc_buf_desc *smc_llc_get_first_rmb(struct smc_link_group *lgr, - int *buf_lst) -{ - *buf_lst = 0; - return smc_llc_get_next_rmb(lgr, buf_lst, NULL); -} - /* send one add_link_continue msg */ static int smc_llc_add_link_cont(struct smc_link *link, struct smc_link *link_new, u8 *num_rkeys_todo, @@ -734,7 +860,7 @@ static int smc_llc_add_link_cont(struct smc_link *link, while (*buf_pos && !(*buf_pos)->used) *buf_pos = smc_llc_get_next_rmb(lgr, buf_lst, *buf_pos); } - addc_llc->hd.common.type = SMC_LLC_ADD_LINK_CONT; + addc_llc->hd.common.llc_type = SMC_LLC_ADD_LINK_CONT; addc_llc->hd.length = sizeof(struct smc_llc_msg_add_link_cont); if (lgr->role == SMC_CLNT) addc_llc->hd.flags |= SMC_LLC_FLAG_RESP; @@ -793,6 +919,8 @@ static int smc_llc_cli_add_link_reject(struct smc_llc_qentry *qentry) qentry->msg.raw.hdr.flags |= SMC_LLC_FLAG_RESP; qentry->msg.raw.hdr.flags |= SMC_LLC_FLAG_ADD_LNK_REJ; qentry->msg.raw.hdr.add_link_rej_rsn = SMC_LLC_REJ_RSN_NO_ALT_PATH; + smc_llc_init_msg_hdr(&qentry->msg.raw.hdr, qentry->link->lgr, + sizeof(qentry->msg)); return smc_llc_send_message(qentry->link, &qentry->msg); } @@ -813,7 +941,7 @@ static int smc_llc_cli_conf_link(struct smc_link *link, SMC_LLC_DEL_LOST_PATH); return -ENOLINK; } - if (qentry->msg.raw.hdr.common.type != SMC_LLC_CONFIRM_LINK) { + if (qentry->msg.raw.hdr.common.llc_type != SMC_LLC_CONFIRM_LINK) { /* received DELETE_LINK instead */ qentry->msg.raw.hdr.flags |= SMC_LLC_FLAG_RESP; smc_llc_send_message(link, &qentry->msg); @@ -854,6 +982,26 @@ static int smc_llc_cli_conf_link(struct smc_link *link, return 0; } +static void smc_llc_save_add_link_rkeys(struct smc_link *link, + struct smc_link *link_new) +{ + struct smc_llc_msg_add_link_v2_ext *ext; + struct smc_link_group *lgr = link->lgr; + int max, i; + + ext = (struct smc_llc_msg_add_link_v2_ext *)((u8 *)lgr->wr_rx_buf_v2 + + SMC_WR_TX_SIZE); + max = min_t(u8, ext->num_rkeys, SMC_LLC_RKEYS_PER_MSG_V2); + mutex_lock(&lgr->rmbs_lock); + for (i = 0; i < max; i++) { + smc_rtoken_set(lgr, link->link_idx, link_new->link_idx, + ext->rt[i].rmb_key, + ext->rt[i].rmb_vaddr_new, + ext->rt[i].rmb_key_new); + } + mutex_unlock(&lgr->rmbs_lock); +} + static void smc_llc_save_add_link_info(struct smc_link *link, struct smc_llc_msg_add_link *add_llc) { @@ -870,31 +1018,47 @@ int smc_llc_cli_add_link(struct smc_link *link, struct smc_llc_qentry *qentry) struct smc_llc_msg_add_link *llc = &qentry->msg.add_link; enum smc_lgr_type lgr_new_t = SMC_LGR_SYMMETRIC; struct smc_link_group *lgr = smc_get_lgr(link); + struct smc_init_info *ini = NULL; struct smc_link *lnk_new = NULL; - struct smc_init_info ini; int lnk_idx, rc = 0; if (!llc->qp_mtu) goto out_reject; - ini.vlan_id = lgr->vlan_id; - smc_pnet_find_alt_roce(lgr, &ini, link->smcibdev); + ini = kzalloc(sizeof(*ini), GFP_KERNEL); + if (!ini) { + rc = -ENOMEM; + goto out_reject; + } + + ini->vlan_id = lgr->vlan_id; + if (lgr->smc_version == SMC_V2) { + ini->check_smcrv2 = true; + ini->smcrv2.saddr = lgr->saddr; + ini->smcrv2.daddr = smc_ib_gid_to_ipv4(llc->sender_gid); + } + smc_pnet_find_alt_roce(lgr, ini, link->smcibdev); if (!memcmp(llc->sender_gid, link->peer_gid, SMC_GID_SIZE) && - !memcmp(llc->sender_mac, link->peer_mac, ETH_ALEN)) { - if (!ini.ib_dev) + (lgr->smc_version == SMC_V2 || + !memcmp(llc->sender_mac, link->peer_mac, ETH_ALEN))) { + if (!ini->ib_dev && !ini->smcrv2.ib_dev_v2) goto out_reject; lgr_new_t = SMC_LGR_ASYMMETRIC_PEER; } - if (!ini.ib_dev) { + if (lgr->smc_version == SMC_V2 && !ini->smcrv2.ib_dev_v2) { lgr_new_t = SMC_LGR_ASYMMETRIC_LOCAL; - ini.ib_dev = link->smcibdev; - ini.ib_port = link->ibport; + ini->smcrv2.ib_dev_v2 = link->smcibdev; + ini->smcrv2.ib_port_v2 = link->ibport; + } else if (lgr->smc_version < SMC_V2 && !ini->ib_dev) { + lgr_new_t = SMC_LGR_ASYMMETRIC_LOCAL; + ini->ib_dev = link->smcibdev; + ini->ib_port = link->ibport; } lnk_idx = smc_llc_alloc_alt_link(lgr, lgr_new_t); if (lnk_idx < 0) goto out_reject; lnk_new = &lgr->lnk[lnk_idx]; - rc = smcr_link_init(lgr, lnk_new, lnk_idx, &ini); + rc = smcr_link_init(lgr, lnk_new, lnk_idx, ini); if (rc) goto out_reject; smc_llc_save_add_link_info(lnk_new, llc); @@ -910,16 +1074,20 @@ int smc_llc_cli_add_link(struct smc_link *link, struct smc_llc_qentry *qentry) goto out_clear_lnk; rc = smc_llc_send_add_link(link, - lnk_new->smcibdev->mac[ini.ib_port - 1], + lnk_new->smcibdev->mac[lnk_new->ibport - 1], lnk_new->gid, lnk_new, SMC_LLC_RESP); if (rc) goto out_clear_lnk; - rc = smc_llc_cli_rkey_exchange(link, lnk_new); - if (rc) { - rc = 0; - goto out_clear_lnk; + if (lgr->smc_version == SMC_V2) { + smc_llc_save_add_link_rkeys(link, lnk_new); + } else { + rc = smc_llc_cli_rkey_exchange(link, lnk_new); + if (rc) { + rc = 0; + goto out_clear_lnk; + } } - rc = smc_llc_cli_conf_link(link, &ini, lnk_new, lgr_new_t); + rc = smc_llc_cli_conf_link(link, ini, lnk_new, lgr_new_t); if (!rc) goto out; out_clear_lnk: @@ -928,29 +1096,78 @@ out_clear_lnk: out_reject: smc_llc_cli_add_link_reject(qentry); out: + kfree(ini); kfree(qentry); return rc; } +static void smc_llc_send_request_add_link(struct smc_link *link) +{ + struct smc_llc_msg_req_add_link_v2 *llc; + struct smc_wr_tx_pend_priv *pend; + struct smc_wr_v2_buf *wr_buf; + struct smc_gidlist gidlist; + int rc, len, i; + + if (!smc_wr_tx_link_hold(link)) + return; + if (link->lgr->type == SMC_LGR_SYMMETRIC || + link->lgr->type == SMC_LGR_ASYMMETRIC_PEER) + goto put_out; + + smc_fill_gid_list(link->lgr, &gidlist, link->smcibdev, link->gid); + if (gidlist.len <= 1) + goto put_out; + + rc = smc_llc_add_pending_send_v2(link, &wr_buf, &pend); + if (rc) + goto put_out; + llc = (struct smc_llc_msg_req_add_link_v2 *)wr_buf; + memset(llc, 0, SMC_WR_TX_SIZE); + + llc->hd.common.llc_type = SMC_LLC_REQ_ADD_LINK; + for (i = 0; i < gidlist.len; i++) + memcpy(llc->gid[i], gidlist.list[i], sizeof(gidlist.list[0])); + llc->gid_cnt = gidlist.len; + len = sizeof(*llc) + (gidlist.len * sizeof(gidlist.list[0])); + smc_llc_init_msg_hdr(&llc->hd, link->lgr, len); + rc = smc_wr_tx_v2_send(link, pend, len); + if (!rc) + /* set REQ_ADD_LINK flow and wait for response from peer */ + link->lgr->llc_flow_lcl.type = SMC_LLC_FLOW_REQ_ADD_LINK; +put_out: + smc_wr_tx_link_put(link); +} + /* as an SMC client, invite server to start the add_link processing */ static void smc_llc_cli_add_link_invite(struct smc_link *link, struct smc_llc_qentry *qentry) { struct smc_link_group *lgr = smc_get_lgr(link); - struct smc_init_info ini; + struct smc_init_info *ini = NULL; + + if (lgr->smc_version == SMC_V2) { + smc_llc_send_request_add_link(link); + goto out; + } if (lgr->type == SMC_LGR_SYMMETRIC || lgr->type == SMC_LGR_ASYMMETRIC_PEER) goto out; - ini.vlan_id = lgr->vlan_id; - smc_pnet_find_alt_roce(lgr, &ini, link->smcibdev); - if (!ini.ib_dev) + ini = kzalloc(sizeof(*ini), GFP_KERNEL); + if (!ini) goto out; - smc_llc_send_add_link(link, ini.ib_dev->mac[ini.ib_port - 1], - ini.ib_gid, NULL, SMC_LLC_REQ); + ini->vlan_id = lgr->vlan_id; + smc_pnet_find_alt_roce(lgr, ini, link->smcibdev); + if (!ini->ib_dev) + goto out; + + smc_llc_send_add_link(link, ini->ib_dev->mac[ini->ib_port - 1], + ini->ib_gid, NULL, SMC_LLC_REQ); out: + kfree(ini); kfree(qentry); } @@ -966,7 +1183,7 @@ static bool smc_llc_is_empty_llc_message(union smc_llc_msg *llc) static bool smc_llc_is_local_add_link(union smc_llc_msg *llc) { - if (llc->raw.hdr.common.type == SMC_LLC_ADD_LINK && + if (llc->raw.hdr.common.llc_type == SMC_LLC_ADD_LINK && smc_llc_is_empty_llc_message(llc)) return true; return false; @@ -1133,7 +1350,7 @@ static int smc_llc_srv_conf_link(struct smc_link *link, /* receive CONFIRM LINK response over the RoCE fabric */ qentry = smc_llc_wait(lgr, link, SMC_LLC_WAIT_FIRST_TIME, 0); if (!qentry || - qentry->msg.raw.hdr.common.type != SMC_LLC_CONFIRM_LINK) { + qentry->msg.raw.hdr.common.llc_type != SMC_LLC_CONFIRM_LINK) { /* send DELETE LINK */ smc_llc_send_delete_link(link, link_new->link_id, SMC_LLC_REQ, false, SMC_LLC_DEL_LOST_PATH); @@ -1152,37 +1369,80 @@ static int smc_llc_srv_conf_link(struct smc_link *link, return 0; } -int smc_llc_srv_add_link(struct smc_link *link) +static void smc_llc_send_req_add_link_response(struct smc_llc_qentry *qentry) +{ + qentry->msg.raw.hdr.flags |= SMC_LLC_FLAG_RESP; + smc_llc_init_msg_hdr(&qentry->msg.raw.hdr, qentry->link->lgr, + sizeof(qentry->msg)); + memset(&qentry->msg.raw.data, 0, sizeof(qentry->msg.raw.data)); + smc_llc_send_message(qentry->link, &qentry->msg); +} + +int smc_llc_srv_add_link(struct smc_link *link, + struct smc_llc_qentry *req_qentry) { enum smc_lgr_type lgr_new_t = SMC_LGR_SYMMETRIC; struct smc_link_group *lgr = link->lgr; struct smc_llc_msg_add_link *add_llc; struct smc_llc_qentry *qentry = NULL; - struct smc_link *link_new; - struct smc_init_info ini; + bool send_req_add_link_resp = false; + struct smc_link *link_new = NULL; + struct smc_init_info *ini = NULL; int lnk_idx, rc = 0; + if (req_qentry && + req_qentry->msg.raw.hdr.common.llc_type == SMC_LLC_REQ_ADD_LINK) + send_req_add_link_resp = true; + + ini = kzalloc(sizeof(*ini), GFP_KERNEL); + if (!ini) { + rc = -ENOMEM; + goto out; + } + /* ignore client add link recommendation, start new flow */ - ini.vlan_id = lgr->vlan_id; - smc_pnet_find_alt_roce(lgr, &ini, link->smcibdev); - if (!ini.ib_dev) { + ini->vlan_id = lgr->vlan_id; + if (lgr->smc_version == SMC_V2) { + ini->check_smcrv2 = true; + ini->smcrv2.saddr = lgr->saddr; + if (send_req_add_link_resp) { + struct smc_llc_msg_req_add_link_v2 *req_add = + &req_qentry->msg.req_add_link; + + ini->smcrv2.daddr = smc_ib_gid_to_ipv4(req_add->gid[0]); + } + } + smc_pnet_find_alt_roce(lgr, ini, link->smcibdev); + if (lgr->smc_version == SMC_V2 && !ini->smcrv2.ib_dev_v2) { lgr_new_t = SMC_LGR_ASYMMETRIC_LOCAL; - ini.ib_dev = link->smcibdev; - ini.ib_port = link->ibport; + ini->smcrv2.ib_dev_v2 = link->smcibdev; + ini->smcrv2.ib_port_v2 = link->ibport; + } else if (lgr->smc_version < SMC_V2 && !ini->ib_dev) { + lgr_new_t = SMC_LGR_ASYMMETRIC_LOCAL; + ini->ib_dev = link->smcibdev; + ini->ib_port = link->ibport; } lnk_idx = smc_llc_alloc_alt_link(lgr, lgr_new_t); - if (lnk_idx < 0) - return 0; + if (lnk_idx < 0) { + rc = 0; + goto out; + } - rc = smcr_link_init(lgr, &lgr->lnk[lnk_idx], lnk_idx, &ini); + rc = smcr_link_init(lgr, &lgr->lnk[lnk_idx], lnk_idx, ini); if (rc) - return rc; + goto out; link_new = &lgr->lnk[lnk_idx]; + + rc = smcr_buf_map_lgr(link_new); + if (rc) + goto out_err; + rc = smc_llc_send_add_link(link, - link_new->smcibdev->mac[ini.ib_port - 1], + link_new->smcibdev->mac[link_new->ibport-1], link_new->gid, link_new, SMC_LLC_REQ); if (rc) goto out_err; + send_req_add_link_resp = false; /* receive ADD LINK response over the RoCE fabric */ qentry = smc_llc_wait(lgr, link, SMC_LLC_WAIT_TIME, SMC_LLC_ADD_LINK); if (!qentry) { @@ -1197,48 +1457,59 @@ int smc_llc_srv_add_link(struct smc_link *link) } if (lgr->type == SMC_LGR_SINGLE && (!memcmp(add_llc->sender_gid, link->peer_gid, SMC_GID_SIZE) && - !memcmp(add_llc->sender_mac, link->peer_mac, ETH_ALEN))) { + (lgr->smc_version == SMC_V2 || + !memcmp(add_llc->sender_mac, link->peer_mac, ETH_ALEN)))) { lgr_new_t = SMC_LGR_ASYMMETRIC_PEER; } smc_llc_save_add_link_info(link_new, add_llc); smc_llc_flow_qentry_del(&lgr->llc_flow_lcl); rc = smc_ib_ready_link(link_new); - if (rc) - goto out_err; - rc = smcr_buf_map_lgr(link_new); if (rc) goto out_err; rc = smcr_buf_reg_lgr(link_new); if (rc) goto out_err; - rc = smc_llc_srv_rkey_exchange(link, link_new); - if (rc) - goto out_err; + if (lgr->smc_version == SMC_V2) { + smc_llc_save_add_link_rkeys(link, link_new); + } else { + rc = smc_llc_srv_rkey_exchange(link, link_new); + if (rc) + goto out_err; + } rc = smc_llc_srv_conf_link(link, link_new, lgr_new_t); if (rc) goto out_err; + kfree(ini); return 0; out_err: - link_new->state = SMC_LNK_INACTIVE; - smcr_link_clear(link_new, false); + if (link_new) { + link_new->state = SMC_LNK_INACTIVE; + smcr_link_clear(link_new, false); + } +out: + kfree(ini); + if (send_req_add_link_resp) + smc_llc_send_req_add_link_response(req_qentry); return rc; } static void smc_llc_process_srv_add_link(struct smc_link_group *lgr) { struct smc_link *link = lgr->llc_flow_lcl.qentry->link; + struct smc_llc_qentry *qentry; int rc; - smc_llc_flow_qentry_del(&lgr->llc_flow_lcl); + qentry = smc_llc_flow_qentry_clr(&lgr->llc_flow_lcl); mutex_lock(&lgr->llc_conf_mutex); - rc = smc_llc_srv_add_link(link); + rc = smc_llc_srv_add_link(link, qentry); if (!rc && lgr->type == SMC_LGR_SYMMETRIC) { /* delete any asymmetric link */ smc_llc_delete_asym_link(lgr); } mutex_unlock(&lgr->llc_conf_mutex); + kfree(qentry); } /* enqueue a local add_link req to trigger a new add_link flow */ @@ -1246,8 +1517,8 @@ void smc_llc_add_link_local(struct smc_link *link) { struct smc_llc_msg_add_link add_llc = {}; - add_llc.hd.length = sizeof(add_llc); - add_llc.hd.common.type = SMC_LLC_ADD_LINK; + add_llc.hd.common.llc_type = SMC_LLC_ADD_LINK; + smc_llc_init_msg_hdr(&add_llc.hd, link->lgr, sizeof(add_llc)); /* no dev and port needed */ smc_llc_enqueue(link, (union smc_llc_msg *)&add_llc); } @@ -1269,7 +1540,8 @@ static void smc_llc_add_link_work(struct work_struct *work) else smc_llc_process_srv_add_link(lgr); out: - smc_llc_flow_stop(lgr, &lgr->llc_flow_lcl); + if (lgr->llc_flow_lcl.type != SMC_LLC_FLOW_REQ_ADD_LINK) + smc_llc_flow_stop(lgr, &lgr->llc_flow_lcl); } /* enqueue a local del_link msg to trigger a new del_link flow, @@ -1279,8 +1551,8 @@ void smc_llc_srv_delete_link_local(struct smc_link *link, u8 del_link_id) { struct smc_llc_msg_del_link del_llc = {}; - del_llc.hd.length = sizeof(del_llc); - del_llc.hd.common.type = SMC_LLC_DELETE_LINK; + del_llc.hd.common.llc_type = SMC_LLC_DELETE_LINK; + smc_llc_init_msg_hdr(&del_llc.hd, link->lgr, sizeof(del_llc)); del_llc.link_num = del_link_id; del_llc.reason = htonl(SMC_LLC_DEL_LOST_PATH); del_llc.hd.flags |= SMC_LLC_FLAG_DEL_LINK_ORDERLY; @@ -1350,8 +1622,8 @@ void smc_llc_send_link_delete_all(struct smc_link_group *lgr, bool ord, u32 rsn) struct smc_llc_msg_del_link delllc = {}; int i; - delllc.hd.common.type = SMC_LLC_DELETE_LINK; - delllc.hd.length = sizeof(delllc); + delllc.hd.common.llc_type = SMC_LLC_DELETE_LINK; + smc_llc_init_msg_hdr(&delllc.hd, lgr, sizeof(delllc)); if (ord) delllc.hd.flags |= SMC_LLC_FLAG_DEL_LINK_ORDERLY; delllc.hd.flags |= SMC_LLC_FLAG_DEL_LINK_ALL; @@ -1467,6 +1739,8 @@ static void smc_llc_rmt_conf_rkey(struct smc_link_group *lgr) link = qentry->link; num_entries = llc->rtoken[0].num_rkeys; + if (num_entries > SMC_LLC_RKEYS_PER_MSG) + goto out_err; /* first rkey entry is for receiving link */ rk_idx = smc_rtoken_add(link, llc->rtoken[0].rmb_vaddr, @@ -1485,6 +1759,7 @@ out_err: llc->hd.flags |= SMC_LLC_FLAG_RKEY_RETRY; out: llc->hd.flags |= SMC_LLC_FLAG_RESP; + smc_llc_init_msg_hdr(&llc->hd, link->lgr, sizeof(*llc)); smc_llc_send_message(link, &qentry->msg); smc_llc_flow_qentry_del(&lgr->llc_flow_rmt); } @@ -1502,6 +1777,28 @@ static void smc_llc_rmt_delete_rkey(struct smc_link_group *lgr) llc = &qentry->msg.delete_rkey; link = qentry->link; + if (lgr->smc_version == SMC_V2) { + struct smc_llc_msg_delete_rkey_v2 *llcv2; + + memcpy(lgr->wr_rx_buf_v2, llc, sizeof(*llc)); + llcv2 = (struct smc_llc_msg_delete_rkey_v2 *)lgr->wr_rx_buf_v2; + llcv2->num_inval_rkeys = 0; + + max = min_t(u8, llcv2->num_rkeys, SMC_LLC_RKEYS_PER_MSG_V2); + for (i = 0; i < max; i++) { + if (smc_rtoken_delete(link, llcv2->rkey[i])) + llcv2->num_inval_rkeys++; + } + memset(&llc->rkey[0], 0, sizeof(llc->rkey)); + memset(&llc->reserved2, 0, sizeof(llc->reserved2)); + smc_llc_init_msg_hdr(&llc->hd, link->lgr, sizeof(*llc)); + if (llcv2->num_inval_rkeys) { + llc->hd.flags |= SMC_LLC_FLAG_RKEY_NEG; + llc->err_mask = llcv2->num_inval_rkeys; + } + goto finish; + } + max = min_t(u8, llc->num_rkeys, SMC_LLC_DEL_RKEY_MAX); for (i = 0; i < max; i++) { if (smc_rtoken_delete(link, llc->rkey[i])) @@ -1511,6 +1808,7 @@ static void smc_llc_rmt_delete_rkey(struct smc_link_group *lgr) llc->hd.flags |= SMC_LLC_FLAG_RKEY_NEG; llc->err_mask = err_mask; } +finish: llc->hd.flags |= SMC_LLC_FLAG_RESP; smc_llc_send_message(link, &qentry->msg); smc_llc_flow_qentry_del(&lgr->llc_flow_rmt); @@ -1546,7 +1844,7 @@ static void smc_llc_event_handler(struct smc_llc_qentry *qentry) if (!smc_link_usable(link)) goto out; - switch (llc->raw.hdr.common.type) { + switch (llc->raw.hdr.common.llc_type) { case SMC_LLC_TEST_LINK: llc->test_link.hd.flags |= SMC_LLC_FLAG_RESP; smc_llc_send_message(link, llc); @@ -1571,8 +1869,18 @@ static void smc_llc_event_handler(struct smc_llc_qentry *qentry) smc_llc_flow_qentry_set(&lgr->llc_flow_lcl, qentry); wake_up(&lgr->llc_msg_waiter); - } else if (smc_llc_flow_start(&lgr->llc_flow_lcl, - qentry)) { + return; + } + if (lgr->llc_flow_lcl.type == + SMC_LLC_FLOW_REQ_ADD_LINK) { + /* server started add_link processing */ + lgr->llc_flow_lcl.type = SMC_LLC_FLOW_ADD_LINK; + smc_llc_flow_qentry_set(&lgr->llc_flow_lcl, + qentry); + schedule_work(&lgr->llc_add_link_work); + return; + } + if (smc_llc_flow_start(&lgr->llc_flow_lcl, qentry)) { schedule_work(&lgr->llc_add_link_work); } } else if (smc_llc_flow_start(&lgr->llc_flow_lcl, qentry)) { @@ -1620,6 +1928,23 @@ static void smc_llc_event_handler(struct smc_llc_qentry *qentry) smc_llc_flow_stop(lgr, &lgr->llc_flow_rmt); } return; + case SMC_LLC_REQ_ADD_LINK: + /* handle response here, smc_llc_flow_stop() cannot be called + * in tasklet context + */ + if (lgr->role == SMC_CLNT && + lgr->llc_flow_lcl.type == SMC_LLC_FLOW_REQ_ADD_LINK && + (llc->raw.hdr.flags & SMC_LLC_FLAG_RESP)) { + smc_llc_flow_stop(link->lgr, &lgr->llc_flow_lcl); + } else if (lgr->role == SMC_SERV) { + if (smc_llc_flow_start(&lgr->llc_flow_lcl, qentry)) { + /* as smc server, handle client suggestion */ + lgr->llc_flow_lcl.type = SMC_LLC_FLOW_ADD_LINK; + schedule_work(&lgr->llc_add_link_work); + } + return; + } + break; default: smc_llc_protocol_violation(lgr, llc->raw.hdr.common.type); break; @@ -1663,7 +1988,7 @@ static void smc_llc_rx_response(struct smc_link *link, { enum smc_llc_flowtype flowtype = link->lgr->llc_flow_lcl.type; struct smc_llc_flow *flow = &link->lgr->llc_flow_lcl; - u8 llc_type = qentry->msg.raw.hdr.common.type; + u8 llc_type = qentry->msg.raw.hdr.common.llc_type; switch (llc_type) { case SMC_LLC_TEST_LINK: @@ -1689,7 +2014,8 @@ static void smc_llc_rx_response(struct smc_link *link, /* not used because max links is 3 */ break; default: - smc_llc_protocol_violation(link->lgr, llc_type); + smc_llc_protocol_violation(link->lgr, + qentry->msg.raw.hdr.common.type); break; } kfree(qentry); @@ -1714,7 +2040,8 @@ static void smc_llc_enqueue(struct smc_link *link, union smc_llc_msg *llc) memcpy(&qentry->msg, llc, sizeof(union smc_llc_msg)); /* process responses immediately */ - if (llc->raw.hdr.flags & SMC_LLC_FLAG_RESP) { + if ((llc->raw.hdr.flags & SMC_LLC_FLAG_RESP) && + llc->raw.hdr.common.llc_type != SMC_LLC_REQ_ADD_LINK) { smc_llc_rx_response(link, qentry); return; } @@ -1734,8 +2061,13 @@ static void smc_llc_rx_handler(struct ib_wc *wc, void *buf) if (wc->byte_len < sizeof(*llc)) return; /* short message */ - if (llc->raw.hdr.length != sizeof(*llc)) - return; /* invalid message */ + if (!llc->raw.hdr.common.llc_version) { + if (llc->raw.hdr.length != sizeof(*llc)) + return; /* invalid message */ + } else { + if (llc->raw.hdr.length_v2 < sizeof(*llc)) + return; /* invalid message */ + } smc_llc_enqueue(link, llc); } @@ -1954,6 +2286,35 @@ static struct smc_wr_rx_handler smc_llc_rx_handlers[] = { .handler = smc_llc_rx_handler, .type = SMC_LLC_DELETE_RKEY }, + /* V2 types */ + { + .handler = smc_llc_rx_handler, + .type = SMC_LLC_CONFIRM_LINK_V2 + }, + { + .handler = smc_llc_rx_handler, + .type = SMC_LLC_TEST_LINK_V2 + }, + { + .handler = smc_llc_rx_handler, + .type = SMC_LLC_ADD_LINK_V2 + }, + { + .handler = smc_llc_rx_handler, + .type = SMC_LLC_DELETE_LINK_V2 + }, + { + .handler = smc_llc_rx_handler, + .type = SMC_LLC_REQ_ADD_LINK_V2 + }, + { + .handler = smc_llc_rx_handler, + .type = SMC_LLC_CONFIRM_RKEY_V2 + }, + { + .handler = smc_llc_rx_handler, + .type = SMC_LLC_DELETE_RKEY_V2 + }, { .handler = NULL, } diff --git a/net/smc/smc_llc.h b/net/smc/smc_llc.h index cc00a2ec4e92..4404e52b3346 100644 --- a/net/smc/smc_llc.h +++ b/net/smc/smc_llc.h @@ -30,10 +30,19 @@ enum smc_llc_msg_type { SMC_LLC_ADD_LINK = 0x02, SMC_LLC_ADD_LINK_CONT = 0x03, SMC_LLC_DELETE_LINK = 0x04, + SMC_LLC_REQ_ADD_LINK = 0x05, SMC_LLC_CONFIRM_RKEY = 0x06, SMC_LLC_TEST_LINK = 0x07, SMC_LLC_CONFIRM_RKEY_CONT = 0x08, SMC_LLC_DELETE_RKEY = 0x09, + /* V2 types */ + SMC_LLC_CONFIRM_LINK_V2 = 0x21, + SMC_LLC_ADD_LINK_V2 = 0x22, + SMC_LLC_DELETE_LINK_V2 = 0x24, + SMC_LLC_REQ_ADD_LINK_V2 = 0x25, + SMC_LLC_CONFIRM_RKEY_V2 = 0x26, + SMC_LLC_TEST_LINK_V2 = 0x27, + SMC_LLC_DELETE_RKEY_V2 = 0x29, }; #define smc_link_downing(state) \ @@ -102,7 +111,8 @@ void smc_llc_flow_qentry_del(struct smc_llc_flow *flow); void smc_llc_send_link_delete_all(struct smc_link_group *lgr, bool ord, u32 rsn); int smc_llc_cli_add_link(struct smc_link *link, struct smc_llc_qentry *qentry); -int smc_llc_srv_add_link(struct smc_link *link); +int smc_llc_srv_add_link(struct smc_link *link, + struct smc_llc_qentry *req_qentry); void smc_llc_add_link_local(struct smc_link *link); int smc_llc_init(void) __init; diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c index 4a964e9190b0..67e9d9fde085 100644 --- a/net/smc/smc_pnet.c +++ b/net/smc/smc_pnet.c @@ -953,6 +953,26 @@ static int smc_pnet_find_ndev_pnetid_by_table(struct net_device *ndev, return rc; } +static int smc_pnet_determine_gid(struct smc_ib_device *ibdev, int i, + struct smc_init_info *ini) +{ + if (!ini->check_smcrv2 && + !smc_ib_determine_gid(ibdev, i, ini->vlan_id, ini->ib_gid, NULL, + NULL)) { + ini->ib_dev = ibdev; + ini->ib_port = i; + return 0; + } + if (ini->check_smcrv2 && + !smc_ib_determine_gid(ibdev, i, ini->vlan_id, ini->smcrv2.ib_gid_v2, + NULL, &ini->smcrv2)) { + ini->smcrv2.ib_dev_v2 = ibdev; + ini->smcrv2.ib_port_v2 = i; + return 0; + } + return -ENODEV; +} + /* find a roce device for the given pnetid */ static void _smc_pnet_find_roce_by_pnetid(u8 *pnet_id, struct smc_init_info *ini, @@ -961,7 +981,6 @@ static void _smc_pnet_find_roce_by_pnetid(u8 *pnet_id, struct smc_ib_device *ibdev; int i; - ini->ib_dev = NULL; mutex_lock(&smc_ib_devices.mutex); list_for_each_entry(ibdev, &smc_ib_devices.list, list) { if (ibdev == known_dev) @@ -971,12 +990,9 @@ static void _smc_pnet_find_roce_by_pnetid(u8 *pnet_id, continue; if (smc_pnet_match(ibdev->pnetid[i - 1], pnet_id) && smc_ib_port_active(ibdev, i) && - !test_bit(i - 1, ibdev->ports_going_away) && - !smc_ib_determine_gid(ibdev, i, ini->vlan_id, - ini->ib_gid, NULL)) { - ini->ib_dev = ibdev; - ini->ib_port = i; - goto out; + !test_bit(i - 1, ibdev->ports_going_away)) { + if (!smc_pnet_determine_gid(ibdev, i, ini)) + goto out; } } } @@ -1016,12 +1032,9 @@ static void smc_pnet_find_rdma_dev(struct net_device *netdev, dev_put(ndev); if (netdev == ndev && smc_ib_port_active(ibdev, i) && - !test_bit(i - 1, ibdev->ports_going_away) && - !smc_ib_determine_gid(ibdev, i, ini->vlan_id, - ini->ib_gid, NULL)) { - ini->ib_dev = ibdev; - ini->ib_port = i; - break; + !test_bit(i - 1, ibdev->ports_going_away)) { + if (!smc_pnet_determine_gid(ibdev, i, ini)) + break; } } } @@ -1083,8 +1096,6 @@ void smc_pnet_find_roce_resource(struct sock *sk, struct smc_init_info *ini) { struct dst_entry *dst = sk_dst_get(sk); - ini->ib_dev = NULL; - ini->ib_port = 0; if (!dst) goto out; if (!dst->dev) diff --git a/net/smc/smc_wr.c b/net/smc/smc_wr.c index a419e9af36b9..600ab5889227 100644 --- a/net/smc/smc_wr.c +++ b/net/smc/smc_wr.c @@ -101,19 +101,32 @@ static inline void smc_wr_tx_process_cqe(struct ib_wc *wc) } pnd_snd_idx = smc_wr_tx_find_pending_index(link, wc->wr_id); - if (pnd_snd_idx == link->wr_tx_cnt) - return; - link->wr_tx_pends[pnd_snd_idx].wc_status = wc->status; - if (link->wr_tx_pends[pnd_snd_idx].compl_requested) - complete(&link->wr_tx_compl[pnd_snd_idx]); - memcpy(&pnd_snd, &link->wr_tx_pends[pnd_snd_idx], sizeof(pnd_snd)); - /* clear the full struct smc_wr_tx_pend including .priv */ - memset(&link->wr_tx_pends[pnd_snd_idx], 0, - sizeof(link->wr_tx_pends[pnd_snd_idx])); - memset(&link->wr_tx_bufs[pnd_snd_idx], 0, - sizeof(link->wr_tx_bufs[pnd_snd_idx])); - if (!test_and_clear_bit(pnd_snd_idx, link->wr_tx_mask)) - return; + if (pnd_snd_idx == link->wr_tx_cnt) { + if (link->lgr->smc_version != SMC_V2 || + link->wr_tx_v2_pend->wr_id != wc->wr_id) + return; + link->wr_tx_v2_pend->wc_status = wc->status; + memcpy(&pnd_snd, link->wr_tx_v2_pend, sizeof(pnd_snd)); + /* clear the full struct smc_wr_tx_pend including .priv */ + memset(link->wr_tx_v2_pend, 0, + sizeof(*link->wr_tx_v2_pend)); + memset(link->lgr->wr_tx_buf_v2, 0, + sizeof(*link->lgr->wr_tx_buf_v2)); + } else { + link->wr_tx_pends[pnd_snd_idx].wc_status = wc->status; + if (link->wr_tx_pends[pnd_snd_idx].compl_requested) + complete(&link->wr_tx_compl[pnd_snd_idx]); + memcpy(&pnd_snd, &link->wr_tx_pends[pnd_snd_idx], + sizeof(pnd_snd)); + /* clear the full struct smc_wr_tx_pend including .priv */ + memset(&link->wr_tx_pends[pnd_snd_idx], 0, + sizeof(link->wr_tx_pends[pnd_snd_idx])); + memset(&link->wr_tx_bufs[pnd_snd_idx], 0, + sizeof(link->wr_tx_bufs[pnd_snd_idx])); + if (!test_and_clear_bit(pnd_snd_idx, link->wr_tx_mask)) + return; + } + if (wc->status) { for_each_set_bit(i, link->wr_tx_mask, link->wr_tx_cnt) { /* clear full struct smc_wr_tx_pend including .priv */ @@ -123,6 +136,12 @@ static inline void smc_wr_tx_process_cqe(struct ib_wc *wc) sizeof(link->wr_tx_bufs[i])); clear_bit(i, link->wr_tx_mask); } + if (link->lgr->smc_version == SMC_V2) { + memset(link->wr_tx_v2_pend, 0, + sizeof(*link->wr_tx_v2_pend)); + memset(link->lgr->wr_tx_buf_v2, 0, + sizeof(*link->lgr->wr_tx_buf_v2)); + } /* terminate link */ smcr_link_down_cond_sched(link); } @@ -239,6 +258,33 @@ int smc_wr_tx_get_free_slot(struct smc_link *link, return 0; } +int smc_wr_tx_get_v2_slot(struct smc_link *link, + smc_wr_tx_handler handler, + struct smc_wr_v2_buf **wr_buf, + struct smc_wr_tx_pend_priv **wr_pend_priv) +{ + struct smc_wr_tx_pend *wr_pend; + struct ib_send_wr *wr_ib; + u64 wr_id; + + if (link->wr_tx_v2_pend->idx == link->wr_tx_cnt) + return -EBUSY; + + *wr_buf = NULL; + *wr_pend_priv = NULL; + wr_id = smc_wr_tx_get_next_wr_id(link); + wr_pend = link->wr_tx_v2_pend; + wr_pend->wr_id = wr_id; + wr_pend->handler = handler; + wr_pend->link = link; + wr_pend->idx = link->wr_tx_cnt; + wr_ib = link->wr_tx_v2_ib; + wr_ib->wr_id = wr_id; + *wr_buf = link->lgr->wr_tx_buf_v2; + *wr_pend_priv = &wr_pend->priv; + return 0; +} + int smc_wr_tx_put_slot(struct smc_link *link, struct smc_wr_tx_pend_priv *wr_pend_priv) { @@ -256,6 +302,14 @@ int smc_wr_tx_put_slot(struct smc_link *link, test_and_clear_bit(idx, link->wr_tx_mask); wake_up(&link->wr_tx_wait); return 1; + } else if (link->lgr->smc_version == SMC_V2 && + pend->idx == link->wr_tx_cnt) { + /* Large v2 buffer */ + memset(&link->wr_tx_v2_pend, 0, + sizeof(link->wr_tx_v2_pend)); + memset(&link->lgr->wr_tx_buf_v2, 0, + sizeof(link->lgr->wr_tx_buf_v2)); + return 1; } return 0; @@ -280,6 +334,22 @@ int smc_wr_tx_send(struct smc_link *link, struct smc_wr_tx_pend_priv *priv) return rc; } +int smc_wr_tx_v2_send(struct smc_link *link, struct smc_wr_tx_pend_priv *priv, + int len) +{ + int rc; + + link->wr_tx_v2_ib->sg_list[0].length = len; + ib_req_notify_cq(link->smcibdev->roce_cq_send, + IB_CQ_NEXT_COMP | IB_CQ_REPORT_MISSED_EVENTS); + rc = ib_post_send(link->roce_qp, link->wr_tx_v2_ib, NULL); + if (rc) { + smc_wr_tx_put_slot(link, priv); + smcr_link_down_cond_sched(link); + } + return rc; +} + /* Send prepared WR slot via ib_post_send and wait for send completion * notification. * @priv: pointer to smc_wr_tx_pend_priv identifying prepared message buffer @@ -517,6 +587,7 @@ void smc_wr_remember_qp_attr(struct smc_link *lnk) static void smc_wr_init_sge(struct smc_link *lnk) { + int sges_per_buf = (lnk->lgr->smc_version == SMC_V2) ? 2 : 1; u32 i; for (i = 0; i < lnk->wr_tx_cnt; i++) { @@ -545,14 +616,44 @@ static void smc_wr_init_sge(struct smc_link *lnk) lnk->wr_tx_rdmas[i].wr_tx_rdma[1].wr.sg_list = lnk->wr_tx_rdma_sges[i].tx_rdma_sge[1].wr_tx_rdma_sge; } + + if (lnk->lgr->smc_version == SMC_V2) { + lnk->wr_tx_v2_sge->addr = lnk->wr_tx_v2_dma_addr; + lnk->wr_tx_v2_sge->length = SMC_WR_BUF_V2_SIZE; + lnk->wr_tx_v2_sge->lkey = lnk->roce_pd->local_dma_lkey; + + lnk->wr_tx_v2_ib->next = NULL; + lnk->wr_tx_v2_ib->sg_list = lnk->wr_tx_v2_sge; + lnk->wr_tx_v2_ib->num_sge = 1; + lnk->wr_tx_v2_ib->opcode = IB_WR_SEND; + lnk->wr_tx_v2_ib->send_flags = + IB_SEND_SIGNALED | IB_SEND_SOLICITED; + } + + /* With SMC-Rv2 there can be messages larger than SMC_WR_TX_SIZE. + * Each ib_recv_wr gets 2 sges, the second one is a spillover buffer + * and the same buffer for all sges. When a larger message arrived then + * the content of the first small sge is copied to the beginning of + * the larger spillover buffer, allowing easy data mapping. + */ for (i = 0; i < lnk->wr_rx_cnt; i++) { - lnk->wr_rx_sges[i].addr = + int x = i * sges_per_buf; + + lnk->wr_rx_sges[x].addr = lnk->wr_rx_dma_addr + i * SMC_WR_BUF_SIZE; - lnk->wr_rx_sges[i].length = SMC_WR_BUF_SIZE; - lnk->wr_rx_sges[i].lkey = lnk->roce_pd->local_dma_lkey; + lnk->wr_rx_sges[x].length = SMC_WR_TX_SIZE; + lnk->wr_rx_sges[x].lkey = lnk->roce_pd->local_dma_lkey; + if (lnk->lgr->smc_version == SMC_V2) { + lnk->wr_rx_sges[x + 1].addr = + lnk->wr_rx_v2_dma_addr + SMC_WR_TX_SIZE; + lnk->wr_rx_sges[x + 1].length = + SMC_WR_BUF_V2_SIZE - SMC_WR_TX_SIZE; + lnk->wr_rx_sges[x + 1].lkey = + lnk->roce_pd->local_dma_lkey; + } lnk->wr_rx_ibs[i].next = NULL; - lnk->wr_rx_ibs[i].sg_list = &lnk->wr_rx_sges[i]; - lnk->wr_rx_ibs[i].num_sge = 1; + lnk->wr_rx_ibs[i].sg_list = &lnk->wr_rx_sges[x]; + lnk->wr_rx_ibs[i].num_sge = sges_per_buf; } lnk->wr_reg.wr.next = NULL; lnk->wr_reg.wr.num_sge = 0; @@ -585,16 +686,45 @@ void smc_wr_free_link(struct smc_link *lnk) DMA_FROM_DEVICE); lnk->wr_rx_dma_addr = 0; } + if (lnk->wr_rx_v2_dma_addr) { + ib_dma_unmap_single(ibdev, lnk->wr_rx_v2_dma_addr, + SMC_WR_BUF_V2_SIZE, + DMA_FROM_DEVICE); + lnk->wr_rx_v2_dma_addr = 0; + } if (lnk->wr_tx_dma_addr) { ib_dma_unmap_single(ibdev, lnk->wr_tx_dma_addr, SMC_WR_BUF_SIZE * lnk->wr_tx_cnt, DMA_TO_DEVICE); lnk->wr_tx_dma_addr = 0; } + if (lnk->wr_tx_v2_dma_addr) { + ib_dma_unmap_single(ibdev, lnk->wr_tx_v2_dma_addr, + SMC_WR_BUF_V2_SIZE, + DMA_TO_DEVICE); + lnk->wr_tx_v2_dma_addr = 0; + } +} + +void smc_wr_free_lgr_mem(struct smc_link_group *lgr) +{ + if (lgr->smc_version < SMC_V2) + return; + + kfree(lgr->wr_rx_buf_v2); + lgr->wr_rx_buf_v2 = NULL; + kfree(lgr->wr_tx_buf_v2); + lgr->wr_tx_buf_v2 = NULL; } void smc_wr_free_link_mem(struct smc_link *lnk) { + kfree(lnk->wr_tx_v2_ib); + lnk->wr_tx_v2_ib = NULL; + kfree(lnk->wr_tx_v2_sge); + lnk->wr_tx_v2_sge = NULL; + kfree(lnk->wr_tx_v2_pend); + lnk->wr_tx_v2_pend = NULL; kfree(lnk->wr_tx_compl); lnk->wr_tx_compl = NULL; kfree(lnk->wr_tx_pends); @@ -619,8 +749,26 @@ void smc_wr_free_link_mem(struct smc_link *lnk) lnk->wr_rx_bufs = NULL; } +int smc_wr_alloc_lgr_mem(struct smc_link_group *lgr) +{ + if (lgr->smc_version < SMC_V2) + return 0; + + lgr->wr_rx_buf_v2 = kzalloc(SMC_WR_BUF_V2_SIZE, GFP_KERNEL); + if (!lgr->wr_rx_buf_v2) + return -ENOMEM; + lgr->wr_tx_buf_v2 = kzalloc(SMC_WR_BUF_V2_SIZE, GFP_KERNEL); + if (!lgr->wr_tx_buf_v2) { + kfree(lgr->wr_rx_buf_v2); + return -ENOMEM; + } + return 0; +} + int smc_wr_alloc_link_mem(struct smc_link *link) { + int sges_per_buf = link->lgr->smc_version == SMC_V2 ? 2 : 1; + /* allocate link related memory */ link->wr_tx_bufs = kcalloc(SMC_WR_BUF_CNT, SMC_WR_BUF_SIZE, GFP_KERNEL); if (!link->wr_tx_bufs) @@ -653,7 +801,7 @@ int smc_wr_alloc_link_mem(struct smc_link *link) if (!link->wr_tx_sges) goto no_mem_wr_tx_rdma_sges; link->wr_rx_sges = kcalloc(SMC_WR_BUF_CNT * 3, - sizeof(link->wr_rx_sges[0]), + sizeof(link->wr_rx_sges[0]) * sges_per_buf, GFP_KERNEL); if (!link->wr_rx_sges) goto no_mem_wr_tx_sges; @@ -672,8 +820,29 @@ int smc_wr_alloc_link_mem(struct smc_link *link) GFP_KERNEL); if (!link->wr_tx_compl) goto no_mem_wr_tx_pends; + + if (link->lgr->smc_version == SMC_V2) { + link->wr_tx_v2_ib = kzalloc(sizeof(*link->wr_tx_v2_ib), + GFP_KERNEL); + if (!link->wr_tx_v2_ib) + goto no_mem_tx_compl; + link->wr_tx_v2_sge = kzalloc(sizeof(*link->wr_tx_v2_sge), + GFP_KERNEL); + if (!link->wr_tx_v2_sge) + goto no_mem_v2_ib; + link->wr_tx_v2_pend = kzalloc(sizeof(*link->wr_tx_v2_pend), + GFP_KERNEL); + if (!link->wr_tx_v2_pend) + goto no_mem_v2_sge; + } return 0; +no_mem_v2_sge: + kfree(link->wr_tx_v2_sge); +no_mem_v2_ib: + kfree(link->wr_tx_v2_ib); +no_mem_tx_compl: + kfree(link->wr_tx_compl); no_mem_wr_tx_pends: kfree(link->wr_tx_pends); no_mem_wr_tx_mask: @@ -725,6 +894,24 @@ int smc_wr_create_link(struct smc_link *lnk) rc = -EIO; goto out; } + if (lnk->lgr->smc_version == SMC_V2) { + lnk->wr_rx_v2_dma_addr = ib_dma_map_single(ibdev, + lnk->lgr->wr_rx_buf_v2, SMC_WR_BUF_V2_SIZE, + DMA_FROM_DEVICE); + if (ib_dma_mapping_error(ibdev, lnk->wr_rx_v2_dma_addr)) { + lnk->wr_rx_v2_dma_addr = 0; + rc = -EIO; + goto dma_unmap; + } + lnk->wr_tx_v2_dma_addr = ib_dma_map_single(ibdev, + lnk->lgr->wr_tx_buf_v2, SMC_WR_BUF_V2_SIZE, + DMA_TO_DEVICE); + if (ib_dma_mapping_error(ibdev, lnk->wr_tx_v2_dma_addr)) { + lnk->wr_tx_v2_dma_addr = 0; + rc = -EIO; + goto dma_unmap; + } + } lnk->wr_tx_dma_addr = ib_dma_map_single( ibdev, lnk->wr_tx_bufs, SMC_WR_BUF_SIZE * lnk->wr_tx_cnt, DMA_TO_DEVICE); @@ -742,6 +929,18 @@ int smc_wr_create_link(struct smc_link *lnk) return rc; dma_unmap: + if (lnk->wr_rx_v2_dma_addr) { + ib_dma_unmap_single(ibdev, lnk->wr_rx_v2_dma_addr, + SMC_WR_BUF_V2_SIZE, + DMA_FROM_DEVICE); + lnk->wr_rx_v2_dma_addr = 0; + } + if (lnk->wr_tx_v2_dma_addr) { + ib_dma_unmap_single(ibdev, lnk->wr_tx_v2_dma_addr, + SMC_WR_BUF_V2_SIZE, + DMA_TO_DEVICE); + lnk->wr_tx_v2_dma_addr = 0; + } ib_dma_unmap_single(ibdev, lnk->wr_rx_dma_addr, SMC_WR_BUF_SIZE * lnk->wr_rx_cnt, DMA_FROM_DEVICE); diff --git a/net/smc/smc_wr.h b/net/smc/smc_wr.h index 2bc626f230a5..f353311e6f84 100644 --- a/net/smc/smc_wr.h +++ b/net/smc/smc_wr.h @@ -101,8 +101,10 @@ static inline int smc_wr_rx_post(struct smc_link *link) int smc_wr_create_link(struct smc_link *lnk); int smc_wr_alloc_link_mem(struct smc_link *lnk); +int smc_wr_alloc_lgr_mem(struct smc_link_group *lgr); void smc_wr_free_link(struct smc_link *lnk); void smc_wr_free_link_mem(struct smc_link *lnk); +void smc_wr_free_lgr_mem(struct smc_link_group *lgr); void smc_wr_remember_qp_attr(struct smc_link *lnk); void smc_wr_remove_dev(struct smc_ib_device *smcibdev); void smc_wr_add_dev(struct smc_ib_device *smcibdev); @@ -111,10 +113,16 @@ int smc_wr_tx_get_free_slot(struct smc_link *link, smc_wr_tx_handler handler, struct smc_wr_buf **wr_buf, struct smc_rdma_wr **wrs, struct smc_wr_tx_pend_priv **wr_pend_priv); +int smc_wr_tx_get_v2_slot(struct smc_link *link, + smc_wr_tx_handler handler, + struct smc_wr_v2_buf **wr_buf, + struct smc_wr_tx_pend_priv **wr_pend_priv); int smc_wr_tx_put_slot(struct smc_link *link, struct smc_wr_tx_pend_priv *wr_pend_priv); int smc_wr_tx_send(struct smc_link *link, struct smc_wr_tx_pend_priv *wr_pend_priv); +int smc_wr_tx_v2_send(struct smc_link *link, + struct smc_wr_tx_pend_priv *priv, int len); int smc_wr_tx_send_wait(struct smc_link *link, struct smc_wr_tx_pend_priv *priv, unsigned long timeout); void smc_wr_tx_cq_handler(struct ib_cq *ib_cq, void *cq_context); diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 443f8e5b9477..60bc74b76adc 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -462,7 +462,7 @@ int tipc_enable_l2_media(struct net *net, struct tipc_bearer *b, b->bcast_addr.media_id = b->media->type_id; b->bcast_addr.broadcast = TIPC_BROADCAST_SUPPORT; b->mtu = dev->mtu; - b->media->raw2addr(b, &b->addr, (char *)dev->dev_addr); + b->media->raw2addr(b, &b->addr, (const char *)dev->dev_addr); rcu_assign_pointer(dev->tipc_ptr, b); return 0; } @@ -703,7 +703,7 @@ static int tipc_l2_device_event(struct notifier_block *nb, unsigned long evt, break; case NETDEV_CHANGEADDR: b->media->raw2addr(b, &b->addr, - (char *)dev->dev_addr); + (const char *)dev->dev_addr); tipc_reset_bearer(net, b); break; case NETDEV_UNREGISTER: diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h index 57c6a1a719e2..490ad6e5f7a3 100644 --- a/net/tipc/bearer.h +++ b/net/tipc/bearer.h @@ -117,7 +117,7 @@ struct tipc_media { char *msg); int (*raw2addr)(struct tipc_bearer *b, struct tipc_media_addr *addr, - char *raw); + const char *raw); u32 priority; u32 tolerance; u32 min_win; diff --git a/net/tipc/eth_media.c b/net/tipc/eth_media.c index c68019697cfe..cb0d185e06af 100644 --- a/net/tipc/eth_media.c +++ b/net/tipc/eth_media.c @@ -60,7 +60,7 @@ static int tipc_eth_addr2msg(char *msg, struct tipc_media_addr *addr) /* Convert raw mac address format to media addr format */ static int tipc_eth_raw2addr(struct tipc_bearer *b, struct tipc_media_addr *addr, - char *msg) + const char *msg) { memset(addr, 0, sizeof(*addr)); ether_addr_copy(addr->value, msg); diff --git a/net/tipc/ib_media.c b/net/tipc/ib_media.c index 7aa9ff88458d..b9ad0434c3cd 100644 --- a/net/tipc/ib_media.c +++ b/net/tipc/ib_media.c @@ -67,7 +67,7 @@ static int tipc_ib_addr2msg(char *msg, struct tipc_media_addr *addr) /* Convert raw InfiniBand address format to media addr format */ static int tipc_ib_raw2addr(struct tipc_bearer *b, struct tipc_media_addr *addr, - char *msg) + const char *msg) { memset(addr, 0, sizeof(*addr)); memcpy(addr->value, msg, INFINIBAND_ALEN); diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index e2c0cfb334d2..7d851eb3a683 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1614,13 +1614,18 @@ static int vsock_connectible_setsockopt(struct socket *sock, vsock_update_buffer_size(vsk, transport, vsk->buffer_size); break; - case SO_VM_SOCKETS_CONNECT_TIMEOUT: { - struct __kernel_old_timeval tv; - COPY_IN(tv); + case SO_VM_SOCKETS_CONNECT_TIMEOUT_NEW: + case SO_VM_SOCKETS_CONNECT_TIMEOUT_OLD: { + struct __kernel_sock_timeval tv; + + err = sock_copy_user_timeval(&tv, optval, optlen, + optname == SO_VM_SOCKETS_CONNECT_TIMEOUT_OLD); + if (err) + break; if (tv.tv_sec >= 0 && tv.tv_usec < USEC_PER_SEC && tv.tv_sec < (MAX_SCHEDULE_TIMEOUT / HZ - 1)) { vsk->connect_timeout = tv.tv_sec * HZ + - DIV_ROUND_UP(tv.tv_usec, (1000000 / HZ)); + DIV_ROUND_UP((unsigned long)tv.tv_usec, (USEC_PER_SEC / HZ)); if (vsk->connect_timeout == 0) vsk->connect_timeout = VSOCK_DEFAULT_CONNECT_TIMEOUT; @@ -1648,68 +1653,59 @@ static int vsock_connectible_getsockopt(struct socket *sock, char __user *optval, int __user *optlen) { - int err; + struct sock *sk = sock->sk; + struct vsock_sock *vsk = vsock_sk(sk); + + union { + u64 val64; + struct old_timeval32 tm32; + struct __kernel_old_timeval tm; + struct __kernel_sock_timeval stm; + } v; + + int lv = sizeof(v.val64); int len; - struct sock *sk; - struct vsock_sock *vsk; - u64 val; if (level != AF_VSOCK) return -ENOPROTOOPT; - err = get_user(len, optlen); - if (err != 0) - return err; + if (get_user(len, optlen)) + return -EFAULT; -#define COPY_OUT(_v) \ - do { \ - if (len < sizeof(_v)) \ - return -EINVAL; \ - \ - len = sizeof(_v); \ - if (copy_to_user(optval, &_v, len) != 0) \ - return -EFAULT; \ - \ - } while (0) - - err = 0; - sk = sock->sk; - vsk = vsock_sk(sk); + memset(&v, 0, sizeof(v)); switch (optname) { case SO_VM_SOCKETS_BUFFER_SIZE: - val = vsk->buffer_size; - COPY_OUT(val); + v.val64 = vsk->buffer_size; break; case SO_VM_SOCKETS_BUFFER_MAX_SIZE: - val = vsk->buffer_max_size; - COPY_OUT(val); + v.val64 = vsk->buffer_max_size; break; case SO_VM_SOCKETS_BUFFER_MIN_SIZE: - val = vsk->buffer_min_size; - COPY_OUT(val); + v.val64 = vsk->buffer_min_size; break; - case SO_VM_SOCKETS_CONNECT_TIMEOUT: { - struct __kernel_old_timeval tv; - tv.tv_sec = vsk->connect_timeout / HZ; - tv.tv_usec = - (vsk->connect_timeout - - tv.tv_sec * HZ) * (1000000 / HZ); - COPY_OUT(tv); + case SO_VM_SOCKETS_CONNECT_TIMEOUT_NEW: + case SO_VM_SOCKETS_CONNECT_TIMEOUT_OLD: + lv = sock_get_timeout(vsk->connect_timeout, &v, + optname == SO_VM_SOCKETS_CONNECT_TIMEOUT_OLD); break; - } + default: return -ENOPROTOOPT; } - err = put_user(len, optlen); - if (err != 0) + if (len < lv) + return -EINVAL; + if (len > lv) + len = lv; + if (copy_to_user(optval, &v, len)) return -EFAULT; -#undef COPY_OUT + if (put_user(len, optlen)) + return -EFAULT; return 0; } diff --git a/net/wireless/Makefile b/net/wireless/Makefile index af590ae606b6..756e7de7e33f 100644 --- a/net/wireless/Makefile +++ b/net/wireless/Makefile @@ -26,7 +26,7 @@ endif $(obj)/shipped-certs.c: $(wildcard $(srctree)/$(src)/certs/*.hex) @$(kecho) " GEN $@" - @(echo '#include "reg.h"'; \ + $(Q)(echo '#include "reg.h"'; \ echo 'const u8 shipped_regdb_certs[] = {'; \ echo | cat - $^ ; \ echo '};'; \ @@ -36,7 +36,7 @@ $(obj)/shipped-certs.c: $(wildcard $(srctree)/$(src)/certs/*.hex) $(obj)/extra-certs.c: $(CONFIG_CFG80211_EXTRA_REGDB_KEYDIR:"%"=%) \ $(wildcard $(CONFIG_CFG80211_EXTRA_REGDB_KEYDIR:"%"=%)/*.x509) @$(kecho) " GEN $@" - @(set -e; \ + $(Q)(set -e; \ allf=""; \ for f in $^ ; do \ test -f $$f || continue;\ diff --git a/net/wireless/core.c b/net/wireless/core.c index aaba847d79eb..eb297e1015e0 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -1081,6 +1081,16 @@ void cfg80211_dev_free(struct cfg80211_registered_device *rdev) list_for_each_entry_safe(scan, tmp, &rdev->bss_list, list) cfg80211_put_bss(&rdev->wiphy, &scan->pub); mutex_destroy(&rdev->wiphy.mtx); + + /* + * The 'regd' can only be non-NULL if we never finished + * initializing the wiphy and thus never went through the + * unregister path - e.g. in failure scenarios. Thus, it + * cannot have been visible to anyone if non-NULL, so we + * can just free it here. + */ + kfree(rcu_dereference_raw(rdev->wiphy.regd)); + kfree(rdev); } diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index bf7cd4752547..81232b73df8f 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -437,6 +437,16 @@ sar_policy[NL80211_SAR_ATTR_MAX + 1] = { [NL80211_SAR_ATTR_SPECS] = NLA_POLICY_NESTED_ARRAY(sar_specs_policy), }; +static const struct nla_policy +nl80211_mbssid_config_policy[NL80211_MBSSID_CONFIG_ATTR_MAX + 1] = { + [NL80211_MBSSID_CONFIG_ATTR_MAX_INTERFACES] = NLA_POLICY_MIN(NLA_U8, 2), + [NL80211_MBSSID_CONFIG_ATTR_MAX_EMA_PROFILE_PERIODICITY] = + NLA_POLICY_MIN(NLA_U8, 1), + [NL80211_MBSSID_CONFIG_ATTR_INDEX] = { .type = NLA_U8 }, + [NL80211_MBSSID_CONFIG_ATTR_TX_IFINDEX] = { .type = NLA_U32 }, + [NL80211_MBSSID_CONFIG_ATTR_EMA] = { .type = NLA_FLAG }, +}; + static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [0] = { .strict_start_type = NL80211_ATTR_HE_OBSS_PD }, [NL80211_ATTR_WIPHY] = { .type = NLA_U32 }, @@ -763,6 +773,9 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_COLOR_CHANGE_COUNT] = { .type = NLA_U8 }, [NL80211_ATTR_COLOR_CHANGE_COLOR] = { .type = NLA_U8 }, [NL80211_ATTR_COLOR_CHANGE_ELEMS] = NLA_POLICY_NESTED(nl80211_policy), + [NL80211_ATTR_MBSSID_CONFIG] = + NLA_POLICY_NESTED(nl80211_mbssid_config_policy), + [NL80211_ATTR_MBSSID_ELEMS] = { .type = NLA_NESTED }, }; /* policy for the key attributes */ @@ -853,6 +866,7 @@ nl80211_match_band_rssi_policy[NUM_NL80211_BANDS] = { [NL80211_BAND_5GHZ] = { .type = NLA_S32 }, [NL80211_BAND_6GHZ] = { .type = NLA_S32 }, [NL80211_BAND_60GHZ] = { .type = NLA_S32 }, + [NL80211_BAND_LC] = { .type = NLA_S32 }, }; static const struct nla_policy @@ -2207,6 +2221,35 @@ fail: return -ENOBUFS; } +static int nl80211_put_mbssid_support(struct wiphy *wiphy, struct sk_buff *msg) +{ + struct nlattr *config; + + if (!wiphy->mbssid_max_interfaces) + return 0; + + config = nla_nest_start(msg, NL80211_ATTR_MBSSID_CONFIG); + if (!config) + return -ENOBUFS; + + if (nla_put_u8(msg, NL80211_MBSSID_CONFIG_ATTR_MAX_INTERFACES, + wiphy->mbssid_max_interfaces)) + goto fail; + + if (wiphy->ema_max_profile_periodicity && + nla_put_u8(msg, + NL80211_MBSSID_CONFIG_ATTR_MAX_EMA_PROFILE_PERIODICITY, + wiphy->ema_max_profile_periodicity)) + goto fail; + + nla_nest_end(msg, config); + return 0; + +fail: + nla_nest_cancel(msg, config); + return -ENOBUFS; +} + struct nl80211_dump_wiphy_state { s64 filter_wiphy; long start; @@ -2792,6 +2835,9 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, if (nl80211_put_sar_specs(rdev, msg)) goto nla_put_failure; + if (nl80211_put_mbssid_support(&rdev->wiphy, msg)) + goto nla_put_failure; + /* done */ state->split_start = 0; break; @@ -4981,6 +5027,96 @@ static int validate_beacon_tx_rate(struct cfg80211_registered_device *rdev, return 0; } +static int nl80211_parse_mbssid_config(struct wiphy *wiphy, + struct net_device *dev, + struct nlattr *attrs, + struct cfg80211_mbssid_config *config, + u8 num_elems) +{ + struct nlattr *tb[NL80211_MBSSID_CONFIG_ATTR_MAX + 1]; + + if (!wiphy->mbssid_max_interfaces) + return -EOPNOTSUPP; + + if (nla_parse_nested(tb, NL80211_MBSSID_CONFIG_ATTR_MAX, attrs, NULL, + NULL) || + !tb[NL80211_MBSSID_CONFIG_ATTR_INDEX]) + return -EINVAL; + + config->ema = nla_get_flag(tb[NL80211_MBSSID_CONFIG_ATTR_EMA]); + if (config->ema) { + if (!wiphy->ema_max_profile_periodicity) + return -EOPNOTSUPP; + + if (num_elems > wiphy->ema_max_profile_periodicity) + return -EINVAL; + } + + config->index = nla_get_u8(tb[NL80211_MBSSID_CONFIG_ATTR_INDEX]); + if (config->index >= wiphy->mbssid_max_interfaces || + (!config->index && !num_elems)) + return -EINVAL; + + if (tb[NL80211_MBSSID_CONFIG_ATTR_TX_IFINDEX]) { + u32 tx_ifindex = + nla_get_u32(tb[NL80211_MBSSID_CONFIG_ATTR_TX_IFINDEX]); + + if ((!config->index && tx_ifindex != dev->ifindex) || + (config->index && tx_ifindex == dev->ifindex)) + return -EINVAL; + + if (tx_ifindex != dev->ifindex) { + struct net_device *tx_netdev = + dev_get_by_index(wiphy_net(wiphy), tx_ifindex); + + if (!tx_netdev || !tx_netdev->ieee80211_ptr || + tx_netdev->ieee80211_ptr->wiphy != wiphy || + tx_netdev->ieee80211_ptr->iftype != + NL80211_IFTYPE_AP) { + dev_put(tx_netdev); + return -EINVAL; + } + + config->tx_wdev = tx_netdev->ieee80211_ptr; + } else { + config->tx_wdev = dev->ieee80211_ptr; + } + } else if (!config->index) { + config->tx_wdev = dev->ieee80211_ptr; + } else { + return -EINVAL; + } + + return 0; +} + +static struct cfg80211_mbssid_elems * +nl80211_parse_mbssid_elems(struct wiphy *wiphy, struct nlattr *attrs) +{ + struct nlattr *nl_elems; + struct cfg80211_mbssid_elems *elems; + int rem_elems; + u8 i = 0, num_elems = 0; + + if (!wiphy->mbssid_max_interfaces) + return ERR_PTR(-EINVAL); + + nla_for_each_nested(nl_elems, attrs, rem_elems) + num_elems++; + + elems = kzalloc(struct_size(elems, elem, num_elems), GFP_KERNEL); + if (!elems) + return ERR_PTR(-ENOMEM); + + nla_for_each_nested(nl_elems, attrs, rem_elems) { + elems->elem[i].data = nla_data(nl_elems); + elems->elem[i].len = nla_len(nl_elems); + i++; + } + elems->cnt = num_elems; + return elems; +} + static int nl80211_parse_beacon(struct cfg80211_registered_device *rdev, struct nlattr *attrs[], struct cfg80211_beacon_data *bcn) @@ -5061,6 +5197,17 @@ static int nl80211_parse_beacon(struct cfg80211_registered_device *rdev, bcn->ftm_responder = -1; } + if (attrs[NL80211_ATTR_MBSSID_ELEMS]) { + struct cfg80211_mbssid_elems *mbssid = + nl80211_parse_mbssid_elems(&rdev->wiphy, + attrs[NL80211_ATTR_MBSSID_ELEMS]); + + if (IS_ERR(mbssid)) + return PTR_ERR(mbssid); + + bcn->mbssid_ies = mbssid; + } + return 0; } @@ -5192,21 +5339,21 @@ nl80211_parse_unsol_bcast_probe_resp(struct cfg80211_registered_device *rdev, } static void nl80211_check_ap_rate_selectors(struct cfg80211_ap_settings *params, - const u8 *rates) + const struct element *rates) { int i; if (!rates) return; - for (i = 0; i < rates[1]; i++) { - if (rates[2 + i] == BSS_MEMBERSHIP_SELECTOR_HT_PHY) + for (i = 0; i < rates->datalen; i++) { + if (rates->data[i] == BSS_MEMBERSHIP_SELECTOR_HT_PHY) params->ht_required = true; - if (rates[2 + i] == BSS_MEMBERSHIP_SELECTOR_VHT_PHY) + if (rates->data[i] == BSS_MEMBERSHIP_SELECTOR_VHT_PHY) params->vht_required = true; - if (rates[2 + i] == BSS_MEMBERSHIP_SELECTOR_HE_PHY) + if (rates->data[i] == BSS_MEMBERSHIP_SELECTOR_HE_PHY) params->he_required = true; - if (rates[2 + i] == BSS_MEMBERSHIP_SELECTOR_SAE_H2E) + if (rates->data[i] == BSS_MEMBERSHIP_SELECTOR_SAE_H2E) params->sae_h2e_required = true; } } @@ -5221,27 +5368,27 @@ static void nl80211_calculate_ap_params(struct cfg80211_ap_settings *params) const struct cfg80211_beacon_data *bcn = ¶ms->beacon; size_t ies_len = bcn->tail_len; const u8 *ies = bcn->tail; - const u8 *rates; - const u8 *cap; + const struct element *rates; + const struct element *cap; - rates = cfg80211_find_ie(WLAN_EID_SUPP_RATES, ies, ies_len); + rates = cfg80211_find_elem(WLAN_EID_SUPP_RATES, ies, ies_len); nl80211_check_ap_rate_selectors(params, rates); - rates = cfg80211_find_ie(WLAN_EID_EXT_SUPP_RATES, ies, ies_len); + rates = cfg80211_find_elem(WLAN_EID_EXT_SUPP_RATES, ies, ies_len); nl80211_check_ap_rate_selectors(params, rates); - cap = cfg80211_find_ie(WLAN_EID_HT_CAPABILITY, ies, ies_len); - if (cap && cap[1] >= sizeof(*params->ht_cap)) - params->ht_cap = (void *)(cap + 2); - cap = cfg80211_find_ie(WLAN_EID_VHT_CAPABILITY, ies, ies_len); - if (cap && cap[1] >= sizeof(*params->vht_cap)) - params->vht_cap = (void *)(cap + 2); - cap = cfg80211_find_ext_ie(WLAN_EID_EXT_HE_CAPABILITY, ies, ies_len); - if (cap && cap[1] >= sizeof(*params->he_cap) + 1) - params->he_cap = (void *)(cap + 3); - cap = cfg80211_find_ext_ie(WLAN_EID_EXT_HE_OPERATION, ies, ies_len); - if (cap && cap[1] >= sizeof(*params->he_oper) + 1) - params->he_oper = (void *)(cap + 3); + cap = cfg80211_find_elem(WLAN_EID_HT_CAPABILITY, ies, ies_len); + if (cap && cap->datalen >= sizeof(*params->ht_cap)) + params->ht_cap = (void *)cap->data; + cap = cfg80211_find_elem(WLAN_EID_VHT_CAPABILITY, ies, ies_len); + if (cap && cap->datalen >= sizeof(*params->vht_cap)) + params->vht_cap = (void *)cap->data; + cap = cfg80211_find_ext_elem(WLAN_EID_EXT_HE_CAPABILITY, ies, ies_len); + if (cap && cap->datalen >= sizeof(*params->he_cap) + 1) + params->he_cap = (void *)(cap->data + 1); + cap = cfg80211_find_ext_elem(WLAN_EID_EXT_HE_OPERATION, ies, ies_len); + if (cap && cap->datalen >= sizeof(*params->he_oper) + 1) + params->he_oper = (void *)(cap->data + 1); } static bool nl80211_get_ap_channel(struct cfg80211_registered_device *rdev, @@ -5323,7 +5470,7 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) struct cfg80211_registered_device *rdev = info->user_ptr[0]; struct net_device *dev = info->user_ptr[1]; struct wireless_dev *wdev = dev->ieee80211_ptr; - struct cfg80211_ap_settings params; + struct cfg80211_ap_settings *params; int err; if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_AP && @@ -5336,27 +5483,29 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) if (wdev->beacon_interval) return -EALREADY; - memset(¶ms, 0, sizeof(params)); - /* these are required for START_AP */ if (!info->attrs[NL80211_ATTR_BEACON_INTERVAL] || !info->attrs[NL80211_ATTR_DTIM_PERIOD] || !info->attrs[NL80211_ATTR_BEACON_HEAD]) return -EINVAL; - err = nl80211_parse_beacon(rdev, info->attrs, ¶ms.beacon); - if (err) - return err; + params = kzalloc(sizeof(*params), GFP_KERNEL); + if (!params) + return -ENOMEM; - params.beacon_interval = + err = nl80211_parse_beacon(rdev, info->attrs, ¶ms->beacon); + if (err) + goto out; + + params->beacon_interval = nla_get_u32(info->attrs[NL80211_ATTR_BEACON_INTERVAL]); - params.dtim_period = + params->dtim_period = nla_get_u32(info->attrs[NL80211_ATTR_DTIM_PERIOD]); err = cfg80211_validate_beacon_int(rdev, dev->ieee80211_ptr->iftype, - params.beacon_interval); + params->beacon_interval); if (err) - return err; + goto out; /* * In theory, some of these attributes should be required here @@ -5366,129 +5515,157 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) * additional information -- drivers must check! */ if (info->attrs[NL80211_ATTR_SSID]) { - params.ssid = nla_data(info->attrs[NL80211_ATTR_SSID]); - params.ssid_len = + params->ssid = nla_data(info->attrs[NL80211_ATTR_SSID]); + params->ssid_len = nla_len(info->attrs[NL80211_ATTR_SSID]); - if (params.ssid_len == 0) - return -EINVAL; + if (params->ssid_len == 0) { + err = -EINVAL; + goto out; + } } if (info->attrs[NL80211_ATTR_HIDDEN_SSID]) - params.hidden_ssid = nla_get_u32( + params->hidden_ssid = nla_get_u32( info->attrs[NL80211_ATTR_HIDDEN_SSID]); - params.privacy = !!info->attrs[NL80211_ATTR_PRIVACY]; + params->privacy = !!info->attrs[NL80211_ATTR_PRIVACY]; if (info->attrs[NL80211_ATTR_AUTH_TYPE]) { - params.auth_type = nla_get_u32( + params->auth_type = nla_get_u32( info->attrs[NL80211_ATTR_AUTH_TYPE]); - if (!nl80211_valid_auth_type(rdev, params.auth_type, - NL80211_CMD_START_AP)) - return -EINVAL; + if (!nl80211_valid_auth_type(rdev, params->auth_type, + NL80211_CMD_START_AP)) { + err = -EINVAL; + goto out; + } } else - params.auth_type = NL80211_AUTHTYPE_AUTOMATIC; + params->auth_type = NL80211_AUTHTYPE_AUTOMATIC; - err = nl80211_crypto_settings(rdev, info, ¶ms.crypto, + err = nl80211_crypto_settings(rdev, info, ¶ms->crypto, NL80211_MAX_NR_CIPHER_SUITES); if (err) - return err; + goto out; if (info->attrs[NL80211_ATTR_INACTIVITY_TIMEOUT]) { - if (!(rdev->wiphy.features & NL80211_FEATURE_INACTIVITY_TIMER)) - return -EOPNOTSUPP; - params.inactivity_timeout = nla_get_u16( + if (!(rdev->wiphy.features & NL80211_FEATURE_INACTIVITY_TIMER)) { + err = -EOPNOTSUPP; + goto out; + } + params->inactivity_timeout = nla_get_u16( info->attrs[NL80211_ATTR_INACTIVITY_TIMEOUT]); } if (info->attrs[NL80211_ATTR_P2P_CTWINDOW]) { - if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_GO) - return -EINVAL; - params.p2p_ctwindow = + if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_GO) { + err = -EINVAL; + goto out; + } + params->p2p_ctwindow = nla_get_u8(info->attrs[NL80211_ATTR_P2P_CTWINDOW]); - if (params.p2p_ctwindow != 0 && - !(rdev->wiphy.features & NL80211_FEATURE_P2P_GO_CTWIN)) - return -EINVAL; + if (params->p2p_ctwindow != 0 && + !(rdev->wiphy.features & NL80211_FEATURE_P2P_GO_CTWIN)) { + err = -EINVAL; + goto out; + } } if (info->attrs[NL80211_ATTR_P2P_OPPPS]) { u8 tmp; - if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_GO) - return -EINVAL; + if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_GO) { + err = -EINVAL; + goto out; + } tmp = nla_get_u8(info->attrs[NL80211_ATTR_P2P_OPPPS]); - params.p2p_opp_ps = tmp; - if (params.p2p_opp_ps != 0 && - !(rdev->wiphy.features & NL80211_FEATURE_P2P_GO_OPPPS)) - return -EINVAL; + params->p2p_opp_ps = tmp; + if (params->p2p_opp_ps != 0 && + !(rdev->wiphy.features & NL80211_FEATURE_P2P_GO_OPPPS)) { + err = -EINVAL; + goto out; + } } if (info->attrs[NL80211_ATTR_WIPHY_FREQ]) { - err = nl80211_parse_chandef(rdev, info, ¶ms.chandef); + err = nl80211_parse_chandef(rdev, info, ¶ms->chandef); if (err) - return err; + goto out; } else if (wdev->preset_chandef.chan) { - params.chandef = wdev->preset_chandef; - } else if (!nl80211_get_ap_channel(rdev, ¶ms)) - return -EINVAL; + params->chandef = wdev->preset_chandef; + } else if (!nl80211_get_ap_channel(rdev, params)) { + err = -EINVAL; + goto out; + } - if (!cfg80211_reg_can_beacon_relax(&rdev->wiphy, ¶ms.chandef, - wdev->iftype)) - return -EINVAL; + if (!cfg80211_reg_can_beacon_relax(&rdev->wiphy, ¶ms->chandef, + wdev->iftype)) { + err = -EINVAL; + goto out; + } if (info->attrs[NL80211_ATTR_TX_RATES]) { err = nl80211_parse_tx_bitrate_mask(info, info->attrs, NL80211_ATTR_TX_RATES, - ¶ms.beacon_rate, + ¶ms->beacon_rate, dev, false); if (err) - return err; + goto out; - err = validate_beacon_tx_rate(rdev, params.chandef.chan->band, - ¶ms.beacon_rate); + err = validate_beacon_tx_rate(rdev, params->chandef.chan->band, + ¶ms->beacon_rate); if (err) - return err; + goto out; } if (info->attrs[NL80211_ATTR_SMPS_MODE]) { - params.smps_mode = + params->smps_mode = nla_get_u8(info->attrs[NL80211_ATTR_SMPS_MODE]); - switch (params.smps_mode) { + switch (params->smps_mode) { case NL80211_SMPS_OFF: break; case NL80211_SMPS_STATIC: if (!(rdev->wiphy.features & - NL80211_FEATURE_STATIC_SMPS)) - return -EINVAL; + NL80211_FEATURE_STATIC_SMPS)) { + err = -EINVAL; + goto out; + } break; case NL80211_SMPS_DYNAMIC: if (!(rdev->wiphy.features & - NL80211_FEATURE_DYNAMIC_SMPS)) - return -EINVAL; + NL80211_FEATURE_DYNAMIC_SMPS)) { + err = -EINVAL; + goto out; + } break; default: - return -EINVAL; + err = -EINVAL; + goto out; } } else { - params.smps_mode = NL80211_SMPS_OFF; + params->smps_mode = NL80211_SMPS_OFF; } - params.pbss = nla_get_flag(info->attrs[NL80211_ATTR_PBSS]); - if (params.pbss && !rdev->wiphy.bands[NL80211_BAND_60GHZ]) - return -EOPNOTSUPP; + params->pbss = nla_get_flag(info->attrs[NL80211_ATTR_PBSS]); + if (params->pbss && !rdev->wiphy.bands[NL80211_BAND_60GHZ]) { + err = -EOPNOTSUPP; + goto out; + } if (info->attrs[NL80211_ATTR_ACL_POLICY]) { - params.acl = parse_acl_data(&rdev->wiphy, info); - if (IS_ERR(params.acl)) - return PTR_ERR(params.acl); + params->acl = parse_acl_data(&rdev->wiphy, info); + if (IS_ERR(params->acl)) { + err = PTR_ERR(params->acl); + params->acl = NULL; + goto out; + } } - params.twt_responder = + params->twt_responder = nla_get_flag(info->attrs[NL80211_ATTR_TWT_RESPONDER]); if (info->attrs[NL80211_ATTR_HE_OBSS_PD]) { err = nl80211_parse_he_obss_pd( info->attrs[NL80211_ATTR_HE_OBSS_PD], - ¶ms.he_obss_pd); + ¶ms->he_obss_pd); if (err) goto out; } @@ -5496,7 +5673,7 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NL80211_ATTR_HE_BSS_COLOR]) { err = nl80211_parse_he_bss_color( info->attrs[NL80211_ATTR_HE_BSS_COLOR], - ¶ms.he_bss_color); + ¶ms->he_bss_color); if (err) goto out; } @@ -5504,7 +5681,7 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NL80211_ATTR_FILS_DISCOVERY]) { err = nl80211_parse_fils_discovery(rdev, info->attrs[NL80211_ATTR_FILS_DISCOVERY], - ¶ms); + params); if (err) goto out; } @@ -5512,24 +5689,35 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NL80211_ATTR_UNSOL_BCAST_PROBE_RESP]) { err = nl80211_parse_unsol_bcast_probe_resp( rdev, info->attrs[NL80211_ATTR_UNSOL_BCAST_PROBE_RESP], - ¶ms); + params); if (err) goto out; } - nl80211_calculate_ap_params(¶ms); + if (info->attrs[NL80211_ATTR_MBSSID_CONFIG]) { + err = nl80211_parse_mbssid_config(&rdev->wiphy, dev, + info->attrs[NL80211_ATTR_MBSSID_CONFIG], + ¶ms->mbssid_config, + params->beacon.mbssid_ies ? + params->beacon.mbssid_ies->cnt : + 0); + if (err) + goto out; + } + + nl80211_calculate_ap_params(params); if (info->attrs[NL80211_ATTR_EXTERNAL_AUTH_SUPPORT]) - params.flags |= AP_SETTINGS_EXTERNAL_AUTH_SUPPORT; + params->flags |= AP_SETTINGS_EXTERNAL_AUTH_SUPPORT; wdev_lock(wdev); - err = rdev_start_ap(rdev, dev, ¶ms); + err = rdev_start_ap(rdev, dev, params); if (!err) { - wdev->preset_chandef = params.chandef; - wdev->beacon_interval = params.beacon_interval; - wdev->chandef = params.chandef; - wdev->ssid_len = params.ssid_len; - memcpy(wdev->ssid, params.ssid, wdev->ssid_len); + wdev->preset_chandef = params->chandef; + wdev->beacon_interval = params->beacon_interval; + wdev->chandef = params->chandef; + wdev->ssid_len = params->ssid_len; + memcpy(wdev->ssid, params->ssid, wdev->ssid_len); if (info->attrs[NL80211_ATTR_SOCKET_OWNER]) wdev->conn_owner_nlportid = info->snd_portid; @@ -5537,7 +5725,13 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) wdev_unlock(wdev); out: - kfree(params.acl); + kfree(params->acl); + kfree(params->beacon.mbssid_ies); + if (params->mbssid_config.tx_wdev && + params->mbssid_config.tx_wdev->netdev && + params->mbssid_config.tx_wdev->netdev != dev) + dev_put(params->mbssid_config.tx_wdev->netdev); + kfree(params); return err; } @@ -5562,12 +5756,14 @@ static int nl80211_set_beacon(struct sk_buff *skb, struct genl_info *info) err = nl80211_parse_beacon(rdev, info->attrs, ¶ms); if (err) - return err; + goto out; wdev_lock(wdev); err = rdev_change_beacon(rdev, dev, ¶ms); wdev_unlock(wdev); +out: + kfree(params.mbssid_ies); return err; } @@ -9244,12 +9440,14 @@ static int nl80211_channel_switch(struct sk_buff *skb, struct genl_info *info) err = nl80211_parse_beacon(rdev, info->attrs, ¶ms.beacon_after); if (err) - return err; + goto free; csa_attrs = kcalloc(NL80211_ATTR_MAX + 1, sizeof(*csa_attrs), GFP_KERNEL); - if (!csa_attrs) - return -ENOMEM; + if (!csa_attrs) { + err = -ENOMEM; + goto free; + } err = nla_parse_nested_deprecated(csa_attrs, NL80211_ATTR_MAX, info->attrs[NL80211_ATTR_CSA_IES], @@ -9367,6 +9565,8 @@ skip_beacons: wdev_unlock(wdev); free: + kfree(params.beacon_after.mbssid_ies); + kfree(params.beacon_csa.mbssid_ies); kfree(csa_attrs); return err; } @@ -11767,8 +11967,9 @@ static int nl80211_set_cqm_rssi(struct genl_info *info, if (n_thresholds) { struct cfg80211_cqm_config *cqm_config; - cqm_config = kzalloc(sizeof(struct cfg80211_cqm_config) + - n_thresholds * sizeof(s32), GFP_KERNEL); + cqm_config = kzalloc(struct_size(cqm_config, rssi_thresholds, + n_thresholds), + GFP_KERNEL); if (!cqm_config) { err = -ENOMEM; goto unlock; @@ -11777,7 +11978,8 @@ static int nl80211_set_cqm_rssi(struct genl_info *info, cqm_config->rssi_hyst = hysteresis; cqm_config->n_rssi_thresholds = n_thresholds; memcpy(cqm_config->rssi_thresholds, thresholds, - n_thresholds * sizeof(s32)); + flex_array_size(cqm_config, rssi_thresholds, + n_thresholds)); wdev->cqm_config = cqm_config; } @@ -14900,10 +15102,35 @@ static int nl80211_color_change(struct sk_buff *skb, struct genl_info *info) wdev_unlock(wdev); out: + kfree(params.beacon_next.mbssid_ies); + kfree(params.beacon_color_change.mbssid_ies); kfree(tb); return err; } +static int nl80211_set_fils_aad(struct sk_buff *skb, + struct genl_info *info) +{ + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct net_device *dev = info->user_ptr[1]; + struct cfg80211_fils_aad fils_aad = {}; + u8 *nonces; + + if (!info->attrs[NL80211_ATTR_MAC] || + !info->attrs[NL80211_ATTR_FILS_KEK] || + !info->attrs[NL80211_ATTR_FILS_NONCES]) + return -EINVAL; + + fils_aad.macaddr = nla_data(info->attrs[NL80211_ATTR_MAC]); + fils_aad.kek_len = nla_len(info->attrs[NL80211_ATTR_FILS_KEK]); + fils_aad.kek = nla_data(info->attrs[NL80211_ATTR_FILS_KEK]); + nonces = nla_data(info->attrs[NL80211_ATTR_FILS_NONCES]); + fils_aad.snonce = nonces; + fils_aad.anonce = nonces + FILS_NONCE_LEN; + + return rdev_set_fils_aad(rdev, dev, &fils_aad); +} + #define NL80211_FLAG_NEED_WIPHY 0x01 #define NL80211_FLAG_NEED_NETDEV 0x02 #define NL80211_FLAG_NEED_RTNL 0x04 @@ -15081,9 +15308,7 @@ static int nl80211_set_sar_specs(struct sk_buff *skb, struct genl_info *info) if (specs > rdev->wiphy.sar_capa->num_freq_ranges) return -EINVAL; - sar_spec = kzalloc(sizeof(*sar_spec) + - specs * sizeof(struct cfg80211_sar_sub_specs), - GFP_KERNEL); + sar_spec = kzalloc(struct_size(sar_spec, sub_specs, specs), GFP_KERNEL); if (!sar_spec) return -ENOMEM; @@ -15907,6 +16132,13 @@ static const struct genl_small_ops nl80211_small_ops[] = { .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, }, + { + .cmd = NL80211_CMD_SET_FILS_AAD, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = nl80211_set_fils_aad, + .flags = GENL_UNS_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP, + }, }; static struct genl_family nl80211_fam __ro_after_init = { diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h index ce6bf218a1a3..cc1efec4b27b 100644 --- a/net/wireless/rdev-ops.h +++ b/net/wireless/rdev-ops.h @@ -1381,4 +1381,18 @@ static inline int rdev_color_change(struct cfg80211_registered_device *rdev, return ret; } +static inline int +rdev_set_fils_aad(struct cfg80211_registered_device *rdev, + struct net_device *dev, struct cfg80211_fils_aad *fils_aad) +{ + int ret = -EOPNOTSUPP; + + trace_rdev_set_fils_aad(&rdev->wiphy, dev, fils_aad); + if (rdev->ops->set_fils_aad) + ret = rdev->ops->set_fils_aad(&rdev->wiphy, dev, fils_aad); + trace_rdev_return_int(&rdev->wiphy, ret); + + return ret; +} + #endif /* __CFG80211_RDEV_OPS */ diff --git a/net/wireless/scan.c b/net/wireless/scan.c index adc0d14cfd86..22e92be61938 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -383,7 +383,7 @@ static bool is_bss(struct cfg80211_bss *a, const u8 *bssid, const u8 *ssid, size_t ssid_len) { const struct cfg80211_bss_ies *ies; - const u8 *ssidie; + const struct element *ssid_elem; if (bssid && !ether_addr_equal(a->bssid, bssid)) return false; @@ -394,12 +394,12 @@ static bool is_bss(struct cfg80211_bss *a, const u8 *bssid, ies = rcu_access_pointer(a->ies); if (!ies) return false; - ssidie = cfg80211_find_ie(WLAN_EID_SSID, ies->data, ies->len); - if (!ssidie) + ssid_elem = cfg80211_find_elem(WLAN_EID_SSID, ies->data, ies->len); + if (!ssid_elem) return false; - if (ssidie[1] != ssid_len) + if (ssid_elem->datalen != ssid_len) return false; - return memcmp(ssidie + 2, ssid, ssid_len) == 0; + return memcmp(ssid_elem->data, ssid, ssid_len) == 0; } static int @@ -1794,25 +1794,13 @@ cfg80211_bss_update(struct cfg80211_registered_device *rdev, return NULL; } -/* - * Update RX channel information based on the available frame payload - * information. This is mainly for the 2.4 GHz band where frames can be received - * from neighboring channels and the Beacon frames use the DSSS Parameter Set - * element to indicate the current (transmitting) channel, but this might also - * be needed on other bands if RX frequency does not match with the actual - * operating channel of a BSS. - */ -static struct ieee80211_channel * -cfg80211_get_bss_channel(struct wiphy *wiphy, const u8 *ie, size_t ielen, - struct ieee80211_channel *channel, - enum nl80211_bss_scan_width scan_width) +int cfg80211_get_ies_channel_number(const u8 *ie, size_t ielen, + enum nl80211_band band) { const u8 *tmp; - u32 freq; int channel_number = -1; - struct ieee80211_channel *alt_channel; - if (channel->band == NL80211_BAND_S1GHZ) { + if (band == NL80211_BAND_S1GHZ) { tmp = cfg80211_find_ie(WLAN_EID_S1G_OPERATION, ie, ielen); if (tmp && tmp[1] >= sizeof(struct ieee80211_s1g_oper_ie)) { struct ieee80211_s1g_oper_ie *s1gop = (void *)(tmp + 2); @@ -1833,6 +1821,29 @@ cfg80211_get_bss_channel(struct wiphy *wiphy, const u8 *ie, size_t ielen, } } + return channel_number; +} +EXPORT_SYMBOL(cfg80211_get_ies_channel_number); + +/* + * Update RX channel information based on the available frame payload + * information. This is mainly for the 2.4 GHz band where frames can be received + * from neighboring channels and the Beacon frames use the DSSS Parameter Set + * element to indicate the current (transmitting) channel, but this might also + * be needed on other bands if RX frequency does not match with the actual + * operating channel of a BSS. + */ +static struct ieee80211_channel * +cfg80211_get_bss_channel(struct wiphy *wiphy, const u8 *ie, size_t ielen, + struct ieee80211_channel *channel, + enum nl80211_bss_scan_width scan_width) +{ + u32 freq; + int channel_number; + struct ieee80211_channel *alt_channel; + + channel_number = cfg80211_get_ies_channel_number(ie, ielen, channel->band); + if (channel_number < 0) { /* No channel information in frame payload */ return channel; @@ -2075,12 +2086,12 @@ static void cfg80211_parse_mbssid_data(struct wiphy *wiphy, if (!non_tx_data) return; - if (!cfg80211_find_ie(WLAN_EID_MULTIPLE_BSSID, ie, ielen)) + if (!cfg80211_find_elem(WLAN_EID_MULTIPLE_BSSID, ie, ielen)) return; if (!wiphy->support_mbssid) return; if (wiphy->support_only_he_mbssid && - !cfg80211_find_ext_ie(WLAN_EID_EXT_HE_CAPABILITY, ie, ielen)) + !cfg80211_find_ext_elem(WLAN_EID_EXT_HE_CAPABILITY, ie, ielen)) return; new_ie = kmalloc(IEEE80211_MAX_DATA_LEN, gfp); @@ -2447,10 +2458,10 @@ cfg80211_inform_bss_frame_data(struct wiphy *wiphy, res = cfg80211_inform_single_bss_frame_data(wiphy, data, mgmt, len, gfp); if (!res || !wiphy->support_mbssid || - !cfg80211_find_ie(WLAN_EID_MULTIPLE_BSSID, ie, ielen)) + !cfg80211_find_elem(WLAN_EID_MULTIPLE_BSSID, ie, ielen)) return res; if (wiphy->support_only_he_mbssid && - !cfg80211_find_ext_ie(WLAN_EID_EXT_HE_CAPABILITY, ie, ielen)) + !cfg80211_find_ext_elem(WLAN_EID_EXT_HE_CAPABILITY, ie, ielen)) return res; non_tx_data.tx_bss = res; diff --git a/net/wireless/trace.h b/net/wireless/trace.h index 19b78d472283..ad6c16a06bcb 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -167,6 +167,19 @@ __entry->center_freq1, __entry->freq1_offset, \ __entry->center_freq2 +#define FILS_AAD_ASSIGN(fa) \ + do { \ + if (fa) { \ + ether_addr_copy(__entry->macaddr, fa->macaddr); \ + __entry->kek_len = fa->kek_len; \ + } else { \ + eth_zero_addr(__entry->macaddr); \ + __entry->kek_len = 0; \ + } \ + } while (0) +#define FILS_AAD_PR_FMT \ + "macaddr: %pM, kek_len: %d" + #define SINFO_ENTRY __field(int, generation) \ __field(u32, connected_time) \ __field(u32, inactive_time) \ @@ -2614,6 +2627,24 @@ DEFINE_EVENT(wiphy_wdev_cookie_evt, rdev_abort_pmsr, TP_ARGS(wiphy, wdev, cookie) ); +TRACE_EVENT(rdev_set_fils_aad, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, + struct cfg80211_fils_aad *fils_aad), + TP_ARGS(wiphy, netdev, fils_aad), + TP_STRUCT__entry(WIPHY_ENTRY + NETDEV_ENTRY + __array(u8, macaddr, ETH_ALEN) + __field(u8, kek_len) + ), + TP_fast_assign(WIPHY_ASSIGN; + NETDEV_ASSIGN; + FILS_AAD_ASSIGN(fils_aad); + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", " FILS_AAD_PR_FMT, + WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->macaddr, + __entry->kek_len) +); + /************************************************************* * cfg80211 exported functions traces * *************************************************************/ diff --git a/net/wireless/util.c b/net/wireless/util.c index a1a99a574984..5ff1f8726faf 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -80,6 +80,7 @@ u32 ieee80211_channel_to_freq_khz(int chan, enum nl80211_band band) return 0; /* not supported */ switch (band) { case NL80211_BAND_2GHZ: + case NL80211_BAND_LC: if (chan == 14) return MHZ_TO_KHZ(2484); else if (chan < 14) @@ -209,6 +210,7 @@ static void set_mandatory_flags_band(struct ieee80211_supported_band *sband) WARN_ON(want); break; case NL80211_BAND_2GHZ: + case NL80211_BAND_LC: want = 7; for (i = 0; i < sband->n_bitrates; i++) { switch (sband->bitrates[i].bitrate) { diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh index 8817851da7a9..e9a82cae8c9a 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh @@ -13,7 +13,7 @@ # | # +-------------------|-----+ # | SW1 | | -# | $swp1 + | +# | $swp1 + | # | 192.0.2.2/28 | # | | # | + g1a (gre) | @@ -27,8 +27,8 @@ # | # +--|----------------------+ # | | VRF2 | -# | + $rp2 | -# | 198.51.100.2/28 | +# | + $rp2 | +# | 198.51.100.2/28 | # +-------------------------+ lib_dir=$(dirname $0)/../../../net/forwarding @@ -116,12 +116,16 @@ cleanup() forwarding_restore } -ecn_payload_get() +ipip_payload_get() { + local flags=$1; shift + local key=$1; shift + p=$(: - )"0"$( : GRE flags + )"$flags"$( : GRE flags )"0:00:"$( : Reserved + version )"08:00:"$( : ETH protocol type + )"$key"$( : Key )"4"$( : IP version )"5:"$( : IHL )"00:"$( : IP TOS @@ -137,6 +141,11 @@ ecn_payload_get() echo $p } +ecn_payload_get() +{ + echo $(ipip_payload_get "0") +} + ecn_decap_test() { local trap_name="decap_error" @@ -171,31 +180,6 @@ ecn_decap_test() tc filter del dev $swp1 egress protocol ip pref 1 handle 101 flower } -ipip_payload_get() -{ - local flags=$1; shift - local key=$1; shift - - p=$(: - )"$flags"$( : GRE flags - )"0:00:"$( : Reserved + version - )"08:00:"$( : ETH protocol type - )"$key"$( : Key - )"4"$( : IP version - )"5:"$( : IHL - )"00:"$( : IP TOS - )"00:14:"$( : IP total length - )"00:00:"$( : IP identification - )"20:00:"$( : IP flags + frag off - )"30:"$( : IP TTL - )"01:"$( : IP proto - )"E7:E6:"$( : IP header csum - )"C0:00:01:01:"$( : IP saddr : 192.0.1.1 - )"C0:00:02:01:"$( : IP daddr : 192.0.2.1 - ) - echo $p -} - no_matching_tunnel_test() { local trap_name="decap_error" @@ -239,7 +223,8 @@ decap_error_test() no_matching_tunnel_test "Decap error: Source IP check failed" \ 192.0.2.68 "0" no_matching_tunnel_test \ - "Decap error: Key exists but was not expected" $sip "2" ":E9:" + "Decap error: Key exists but was not expected" $sip "2" \ + "00:00:00:E9:" # Destroy the tunnel and create new one with key __addr_add_del g1 del 192.0.2.65/32 @@ -251,7 +236,8 @@ decap_error_test() no_matching_tunnel_test \ "Decap error: Key does not exist but was expected" $sip "0" no_matching_tunnel_test \ - "Decap error: Packet has a wrong key field" $sip "2" "E8:" + "Decap error: Packet has a wrong key field" $sip "2" \ + "00:00:00:E8:" } trap cleanup EXIT diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_offload.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_offload.sh new file mode 100755 index 000000000000..ade79ef08de3 --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/sch_offload.sh @@ -0,0 +1,276 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test qdisc offload indication + + +ALL_TESTS=" + test_root + test_etsprio +" +NUM_NETIFS=1 +lib_dir=$(dirname $0)/../../../net/forwarding +source $lib_dir/lib.sh + +check_not_offloaded() +{ + local handle=$1; shift + local h + local offloaded + + h=$(qdisc_stats_get $h1 "$handle" .handle) + [[ $h == '"'$handle'"' ]] + check_err $? "Qdisc with handle $handle does not exist" + + offloaded=$(qdisc_stats_get $h1 "$handle" .offloaded) + [[ $offloaded == true ]] + check_fail $? "Qdisc with handle $handle offloaded, but should not be" +} + +check_all_offloaded() +{ + local handle=$1; shift + + if [[ ! -z $handle ]]; then + local offloaded=$(qdisc_stats_get $h1 "$handle" .offloaded) + [[ $offloaded == true ]] + check_err $? "Qdisc with handle $handle not offloaded" + fi + + local unoffloaded=$(tc q sh dev $h1 invisible | + grep -v offloaded | + sed s/root/parent\ root/ | + cut -d' ' -f 5) + [[ -z $unoffloaded ]] + check_err $? "Qdiscs with following parents not offloaded: $unoffloaded" + + pre_cleanup +} + +with_ets() +{ + local handle=$1; shift + local locus=$1; shift + + tc qdisc add dev $h1 $locus handle $handle \ + ets bands 8 priomap 7 6 5 4 3 2 1 0 + "$@" + tc qdisc del dev $h1 $locus +} + +with_prio() +{ + local handle=$1; shift + local locus=$1; shift + + tc qdisc add dev $h1 $locus handle $handle \ + prio bands 8 priomap 7 6 5 4 3 2 1 0 + "$@" + tc qdisc del dev $h1 $locus +} + +with_red() +{ + local handle=$1; shift + local locus=$1; shift + + tc qdisc add dev $h1 $locus handle $handle \ + red limit 1000000 min 200000 max 300000 probability 0.5 avpkt 1500 + "$@" + tc qdisc del dev $h1 $locus +} + +with_tbf() +{ + local handle=$1; shift + local locus=$1; shift + + tc qdisc add dev $h1 $locus handle $handle \ + tbf rate 400Mbit burst 128K limit 1M + "$@" + tc qdisc del dev $h1 $locus +} + +with_pfifo() +{ + local handle=$1; shift + local locus=$1; shift + + tc qdisc add dev $h1 $locus handle $handle pfifo limit 100K + "$@" + tc qdisc del dev $h1 $locus +} + +with_bfifo() +{ + local handle=$1; shift + local locus=$1; shift + + tc qdisc add dev $h1 $locus handle $handle bfifo limit 100K + "$@" + tc qdisc del dev $h1 $locus +} + +with_drr() +{ + local handle=$1; shift + local locus=$1; shift + + tc qdisc add dev $h1 $locus handle $handle drr + "$@" + tc qdisc del dev $h1 $locus +} + +with_qdiscs() +{ + local handle=$1; shift + local parent=$1; shift + local kind=$1; shift + local next_handle=$((handle * 2)) + local locus; + + if [[ $kind == "--" ]]; then + local cmd=$1; shift + $cmd $(printf %x: $parent) "$@" + else + if ((parent == 0)); then + locus=root + else + locus=$(printf "parent %x:1" $parent) + fi + + with_$kind $(printf %x: $handle) "$locus" \ + with_qdiscs $next_handle $handle "$@" + fi +} + +get_name() +{ + local parent=$1; shift + local name=$(echo "" "${@^^}" | tr ' ' -) + + if ((parent != 0)); then + kind=$(qdisc_stats_get $h1 $parent: .kind) + kind=${kind%\"} + kind=${kind#\"} + name="-${kind^^}$name" + fi + + echo root$name +} + +do_test_offloaded() +{ + local handle=$1; shift + local parent=$1; shift + + RET=0 + with_qdiscs $handle $parent "$@" -- check_all_offloaded + log_test $(get_name $parent "$@")" offloaded" +} + +do_test_nooffload() +{ + local handle=$1; shift + local parent=$1; shift + + local name=$(echo "${@^^}" | tr ' ' -) + local kind + + RET=0 + with_qdiscs $handle $parent "$@" -- check_not_offloaded + log_test $(get_name $parent "$@")" not offloaded" +} + +do_test_combinations() +{ + local handle=$1; shift + local parent=$1; shift + + local cont + local leaf + local fifo + + for cont in "" ets prio; do + for leaf in "" red tbf "red tbf" "tbf red"; do + for fifo in "" pfifo bfifo; do + if [[ -z "$cont$leaf$fifo" ]]; then + continue + fi + do_test_offloaded $handle $parent \ + $cont $leaf $fifo + done + done + done + + for cont in ets prio; do + for leaf in red tbf; do + do_test_nooffload $handle $parent $cont red tbf $leaf + do_test_nooffload $handle $parent $cont tbf red $leaf + done + for leaf in "red red" "tbf tbf"; do + do_test_nooffload $handle $parent $cont $leaf + done + done + + do_test_nooffload $handle $parent drr +} + +test_root() +{ + do_test_combinations 1 0 +} + +do_test_etsprio() +{ + local parent=$1; shift + local tbfpfx=$1; shift + local cont + + for cont in ets prio; do + RET=0 + with_$cont 8: "$parent" \ + with_red 11: "parent 8:1" \ + with_red 12: "parent 8:2" \ + with_tbf 13: "parent 8:3" \ + with_tbf 14: "parent 8:4" \ + check_all_offloaded + log_test "root$tbfpfx-ETS-{RED,TBF} offloaded" + + RET=0 + with_$cont 8: "$parent" \ + with_red 81: "parent 8:1" \ + with_tbf 811: "parent 81:1" \ + with_tbf 84: "parent 8:4" \ + with_red 841: "parent 84:1" \ + check_all_offloaded + log_test "root$tbfpfx-ETS-{RED-TBF,TBF-RED} offloaded" + + RET=0 + with_$cont 8: "$parent" \ + with_red 81: "parent 8:1" \ + with_tbf 811: "parent 81:1" \ + with_bfifo 8111: "parent 811:1" \ + with_tbf 82: "parent 8:2" \ + with_red 821: "parent 82:1" \ + with_bfifo 8211: "parent 821:1" \ + check_all_offloaded + log_test "root$tbfpfx-ETS-{RED-TBF-bFIFO,TBF-RED-bFIFO} offloaded" + done +} + +test_etsprio() +{ + do_test_etsprio root "" +} + +cleanup() +{ + tc qdisc del dev $h1 root &>/dev/null +} + +trap cleanup EXIT +h1=${NETIFS[p1]} +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh index 33ddd01689be..dd90cd87d4f9 100644 --- a/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh @@ -331,6 +331,14 @@ get_nmarked() ethtool_stats_get $swp3 ecn_marked } +get_qdisc_nmarked() +{ + local vlan=$1; shift + + busywait_for_counter 1100 +1 \ + qdisc_stats_get $swp3 $(get_qdisc_handle $vlan) .marked +} + get_qdisc_npackets() { local vlan=$1; shift @@ -384,14 +392,15 @@ build_backlog() check_marking() { + local get_nmarked=$1; shift local vlan=$1; shift local cond=$1; shift local npackets_0=$(get_qdisc_npackets $vlan) - local nmarked_0=$(get_nmarked $vlan) + local nmarked_0=$($get_nmarked $vlan) sleep 5 local npackets_1=$(get_qdisc_npackets $vlan) - local nmarked_1=$(get_nmarked $vlan) + local nmarked_1=$($get_nmarked $vlan) local nmarked_d=$((nmarked_1 - nmarked_0)) local npackets_d=$((npackets_1 - npackets_0)) @@ -404,6 +413,7 @@ check_marking() ecn_test_common() { local name=$1; shift + local get_nmarked=$1; shift local vlan=$1; shift local limit=$1; shift local backlog @@ -416,7 +426,7 @@ ecn_test_common() RET=0 backlog=$(build_backlog $vlan $((2 * limit / 3)) udp) check_err $? "Could not build the requested backlog" - pct=$(check_marking $vlan "== 0") + pct=$(check_marking "$get_nmarked" $vlan "== 0") check_err $? "backlog $backlog / $limit Got $pct% marked packets, expected == 0." log_test "TC $((vlan - 10)): $name backlog < limit" @@ -426,22 +436,23 @@ ecn_test_common() RET=0 backlog=$(build_backlog $vlan $((3 * limit / 2)) tcp tos=0x01) check_err $? "Could not build the requested backlog" - pct=$(check_marking $vlan ">= 95") + pct=$(check_marking "$get_nmarked" $vlan ">= 95") check_err $? "backlog $backlog / $limit Got $pct% marked packets, expected >= 95." log_test "TC $((vlan - 10)): $name backlog > limit" } -do_ecn_test() +__do_ecn_test() { + local get_nmarked=$1; shift local vlan=$1; shift local limit=$1; shift - local name=ECN + local name=${1-ECN}; shift start_tcp_traffic $h1.$vlan $(ipaddr 1 $vlan) $(ipaddr 3 $vlan) \ $h3_mac tos=0x01 sleep 1 - ecn_test_common "$name" $vlan $limit + ecn_test_common "$name" "$get_nmarked" $vlan $limit # Up there we saw that UDP gets accepted when backlog is below the # limit. Now that it is above, it should all get dropped, and backlog @@ -455,6 +466,26 @@ do_ecn_test() sleep 1 } +do_ecn_test() +{ + local vlan=$1; shift + local limit=$1; shift + + __do_ecn_test get_nmarked "$vlan" "$limit" +} + +do_ecn_test_perband() +{ + local vlan=$1; shift + local limit=$1; shift + + # Per-band ECN counters are not supported on Spectrum-1 and Spectrum-2. + [[ "$DEVLINK_VIDDID" == "15b3:cb84" || + "$DEVLINK_VIDDID" == "15b3:cf6c" ]] && return + + __do_ecn_test get_qdisc_nmarked "$vlan" "$limit" "per-band ECN" +} + do_ecn_nodrop_test() { local vlan=$1; shift @@ -465,7 +496,7 @@ do_ecn_nodrop_test() $h3_mac tos=0x01 sleep 1 - ecn_test_common "$name" $vlan $limit + ecn_test_common "$name" get_nmarked $vlan $limit # Up there we saw that UDP gets accepted when backlog is below the # limit. Now that it is above, in nodrop mode, make sure it goes to @@ -495,7 +526,7 @@ do_red_test() RET=0 backlog=$(build_backlog $vlan $((2 * limit / 3)) tcp tos=0x01) check_err $? "Could not build the requested backlog" - pct=$(check_marking $vlan "== 0") + pct=$(check_marking get_nmarked $vlan "== 0") check_err $? "backlog $backlog / $limit Got $pct% marked packets, expected == 0." log_test "TC $((vlan - 10)): RED backlog < limit" @@ -503,7 +534,7 @@ do_red_test() RET=0 backlog=$(build_backlog $vlan $((3 * limit / 2)) tcp tos=0x01) check_fail $? "Traffic went into backlog instead of being early-dropped" - pct=$(check_marking $vlan "== 0") + pct=$(check_marking get_nmarked $vlan "== 0") check_err $? "backlog $backlog / $limit Got $pct% marked packets, expected == 0." local diff=$((limit - backlog)) pct=$((100 * diff / limit)) @@ -544,6 +575,53 @@ do_mc_backlog_test() log_test "TC $((vlan - 10)): Qdisc reports MC backlog" } +do_mark_test() +{ + local vlan=$1; shift + local limit=$1; shift + local subtest=$1; shift + local fetch_counter=$1; shift + local should_fail=$1; shift + local base + + RET=0 + + start_tcp_traffic $h1.$vlan $(ipaddr 1 $vlan) $(ipaddr 3 $vlan) \ + $h3_mac tos=0x01 + + # Create a bit of a backlog and observe no mirroring due to marks. + qevent_rule_install_$subtest + + build_backlog $vlan $((2 * limit / 3)) tcp tos=0x01 >/dev/null + + base=$($fetch_counter) + count=$(busywait 1100 until_counter_is ">= $((base + 1))" \ + $fetch_counter) + check_fail $? "Spurious packets ($base -> $count) observed without buffer pressure" + + # Above limit, everything should be mirrored, we should see lots of + # packets. + build_backlog $vlan $((3 * limit / 2)) tcp tos=0x01 >/dev/null + busywait_for_counter 1100 +10000 \ + $fetch_counter > /dev/null + check_err_fail "$should_fail" $? "ECN-marked packets $subtest'd" + + # When the rule is uninstalled, there should be no mirroring. + qevent_rule_uninstall_$subtest + busywait_for_counter 1100 +10 \ + $fetch_counter > /dev/null + check_fail $? "Spurious packets observed after uninstall" + + if ((should_fail)); then + log_test "TC $((vlan - 10)): marked packets not $subtest'd" + else + log_test "TC $((vlan - 10)): marked packets $subtest'd" + fi + + stop_traffic + sleep 1 +} + do_drop_test() { local vlan=$1; shift @@ -551,10 +629,8 @@ do_drop_test() local trigger=$1; shift local subtest=$1; shift local fetch_counter=$1; shift - local backlog local base local now - local pct RET=0 @@ -628,6 +704,22 @@ do_drop_mirror_test() tc filter del dev $h2 ingress pref 1 handle 101 flower } +do_mark_mirror_test() +{ + local vlan=$1; shift + local limit=$1; shift + + tc filter add dev $h2 ingress pref 1 handle 101 prot ip \ + flower skip_sw ip_proto tcp \ + action drop + + do_mark_test "$vlan" "$limit" mirror \ + qevent_counter_fetch_mirror \ + $(: should_fail=)0 + + tc filter del dev $h2 ingress pref 1 handle 101 flower +} + qevent_rule_install_trap() { tc filter add block 10 pref 1234 handle 102 matchall skip_sw \ @@ -655,3 +747,14 @@ do_drop_trap_test() do_drop_test "$vlan" "$limit" "$trap_name" trap \ "qevent_counter_fetch_trap $trap_name" } + +qevent_rule_install_trap_fwd() +{ + tc filter add block 10 pref 1234 handle 102 matchall skip_sw \ + action trap_fwd hw_stats disabled +} + +qevent_rule_uninstall_trap_fwd() +{ + tc filter del block 10 pref 1234 handle 102 matchall +} diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh index f3ef3274f9b3..1e5ad3209436 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh @@ -4,11 +4,13 @@ ALL_TESTS=" ping_ipv4 ecn_test + ecn_test_perband ecn_nodrop_test red_test mc_backlog_test red_mirror_test red_trap_test + ecn_mirror_test " : ${QDISC:=ets} source sch_red_core.sh @@ -21,26 +23,58 @@ source sch_red_core.sh BACKLOG1=200000 BACKLOG2=500000 -install_qdisc() +install_root_qdisc() +{ + tc qdisc add dev $swp3 root handle 10: $QDISC \ + bands 8 priomap 7 6 5 4 3 2 1 0 +} + +install_qdisc_tc0() { local -a args=("$@") - tc qdisc add dev $swp3 root handle 10: $QDISC \ - bands 8 priomap 7 6 5 4 3 2 1 0 tc qdisc add dev $swp3 parent 10:8 handle 108: red \ limit 1000000 min $BACKLOG1 max $((BACKLOG1 + 1)) \ probability 1.0 avpkt 8000 burst 38 "${args[@]}" +} + +install_qdisc_tc1() +{ + local -a args=("$@") + tc qdisc add dev $swp3 parent 10:7 handle 107: red \ limit 1000000 min $BACKLOG2 max $((BACKLOG2 + 1)) \ probability 1.0 avpkt 8000 burst 63 "${args[@]}" +} + +install_qdisc() +{ + install_root_qdisc + install_qdisc_tc0 "$@" + install_qdisc_tc1 "$@" sleep 1 } +uninstall_qdisc_tc0() +{ + tc qdisc del dev $swp3 parent 10:8 +} + +uninstall_qdisc_tc1() +{ + tc qdisc del dev $swp3 parent 10:7 +} + +uninstall_root_qdisc() +{ + tc qdisc del dev $swp3 root +} + uninstall_qdisc() { - tc qdisc del dev $swp3 parent 10:7 - tc qdisc del dev $swp3 parent 10:8 - tc qdisc del dev $swp3 root + uninstall_qdisc_tc0 + uninstall_qdisc_tc1 + uninstall_root_qdisc } ecn_test() @@ -53,6 +87,16 @@ ecn_test() uninstall_qdisc } +ecn_test_perband() +{ + install_qdisc ecn + + do_ecn_test_perband 10 $BACKLOG1 + do_ecn_test_perband 11 $BACKLOG2 + + uninstall_qdisc +} + ecn_nodrop_test() { install_qdisc ecn nodrop @@ -112,6 +156,16 @@ red_trap_test() uninstall_qdisc } +ecn_mirror_test() +{ + install_qdisc ecn qevent mark block 10 + + do_mark_mirror_test 10 $BACKLOG1 + do_mark_mirror_test 11 $BACKLOG2 + + uninstall_qdisc +} + trap cleanup EXIT setup_prepare diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_root.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_root.sh index ede9c38d3eff..d79a82f317d2 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/sch_red_root.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_root.sh @@ -4,6 +4,7 @@ ALL_TESTS=" ping_ipv4 ecn_test + ecn_test_perband ecn_nodrop_test red_test mc_backlog_test @@ -35,6 +36,13 @@ ecn_test() uninstall_qdisc } +ecn_test_perband() +{ + install_qdisc ecn + do_ecn_test_perband 10 $BACKLOG + uninstall_qdisc +} + ecn_nodrop_test() { install_qdisc ecn nodrop diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/devlink_trap_tunnel_ipip6.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/devlink_trap_tunnel_ipip6.sh new file mode 100755 index 000000000000..f62ce479c266 --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/devlink_trap_tunnel_ipip6.sh @@ -0,0 +1,250 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test devlink-trap tunnel exceptions functionality over mlxsw. +# Check all exception traps to make sure they are triggered under the right +# conditions. + +# +-------------------------+ +# | H1 | +# | $h1 + | +# | 2001:db8:1::1/64 | | +# +-------------------|-----+ +# | +# +-------------------|-----+ +# | SW1 | | +# | $swp1 + | +# | 2001:db8:1::2/64 | +# | | +# | + g1 (ip6gre) | +# | loc=2001:db8:3::1 | +# | rem=2001:db8:3::2 | +# | tos=inherit | +# | | +# | + $rp1 | +# | | 2001:db8:10::1/64 | +# +--|----------------------+ +# | +# +--|----------------------+ +# | | VRF2 | +# | + $rp2 | +# | 2001:db8:10::2/64 | +# +-------------------------+ + +lib_dir=$(dirname $0)/../../../../net/forwarding + +ALL_TESTS=" + decap_error_test +" + +NUM_NETIFS=4 +source $lib_dir/lib.sh +source $lib_dir/tc_common.sh +source $lib_dir/devlink_lib.sh + +h1_create() +{ + simple_if_init $h1 2001:db8:1::1/64 +} + +h1_destroy() +{ + simple_if_fini $h1 2001:db8:1::1/64 +} + +vrf2_create() +{ + simple_if_init $rp2 2001:db8:10::2/64 +} + +vrf2_destroy() +{ + simple_if_fini $rp2 2001:db8:10::2/64 +} + +switch_create() +{ + ip link set dev $swp1 up + __addr_add_del $swp1 add 2001:db8:1::2/64 + tc qdisc add dev $swp1 clsact + + tunnel_create g1 ip6gre 2001:db8:3::1 2001:db8:3::2 tos inherit \ + ttl inherit + ip link set dev g1 up + __addr_add_del g1 add 2001:db8:3::1/128 + + ip link set dev $rp1 up + __addr_add_del $rp1 add 2001:db8:10::1/64 +} + +switch_destroy() +{ + __addr_add_del $rp1 del 2001:db8:10::1/64 + ip link set dev $rp1 down + + __addr_add_del g1 del 2001:db8:3::1/128 + ip link set dev g1 down + tunnel_destroy g1 + + tc qdisc del dev $swp1 clsact + __addr_add_del $swp1 del 2001:db8:1::2/64 + ip link set dev $swp1 down +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + rp1=${NETIFS[p3]} + rp2=${NETIFS[p4]} + + forwarding_enable + vrf_prepare + h1_create + switch_create + vrf2_create +} + +cleanup() +{ + pre_cleanup + + vrf2_destroy + switch_destroy + h1_destroy + vrf_cleanup + forwarding_restore +} + +ipip_payload_get() +{ + local saddr="20:01:0d:b8:00:02:00:00:00:00:00:00:00:00:00:01" + local daddr="20:01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:01" + local flags=$1; shift + local key=$1; shift + + p=$(: + )"$flags"$( : GRE flags + )"0:00:"$( : Reserved + version + )"86:dd:"$( : ETH protocol type + )"$key"$( : Key + )"6"$( : IP version + )"0:0"$( : Traffic class + )"0:00:00:"$( : Flow label + )"00:00:"$( : Payload length + )"3a:"$( : Next header + )"04:"$( : Hop limit + )"$saddr:"$( : IP saddr + )"$daddr:"$( : IP daddr + ) + echo $p +} + +ecn_payload_get() +{ + echo $(ipip_payload_get "0") +} + +ecn_decap_test() +{ + local trap_name="decap_error" + local desc=$1; shift + local ecn_desc=$1; shift + local outer_tos=$1; shift + local mz_pid + + RET=0 + + tc filter add dev $swp1 egress protocol ipv6 pref 1 handle 101 \ + flower src_ip 2001:db8:2::1 dst_ip 2001:db8:1::1 skip_sw \ + action pass + + rp1_mac=$(mac_get $rp1) + rp2_mac=$(mac_get $rp2) + payload=$(ecn_payload_get) + + ip vrf exec v$rp2 $MZ -6 $rp2 -c 0 -d 1msec -a $rp2_mac -b $rp1_mac \ + -A 2001:db8:3::2 -B 2001:db8:3::1 -t ip \ + tos=$outer_tos,next=47,p=$payload -q & + mz_pid=$! + + devlink_trap_exception_test $trap_name + + tc_check_packets "dev $swp1 egress" 101 0 + check_err $? "Packets were not dropped" + + log_test "$desc: Inner ECN is not ECT and outer is $ecn_desc" + + kill $mz_pid && wait $mz_pid &> /dev/null + tc filter del dev $swp1 egress protocol ipv6 pref 1 handle 101 flower +} + +no_matching_tunnel_test() +{ + local trap_name="decap_error" + local desc=$1; shift + local sip=$1; shift + local mz_pid + + RET=0 + + tc filter add dev $swp1 egress protocol ipv6 pref 1 handle 101 \ + flower src_ip 2001:db8:2::1 dst_ip 2001:db8:1::1 action pass + + rp1_mac=$(mac_get $rp1) + rp2_mac=$(mac_get $rp2) + payload=$(ipip_payload_get "$@") + + ip vrf exec v$rp2 $MZ -6 $rp2 -c 0 -d 1msec -a $rp2_mac -b $rp1_mac \ + -A $sip -B 2001:db8:3::1 -t ip next=47,p=$payload -q & + mz_pid=$! + + devlink_trap_exception_test $trap_name + + tc_check_packets "dev $swp1 egress" 101 0 + check_err $? "Packets were not dropped" + + log_test "$desc" + + kill $mz_pid && wait $mz_pid &> /dev/null + tc filter del dev $swp1 egress protocol ipv6 pref 1 handle 101 flower +} + +decap_error_test() +{ + # Correct source IP - the remote address + local sip=2001:db8:3::2 + + ecn_decap_test "Decap error" "ECT(1)" 01 + ecn_decap_test "Decap error" "ECT(0)" 02 + ecn_decap_test "Decap error" "CE" 03 + + no_matching_tunnel_test "Decap error: Source IP check failed" \ + 2001:db8:4::2 "0" + no_matching_tunnel_test \ + "Decap error: Key exists but was not expected" $sip "2" \ + "00:00:00:E9:" + + # Destroy the tunnel and create new one with key + __addr_add_del g1 del 2001:db8:3::1/128 + tunnel_destroy g1 + + tunnel_create g1 ip6gre 2001:db8:3::1 2001:db8:3::2 tos inherit \ + ttl inherit key 233 + __addr_add_del g1 add 2001:db8:3::1/128 + + no_matching_tunnel_test \ + "Decap error: Key does not exist but was expected" $sip "0" + no_matching_tunnel_test \ + "Decap error: Packet has a wrong key field" $sip "2" \ + "00:00:00:E8:" +} + +trap cleanup EXIT + +setup_prepare +setup_wait +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/forwarding.config.sample b/tools/testing/selftests/net/forwarding/forwarding.config.sample index e5e2fbeca22e..bf17e485684f 100644 --- a/tools/testing/selftests/net/forwarding/forwarding.config.sample +++ b/tools/testing/selftests/net/forwarding/forwarding.config.sample @@ -39,5 +39,9 @@ NETIF_CREATE=yes # Timeout (in seconds) before ping exits regardless of how many packets have # been sent or received PING_TIMEOUT=5 +# Flag for tc match, supposed to be skip_sw/skip_hw which means do not process +# filter by software/hardware +TC_FLAG=skip_hw # IPv6 traceroute utility name. TROUTE6=traceroute6 + diff --git a/tools/testing/selftests/net/forwarding/ip6gre_flat.sh b/tools/testing/selftests/net/forwarding/ip6gre_flat.sh new file mode 100755 index 000000000000..96c97064f2d3 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/ip6gre_flat.sh @@ -0,0 +1,65 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Test IP-in-IP GRE tunnel without key. +# This test uses flat topology for IP tunneling tests. See ip6gre_lib.sh for +# more details. + +ALL_TESTS=" + gre_flat + gre_mtu_change +" + +NUM_NETIFS=6 +source lib.sh +source ip6gre_lib.sh + +setup_prepare() +{ + h1=${NETIFS[p1]} + ol1=${NETIFS[p2]} + + ul1=${NETIFS[p3]} + ul2=${NETIFS[p4]} + + ol2=${NETIFS[p5]} + h2=${NETIFS[p6]} + + forwarding_enable + vrf_prepare + h1_create + h2_create + sw1_flat_create $ol1 $ul1 + sw2_flat_create $ol2 $ul2 +} + +gre_flat() +{ + test_traffic_ip4ip6 "GRE flat IPv4-in-IPv6" + test_traffic_ip6ip6 "GRE flat IPv6-in-IPv6" +} + +gre_mtu_change() +{ + test_mtu_change +} + +cleanup() +{ + pre_cleanup + + sw2_flat_destroy $ol2 $ul2 + sw1_flat_destroy $ol1 $ul1 + h2_destroy + h1_destroy + vrf_cleanup + forwarding_restore +} + +trap cleanup EXIT + +setup_prepare +setup_wait +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/ip6gre_flat_key.sh b/tools/testing/selftests/net/forwarding/ip6gre_flat_key.sh new file mode 100755 index 000000000000..ff9fb0db9bd1 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/ip6gre_flat_key.sh @@ -0,0 +1,65 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Test IP-in-IP GRE tunnel with key. +# This test uses flat topology for IP tunneling tests. See ip6gre_lib.sh for +# more details. + +ALL_TESTS=" + gre_flat + gre_mtu_change +" + +NUM_NETIFS=6 +source lib.sh +source ip6gre_lib.sh + +setup_prepare() +{ + h1=${NETIFS[p1]} + ol1=${NETIFS[p2]} + + ul1=${NETIFS[p3]} + ul2=${NETIFS[p4]} + + ol2=${NETIFS[p5]} + h2=${NETIFS[p6]} + + forwarding_enable + vrf_prepare + h1_create + h2_create + sw1_flat_create $ol1 $ul1 key 233 + sw2_flat_create $ol2 $ul2 key 233 +} + +gre_flat() +{ + test_traffic_ip4ip6 "GRE flat IPv4-in-IPv6 with key" + test_traffic_ip6ip6 "GRE flat IPv6-in-IPv6 with key" +} + +gre_mtu_change() +{ + test_mtu_change +} + +cleanup() +{ + pre_cleanup + + sw2_flat_destroy $ol2 $ul2 + sw1_flat_destroy $ol1 $ul1 + h2_destroy + h1_destroy + vrf_cleanup + forwarding_restore +} + +trap cleanup EXIT + +setup_prepare +setup_wait +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/ip6gre_flat_keys.sh b/tools/testing/selftests/net/forwarding/ip6gre_flat_keys.sh new file mode 100755 index 000000000000..12c138785242 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/ip6gre_flat_keys.sh @@ -0,0 +1,65 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Test IP-in-IP GRE tunnel with keys. +# This test uses flat topology for IP tunneling tests. See ip6gre_lib.sh for +# more details. + +ALL_TESTS=" + gre_flat + gre_mtu_change +" + +NUM_NETIFS=6 +source lib.sh +source ip6gre_lib.sh + +setup_prepare() +{ + h1=${NETIFS[p1]} + ol1=${NETIFS[p2]} + + ul1=${NETIFS[p3]} + ul2=${NETIFS[p4]} + + ol2=${NETIFS[p5]} + h2=${NETIFS[p6]} + + forwarding_enable + vrf_prepare + h1_create + h2_create + sw1_flat_create $ol1 $ul1 ikey 111 okey 222 + sw2_flat_create $ol2 $ul2 ikey 222 okey 111 +} + +gre_flat() +{ + test_traffic_ip4ip6 "GRE flat IPv4-in-IPv6 with ikey/okey" + test_traffic_ip6ip6 "GRE flat IPv6-in-IPv6 with ikey/okey" +} + +gre_mtu_change() +{ + test_mtu_change gre +} + +cleanup() +{ + pre_cleanup + + sw2_flat_destroy $ol2 $ul2 + sw1_flat_destroy $ol1 $ul1 + h2_destroy + h1_destroy + vrf_cleanup + forwarding_restore +} + +trap cleanup EXIT + +setup_prepare +setup_wait +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/ip6gre_hier.sh b/tools/testing/selftests/net/forwarding/ip6gre_hier.sh new file mode 100755 index 000000000000..83b55c30a5c3 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/ip6gre_hier.sh @@ -0,0 +1,65 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Test IP-in-IP GRE tunnels without key. +# This test uses hierarchical topology for IP tunneling tests. See +# ip6gre_lib.sh for more details. + +ALL_TESTS=" + gre_hier + gre_mtu_change +" + +NUM_NETIFS=6 +source lib.sh +source ip6gre_lib.sh + +setup_prepare() +{ + h1=${NETIFS[p1]} + ol1=${NETIFS[p2]} + + ul1=${NETIFS[p3]} + ul2=${NETIFS[p4]} + + ol2=${NETIFS[p5]} + h2=${NETIFS[p6]} + + forwarding_enable + vrf_prepare + h1_create + h2_create + sw1_hierarchical_create $ol1 $ul1 + sw2_hierarchical_create $ol2 $ul2 +} + +gre_hier() +{ + test_traffic_ip4ip6 "GRE hierarchical IPv4-in-IPv6" + test_traffic_ip6ip6 "GRE hierarchical IPv6-in-IPv6" +} + +gre_mtu_change() +{ + test_mtu_change gre +} + +cleanup() +{ + pre_cleanup + + sw2_hierarchical_destroy $ol2 $ul2 + sw1_hierarchical_destroy $ol1 $ul1 + h2_destroy + h1_destroy + vrf_cleanup + forwarding_restore +} + +trap cleanup EXIT + +setup_prepare +setup_wait +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/ip6gre_hier_key.sh b/tools/testing/selftests/net/forwarding/ip6gre_hier_key.sh new file mode 100755 index 000000000000..256607916d92 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/ip6gre_hier_key.sh @@ -0,0 +1,65 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Test IP-in-IP GRE tunnels without key. +# This test uses hierarchical topology for IP tunneling tests. See +# ip6gre_lib.sh for more details. + +ALL_TESTS=" + gre_hier + gre_mtu_change +" + +NUM_NETIFS=6 +source lib.sh +source ip6gre_lib.sh + +setup_prepare() +{ + h1=${NETIFS[p1]} + ol1=${NETIFS[p2]} + + ul1=${NETIFS[p3]} + ul2=${NETIFS[p4]} + + ol2=${NETIFS[p5]} + h2=${NETIFS[p6]} + + forwarding_enable + vrf_prepare + h1_create + h2_create + sw1_hierarchical_create $ol1 $ul1 key 22 + sw2_hierarchical_create $ol2 $ul2 key 22 +} + +gre_hier() +{ + test_traffic_ip4ip6 "GRE hierarchical IPv4-in-IPv6 with key" + test_traffic_ip6ip6 "GRE hierarchical IPv6-in-IPv6 with key" +} + +gre_mtu_change() +{ + test_mtu_change gre +} + +cleanup() +{ + pre_cleanup + + sw2_hierarchical_destroy $ol2 $ul2 + sw1_hierarchical_destroy $ol1 $ul1 + h2_destroy + h1_destroy + vrf_cleanup + forwarding_restore +} + +trap cleanup EXIT + +setup_prepare +setup_wait +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/ip6gre_hier_keys.sh b/tools/testing/selftests/net/forwarding/ip6gre_hier_keys.sh new file mode 100755 index 000000000000..ad1bcd6334a8 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/ip6gre_hier_keys.sh @@ -0,0 +1,65 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Test IP-in-IP GRE tunnels without key. +# This test uses hierarchical topology for IP tunneling tests. See +# ip6gre_lib.sh for more details. + +ALL_TESTS=" + gre_hier + gre_mtu_change +" + +NUM_NETIFS=6 +source lib.sh +source ip6gre_lib.sh + +setup_prepare() +{ + h1=${NETIFS[p1]} + ol1=${NETIFS[p2]} + + ul1=${NETIFS[p3]} + ul2=${NETIFS[p4]} + + ol2=${NETIFS[p5]} + h2=${NETIFS[p6]} + + forwarding_enable + vrf_prepare + h1_create + h2_create + sw1_hierarchical_create $ol1 $ul1 ikey 111 okey 222 + sw2_hierarchical_create $ol2 $ul2 ikey 222 okey 111 +} + +gre_hier() +{ + test_traffic_ip4ip6 "GRE hierarchical IPv4-in-IPv6 with ikey/okey" + test_traffic_ip6ip6 "GRE hierarchical IPv6-in-IPv6 with ikey/okey" +} + +gre_mtu_change() +{ + test_mtu_change gre +} + +cleanup() +{ + pre_cleanup + + sw2_hierarchical_destroy $ol2 $ul2 + sw1_hierarchical_destroy $ol1 $ul1 + h2_destroy + h1_destroy + vrf_cleanup + forwarding_restore +} + +trap cleanup EXIT + +setup_prepare +setup_wait +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/ip6gre_lib.sh b/tools/testing/selftests/net/forwarding/ip6gre_lib.sh new file mode 100644 index 000000000000..58a3597037b1 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/ip6gre_lib.sh @@ -0,0 +1,438 @@ +# SPDX-License-Identifier: GPL-2.0 +#!/bin/bash + +# Handles creation and destruction of IP-in-IP or GRE tunnels over the given +# topology. Supports both flat and hierarchical models. +# +# Flat Model: +# Overlay and underlay share the same VRF. +# SW1 uses default VRF so tunnel has no bound dev. +# SW2 uses non-default VRF tunnel has a bound dev. +# +--------------------------------+ +# | H1 | +# | $h1 + | +# | 198.51.100.1/24 | | +# | 2001:db8:1::1/64 | | +# +-------------------------|------+ +# | +# +-------------------------|-------------------+ +# | SW1 | | +# | $ol1 + | +# | 198.51.100.2/24 | +# | 2001:db8:1::2/64 | +# | | +# | + g1a (ip6gre) | +# | loc=2001:db8:3::1 | +# | rem=2001:db8:3::2 --. | +# | tos=inherit | | +# | . | +# | .--------------------- | +# | | | +# | v | +# | + $ul1.111 (vlan) | +# | | 2001:db8:10::1/64 | +# | \ | +# | \____________ | +# | | | +# | VRF default + $ul1 | +# +---------------------|-----------------------+ +# | +# +---------------------|-----------------------+ +# | SW2 | | +# | $ul2 + | +# | ___________| | +# | / | +# | / | +# | + $ul2.111 (vlan) | +# | ^ 2001:db8:10::2/64 | +# | | | +# | | | +# | '----------------------. | +# | + g2a (ip6gre) | | +# | loc=2001:db8:3::2 | | +# | rem=2001:db8:3::1 --' | +# | tos=inherit | +# | | +# | + $ol2 | +# | | 203.0.113.2/24 | +# | VRF v$ol2 | 2001:db8:2::2/64 | +# +---------------------|-----------------------+ +# +---------------------|----------+ +# | H2 | | +# | $h2 + | +# | 203.0.113.1/24 | +# | 2001:db8:2::1/64 | +# +--------------------------------+ +# +# Hierarchical model: +# The tunnel is bound to a device in a different VRF +# +# +--------------------------------+ +# | H1 | +# | $h1 + | +# | 198.51.100.1/24 | | +# | 2001:db8:1::1/64 | | +# +-------------------------|------+ +# | +# +-------------------------|-------------------+ +# | SW1 | | +# | +-----------------------|-----------------+ | +# | | $ol1 + | | +# | | 198.51.100.2/24 | | +# | | 2001:db8:1::2/64 | | +# | | | | +# | | + g1a (ip6gre) | | +# | | loc=2001:db8:3::1 | | +# | | rem=2001:db8:3::2 | | +# | | tos=inherit | | +# | | ^ | | +# | | VRF v$ol1 | | | +# | +--------------------|--------------------+ | +# | | | +# | +--------------------|--------------------+ | +# | | VRF v$ul1 | | | +# | | | | | +# | | v | | +# | | dummy1 + | | +# | | 2001:db8:3::1/64 | | +# | | .-----------' | | +# | | | | | +# | | v | | +# | | + $ul1.111 (vlan) | | +# | | | 2001:db8:10::1/64 | | +# | | \ | | +# | | \__________ | | +# | | | | | +# | | + $ul1 | | +# | +---------------------|-------------------+ | +# +-----------------------|---------------------+ +# | +# +-----------------------|---------------------+ +# | SW2 | | +# | +---------------------|-------------------+ | +# | | + $ul2 | | +# | | _____| | | +# | | / | | +# | | / | | +# | | | $ul2.111 (vlan) | | +# | | + 2001:db8:10::2/64 | | +# | | ^ | | +# | | | | | +# | | '------. | | +# | | dummy2 + | | +# | | 2001:db8:3::2/64 | | +# | | ^ | | +# | | | | | +# | | | | | +# | | VRF v$ul2 | | | +# | +---------------------|-------------------+ | +# | | | +# | +---------------------|-------------------+ | +# | | VRF v$ol2 | | | +# | | | | | +# | | v | | +# | | g2a (ip6gre) + | | +# | | loc=2001:db8:3::2 | | +# | | rem=2001:db8:3::1 | | +# | | tos=inherit | | +# | | | | +# | | $ol2 + | | +# | | 203.0.113.2/24 | | | +# | | 2001:db8:2::2/64 | | | +# | +---------------------|-------------------+ | +# +-----------------------|---------------------+ +# | +# +-----------------------|--------+ +# | H2 | | +# | $h2 + | +# | 203.0.113.1/24 | +# | 2001:db8:2::1/64 | +# +--------------------------------+ + +source lib.sh +source tc_common.sh + +h1_create() +{ + simple_if_init $h1 198.51.100.1/24 2001:db8:1::1/64 + ip route add vrf v$h1 203.0.113.0/24 via 198.51.100.2 + ip -6 route add vrf v$h1 2001:db8:2::/64 via 2001:db8:1::2 +} + +h1_destroy() +{ + ip -6 route del vrf v$h1 2001:db8:2::/64 via 2001:db8:1::2 + ip route del vrf v$h1 203.0.113.0/24 via 198.51.100.2 + simple_if_fini $h1 198.51.100.1/24 2001:db8:1::1/64 +} + +h2_create() +{ + simple_if_init $h2 203.0.113.1/24 2001:db8:2::1/64 + ip route add vrf v$h2 198.51.100.0/24 via 203.0.113.2 + ip -6 route add vrf v$h2 2001:db8:1::/64 via 2001:db8:2::2 +} + +h2_destroy() +{ + ip -6 route del vrf v$h2 2001:db8:1::/64 via 2001:db8:2::2 + ip route del vrf v$h2 198.51.100.0/24 via 203.0.113.2 + simple_if_fini $h2 203.0.113.1/24 2001:db8:2::1/64 +} + +sw1_flat_create() +{ + local ol1=$1; shift + local ul1=$1; shift + + ip link set dev $ol1 up + __addr_add_del $ol1 add 198.51.100.2/24 2001:db8:1::2/64 + + ip link set dev $ul1 up + vlan_create $ul1 111 "" 2001:db8:10::1/64 + + tunnel_create g1a ip6gre 2001:db8:3::1 2001:db8:3::2 tos inherit \ + ttl inherit "$@" + ip link set dev g1a up + __addr_add_del g1a add "2001:db8:3::1/128" + + ip -6 route add 2001:db8:3::2/128 via 2001:db8:10::2 + ip route add 203.0.113.0/24 dev g1a + ip -6 route add 2001:db8:2::/64 dev g1a +} + +sw1_flat_destroy() +{ + local ol1=$1; shift + local ul1=$1; shift + + ip -6 route del 2001:db8:2::/64 + ip route del 203.0.113.0/24 + ip -6 route del 2001:db8:3::2/128 via 2001:db8:10::2 + + __simple_if_fini g1a 2001:db8:3::1/128 + tunnel_destroy g1a + + vlan_destroy $ul1 111 + __simple_if_fini $ul1 + __simple_if_fini $ol1 198.51.100.2/24 2001:db8:1::2/64 +} + +sw2_flat_create() +{ + local ol2=$1; shift + local ul2=$1; shift + + simple_if_init $ol2 203.0.113.2/24 2001:db8:2::2/64 + __simple_if_init $ul2 v$ol2 + vlan_create $ul2 111 v$ol2 2001:db8:10::2/64 + + tunnel_create g2a ip6gre 2001:db8:3::2 2001:db8:3::1 tos inherit \ + ttl inherit dev v$ol2 "$@" + __simple_if_init g2a v$ol2 2001:db8:3::2/128 + + # Replace neighbor to avoid 1 dropped packet due to "unresolved neigh" + ip neigh replace dev $ol2 203.0.113.1 lladdr $(mac_get $h2) + ip -6 neigh replace dev $ol2 2001:db8:2::1 lladdr $(mac_get $h2) + + ip -6 route add vrf v$ol2 2001:db8:3::1/128 via 2001:db8:10::1 + ip route add vrf v$ol2 198.51.100.0/24 dev g2a + ip -6 route add vrf v$ol2 2001:db8:1::/64 dev g2a +} + +sw2_flat_destroy() +{ + local ol2=$1; shift + local ul2=$1; shift + + ip -6 route del vrf v$ol2 2001:db8:2::/64 + ip route del vrf v$ol2 198.51.100.0/24 + ip -6 route del vrf v$ol2 2001:db8:3::1/128 via 2001:db8:10::1 + + __simple_if_fini g2a 2001:db8:3::2/128 + tunnel_destroy g2a + + vlan_destroy $ul2 111 + __simple_if_fini $ul2 + simple_if_fini $ol2 203.0.113.2/24 2001:db8:2::2/64 +} + +sw1_hierarchical_create() +{ + local ol1=$1; shift + local ul1=$1; shift + + simple_if_init $ol1 198.51.100.2/24 2001:db8:1::2/64 + simple_if_init $ul1 + ip link add name dummy1 type dummy + __simple_if_init dummy1 v$ul1 2001:db8:3::1/64 + + vlan_create $ul1 111 v$ul1 2001:db8:10::1/64 + tunnel_create g1a ip6gre 2001:db8:3::1 2001:db8:3::2 tos inherit \ + ttl inherit dev dummy1 "$@" + ip link set dev g1a master v$ol1 + + ip -6 route add vrf v$ul1 2001:db8:3::2/128 via 2001:db8:10::2 + ip route add vrf v$ol1 203.0.113.0/24 dev g1a + ip -6 route add vrf v$ol1 2001:db8:2::/64 dev g1a +} + +sw1_hierarchical_destroy() +{ + local ol1=$1; shift + local ul1=$1; shift + + ip -6 route del vrf v$ol1 2001:db8:2::/64 + ip route del vrf v$ol1 203.0.113.0/24 + ip -6 route del vrf v$ul1 2001:db8:3::2/128 + + tunnel_destroy g1a + vlan_destroy $ul1 111 + + __simple_if_fini dummy1 2001:db8:3::1/64 + ip link del dev dummy1 + + simple_if_fini $ul1 + simple_if_fini $ol1 198.51.100.2/24 2001:db8:1::2/64 +} + +sw2_hierarchical_create() +{ + local ol2=$1; shift + local ul2=$1; shift + + simple_if_init $ol2 203.0.113.2/24 2001:db8:2::2/64 + simple_if_init $ul2 + + ip link add name dummy2 type dummy + __simple_if_init dummy2 v$ul2 2001:db8:3::2/64 + + vlan_create $ul2 111 v$ul2 2001:db8:10::2/64 + tunnel_create g2a ip6gre 2001:db8:3::2 2001:db8:3::1 tos inherit \ + ttl inherit dev dummy2 "$@" + ip link set dev g2a master v$ol2 + + # Replace neighbor to avoid 1 dropped packet due to "unresolved neigh" + ip neigh replace dev $ol2 203.0.113.1 lladdr $(mac_get $h2) + ip -6 neigh replace dev $ol2 2001:db8:2::1 lladdr $(mac_get $h2) + + ip -6 route add vrf v$ul2 2001:db8:3::1/128 via 2001:db8:10::1 + ip route add vrf v$ol2 198.51.100.0/24 dev g2a + ip -6 route add vrf v$ol2 2001:db8:1::/64 dev g2a +} + +sw2_hierarchical_destroy() +{ + local ol2=$1; shift + local ul2=$1; shift + + ip -6 route del vrf v$ol2 2001:db8:2::/64 + ip route del vrf v$ol2 198.51.100.0/24 + ip -6 route del vrf v$ul2 2001:db8:3::1/128 + + tunnel_destroy g2a + vlan_destroy $ul2 111 + + __simple_if_fini dummy2 2001:db8:3::2/64 + ip link del dev dummy2 + + simple_if_fini $ul2 + simple_if_fini $ol2 203.0.113.2/24 2001:db8:2::2/64 +} + +test_traffic_ip4ip6() +{ + RET=0 + + h1mac=$(mac_get $h1) + ol1mac=$(mac_get $ol1) + + tc qdisc add dev $ul1 clsact + tc filter add dev $ul1 egress proto all pref 1 handle 101 \ + flower $TC_FLAG action pass + + tc qdisc add dev $ol2 clsact + tc filter add dev $ol2 egress protocol ipv4 pref 1 handle 101 \ + flower $TC_FLAG dst_ip 203.0.113.1 action pass + + $MZ $h1 -c 1000 -p 64 -a $h1mac -b $ol1mac -A 198.51.100.1 \ + -B 203.0.113.1 -t ip -q -d 1msec + + # Check ports after encap and after decap. + tc_check_at_least_x_packets "dev $ul1 egress" 101 1000 + check_err $? "Packets did not go through $ul1, tc_flag = $TC_FLAG" + + tc_check_at_least_x_packets "dev $ol2 egress" 101 1000 + check_err $? "Packets did not go through $ol2, tc_flag = $TC_FLAG" + + log_test "$@" + + tc filter del dev $ol2 egress protocol ipv4 pref 1 handle 101 flower + tc qdisc del dev $ol2 clsact + tc filter del dev $ul1 egress proto all pref 1 handle 101 flower + tc qdisc del dev $ul1 clsact +} + +test_traffic_ip6ip6() +{ + RET=0 + + h1mac=$(mac_get $h1) + ol1mac=$(mac_get $ol1) + + tc qdisc add dev $ul1 clsact + tc filter add dev $ul1 egress proto all pref 1 handle 101 \ + flower $TC_FLAG action pass + + tc qdisc add dev $ol2 clsact + tc filter add dev $ol2 egress protocol ipv6 pref 1 handle 101 \ + flower $TC_FLAG dst_ip 2001:db8:2::1 action pass + + $MZ -6 $h1 -c 1000 -p 64 -a $h1mac -b $ol1mac -A 2001:db8:1::1 \ + -B 2001:db8:2::1 -t ip -q -d 1msec + + # Check ports after encap and after decap. + tc_check_at_least_x_packets "dev $ul1 egress" 101 1000 + check_err $? "Packets did not go through $ul1, tc_flag = $TC_FLAG" + + tc_check_at_least_x_packets "dev $ol2 egress" 101 1000 + check_err $? "Packets did not go through $ol2, tc_flag = $TC_FLAG" + + log_test "$@" + + tc filter del dev $ol2 egress protocol ipv6 pref 1 handle 101 flower + tc qdisc del dev $ol2 clsact + tc filter del dev $ul1 egress proto all pref 1 handle 101 flower + tc qdisc del dev $ul1 clsact +} + +topo_mtu_change() +{ + local mtu=$1 + + ip link set mtu $mtu dev $h1 + ip link set mtu $mtu dev $ol1 + ip link set mtu $mtu dev g1a + ip link set mtu $mtu dev $ul1 + ip link set mtu $mtu dev $ul1.111 + ip link set mtu $mtu dev $h2 + ip link set mtu $mtu dev $ol2 + ip link set mtu $mtu dev g2a + ip link set mtu $mtu dev $ul2 + ip link set mtu $mtu dev $ul2.111 +} + +test_mtu_change() +{ + RET=0 + + ping6_do $h1 2001:db8:2::1 "-s 1800 -w 3" + check_fail $? "ping GRE IPv6 should not pass with packet size 1800" + + RET=0 + + topo_mtu_change 2000 + ping6_do $h1 2001:db8:2::1 "-s 1800 -w 3" + check_err $? + log_test "ping GRE IPv6, packet size 1800 after MTU change" +} diff --git a/tools/testing/selftests/net/forwarding/tc_common.sh b/tools/testing/selftests/net/forwarding/tc_common.sh index 0e18e8be6e2a..bce8bb8d2b6f 100644 --- a/tools/testing/selftests/net/forwarding/tc_common.sh +++ b/tools/testing/selftests/net/forwarding/tc_common.sh @@ -16,6 +16,16 @@ tc_check_packets() tc_rule_handle_stats_get "$id" "$handle" > /dev/null } +tc_check_at_least_x_packets() +{ + local id=$1 + local handle=$2 + local count=$3 + + busywait "$TC_HIT_TIMEOUT" until_counter_is ">= $count" \ + tc_rule_handle_stats_get "$id" "$handle" > /dev/null +} + tc_check_packets_hitting() { local id=$1 diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 255793c5ac4f..293d349e21fe 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -945,12 +945,15 @@ subflows_tests() # subflow limited by client reset + ip netns exec $ns1 ./pm_nl_ctl limits 0 0 + ip netns exec $ns2 ./pm_nl_ctl limits 0 0 ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "single subflow, limited by client" 0 0 0 # subflow limited by server reset + ip netns exec $ns1 ./pm_nl_ctl limits 0 0 ip netns exec $ns2 ./pm_nl_ctl limits 0 1 ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 @@ -973,7 +976,7 @@ subflows_tests() run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "multiple subflows" 2 2 2 - # multiple subflows limited by serverf + # multiple subflows limited by server reset ip netns exec $ns1 ./pm_nl_ctl limits 0 1 ip netns exec $ns2 ./pm_nl_ctl limits 0 2 diff --git a/tools/testing/selftests/net/mptcp/pm_netlink.sh b/tools/testing/selftests/net/mptcp/pm_netlink.sh index 3c741abe034e..cbacf9f6538b 100755 --- a/tools/testing/selftests/net/mptcp/pm_netlink.sh +++ b/tools/testing/selftests/net/mptcp/pm_netlink.sh @@ -70,7 +70,7 @@ check() check "ip netns exec $ns1 ./pm_nl_ctl dump" "" "defaults addr list" check "ip netns exec $ns1 ./pm_nl_ctl limits" "accept 0 -subflows 0" "defaults limits" +subflows 2" "defaults limits" ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.1 ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.2 flags subflow dev lo @@ -118,11 +118,11 @@ check "ip netns exec $ns1 ./pm_nl_ctl dump" "" "flush addrs" ip netns exec $ns1 ./pm_nl_ctl limits 9 1 check "ip netns exec $ns1 ./pm_nl_ctl limits" "accept 0 -subflows 0" "rcv addrs above hard limit" +subflows 2" "rcv addrs above hard limit" ip netns exec $ns1 ./pm_nl_ctl limits 1 9 check "ip netns exec $ns1 ./pm_nl_ctl limits" "accept 0 -subflows 0" "subflows above hard limit" +subflows 2" "subflows above hard limit" ip netns exec $ns1 ./pm_nl_ctl limits 8 8 check "ip netns exec $ns1 ./pm_nl_ctl limits" "accept 8 diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index 97fceb9be9ed..d3047e251fe9 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -29,6 +29,8 @@ struct tls_crypto_info_keys { union { struct tls12_crypto_info_aes_gcm_128 aes128; struct tls12_crypto_info_chacha20_poly1305 chacha20; + struct tls12_crypto_info_sm4_gcm sm4gcm; + struct tls12_crypto_info_sm4_ccm sm4ccm; }; size_t len; }; @@ -49,6 +51,16 @@ static void tls_crypto_info_init(uint16_t tls_version, uint16_t cipher_type, tls12->aes128.info.version = tls_version; tls12->aes128.info.cipher_type = cipher_type; break; + case TLS_CIPHER_SM4_GCM: + tls12->len = sizeof(struct tls12_crypto_info_sm4_gcm); + tls12->sm4gcm.info.version = tls_version; + tls12->sm4gcm.info.cipher_type = cipher_type; + break; + case TLS_CIPHER_SM4_CCM: + tls12->len = sizeof(struct tls12_crypto_info_sm4_ccm); + tls12->sm4ccm.info.version = tls_version; + tls12->sm4ccm.info.cipher_type = cipher_type; + break; default: break; } @@ -148,13 +160,13 @@ FIXTURE_VARIANT(tls) uint16_t cipher_type; }; -FIXTURE_VARIANT_ADD(tls, 12_gcm) +FIXTURE_VARIANT_ADD(tls, 12_aes_gcm) { .tls_version = TLS_1_2_VERSION, .cipher_type = TLS_CIPHER_AES_GCM_128, }; -FIXTURE_VARIANT_ADD(tls, 13_gcm) +FIXTURE_VARIANT_ADD(tls, 13_aes_gcm) { .tls_version = TLS_1_3_VERSION, .cipher_type = TLS_CIPHER_AES_GCM_128, @@ -172,6 +184,18 @@ FIXTURE_VARIANT_ADD(tls, 13_chacha) .cipher_type = TLS_CIPHER_CHACHA20_POLY1305, }; +FIXTURE_VARIANT_ADD(tls, 13_sm4_gcm) +{ + .tls_version = TLS_1_3_VERSION, + .cipher_type = TLS_CIPHER_SM4_GCM, +}; + +FIXTURE_VARIANT_ADD(tls, 13_sm4_ccm) +{ + .tls_version = TLS_1_3_VERSION, + .cipher_type = TLS_CIPHER_SM4_CCM, +}; + FIXTURE_SETUP(tls) { struct tls_crypto_info_keys tls12;